system

Abstract

An object of the system according to the embodiment is to improve the quality of customer experience by performing customer simulation using VR.SOLUTION: A system according to an embodiment includes a setting unit, a generation unit, a response unit, an experience unit, a determination unit, and a feedback unit. The setting unit sets a persona of the customer. The generation unit generates a customer avatar based on the persona set by the setting unit. The response unit generates a response of the customer avatar generated by the generation unit. The experience unit performs a customer service experience based on the response generated by the response unit. The determination unit determines the customer service experience performed by the experience unit. The feedback unit provides feedback based on the determination result obtained by the determination unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology does not adequately simulate the quality of customer service experiences, leaving room for improvement.

[0005] The system according to the embodiment aims to improve the quality of customer service experience by using VR to perform customer simulations. [Means for solving the problem]

[0006] The system according to the embodiment includes a setting unit, a generation unit, a response unit, an experience unit, a determination unit, and a feedback unit. The setting unit sets a customer persona. The generation unit generates a customer avatar based on the persona set by the setting unit. The response unit generates a response of the customer avatar generated by the generation unit. The experience unit provides a customer service experience based on the response generated by the response unit. The determination unit determines the customer service experience provided by the experience unit. The feedback unit provides feedback based on the determination result obtained by the determination unit. [Effects of the Invention]

[0007] The system according to the embodiment uses VR to perform customer simulations, improving the quality of customer service experiences. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The VR customer simulation service according to an embodiment of the present invention is a system that uses a generative AI to generate customer avatars and responses. By setting a customer persona in advance, users can recreate various situations and engage in customer service experiences. After the customer service experience, they can receive AI evaluations and feedback, enabling them to improve their customer service level. Furthermore, using the VR customer simulator allows for employee training anytime, anywhere, resulting in higher quality service. For example, a user sets a customer persona and inputs information such as age, gender, occupation, and hobbies. The generative AI then generates a customer avatar and responses based on this information. For example, a young female customer avatar is generated, and a scenario is recreated in which the avatar asks the user a question or makes a request. After the customer service experience ends, the AI ​​evaluates the user's response and provides feedback, including whether the user's response was appropriate and what needs improvement. This allows users to improve their customer service skills. Furthermore, using the VR customer simulator enables employee training independent of physical location. For example, employees can receive training anywhere, such as their office or home, simply by wearing a VR headset. This improves training efficiency and enables the provision of higher quality service. As a result, the VR customer simulation service can perform everything from customer persona creation to customer service experience, judgment, and feedback in a consistent manner. This allows users to improve their customer service skills. It also makes it possible to conduct employee training without relying on physical locations, improving training efficiency and enabling the provision of higher quality service.

[0029] A VR customer simulation service according to an embodiment includes a setting unit, a generation unit, a response unit, an experience unit, a determination unit, and a feedback unit. The setting unit sets a customer persona. The customer persona includes, for example, but is not limited to, information such as age, gender, occupation, and hobbies. The generation unit uses a generation AI to generate a customer avatar based on the persona set by the setting unit. The generation AI generates the customer avatar using, for example, technology such as deep learning or a generative model. The response unit uses the generation AI to generate responses for the customer avatar generated by the generation unit. The generation AI generates responses for the customer avatar using, for example, natural language processing technology. The experience unit provides a customer service experience based on the responses of the generated customer avatar. The customer service experience includes, for example, but is not limited to, a scenario and an interaction method. The determination unit determines the result of the customer service experience. The determination includes, for example, but is not limited to, evaluation criteria such as customer satisfaction and response accuracy. The feedback unit provides feedback based on the determination result obtained by the determination unit. The feedback may include, but is not limited to, specific improvements and training methods. As a result, the VR customer simulation service according to the embodiment can consistently perform everything from customer persona setting to customer service experience, evaluation, and feedback.

[0030] The setting unit can set the age, gender, occupation, hobbies, and other information of the customer. For example, the setting unit can set the age, gender, occupation, hobbies, and other information of the customer. For example, the setting unit can collect customer information using a questionnaire. The setting unit can also acquire customer information from a database. Furthermore, the setting unit can also allow the user to manually input customer information. This makes it possible to set detailed persona information of the customer.

[0031] The generation unit can generate a customer avatar using a generation AI. The generation unit generates a customer avatar using, for example, the generation AI. The generation AI generates a customer avatar using, for example, deep learning technology. The generation unit can also generate a customer avatar using a generative model. For example, the generation unit inputs customer persona information into the generation AI to generate a customer avatar. This makes it possible to generate a realistic customer avatar using the generation AI.

[0032] The response unit can generate a response for the customer avatar using a generation AI. The response unit generates a response for the customer avatar using, for example, a generation AI. The generation AI generates a response for the customer avatar using, for example, natural language processing technology. The response unit can also generate a response for the customer avatar using a generative model. For example, the response unit inputs information about the customer avatar into the generation AI to generate a response. This allows the generation AI to generate a response for the customer avatar.

[0033] The experience unit can provide a customer service experience based on the responses of the generated customer avatar. The experience unit provides a customer service experience based on, for example, the responses of the generated customer avatar. The customer service experience includes, for example, a scenario and an interaction method. For example, the experience unit provides a scenario in which the user can have a customer service experience based on the responses of the customer avatar. The experience unit also sets an interaction method so that the user can interact with the customer avatar. This allows a customer service experience to be provided based on the responses of the generated customer avatar.

[0034] The determination unit can determine the result of the customer service experience. The determination unit, for example, determines the result of the customer service experience. The determination includes evaluation criteria such as customer satisfaction and accuracy of response. For example, the determination unit determines whether the user's response was appropriate based on the result of the customer service experience. The determination unit can also identify areas for improvement in the user's response based on the result of the customer service experience. This makes it possible to determine the result of the customer service experience.

[0035] The feedback unit can provide feedback based on the determination result. The feedback unit provides feedback based on, for example, the determination result. The feedback includes, for example, specific areas for improvement and training methods. For example, the feedback unit indicates specific areas for improvement in the user's response based on the determination result. The feedback unit can also suggest training methods for improving the user's customer service skills. In this way, feedback can be provided based on the determination result.

[0036] The experience unit can provide a customer service experience using a VR customer simulator. The experience unit can provide a customer service experience using, for example, a VR customer simulator. The VR customer simulator includes, for example, a simulation environment and an interaction method. For example, the experience unit can enable a user to provide a customer service experience in a virtual environment by wearing a VR headset. The experience unit can also use the VR customer simulator to enable a user to provide a customer service experience independent of a physical location. This allows the customer service experience to be provided using the VR customer simulator.

[0037] The feedback unit can provide feedback that contributes to improving customer service skills. The feedback unit provides, for example, feedback that contributes to improving customer service skills. The feedback includes, for example, specific areas for improvement and training methods. For example, the feedback unit can specifically indicate areas for improvement in the user's response, contributing to improving customer service skills. The feedback unit can also suggest training methods for improving the user's customer service skills. In this way, it is possible to provide feedback that contributes to improving customer service skills.

[0038] The setting unit can suggest an appropriate persona by referring to the user's past customer service history when setting a customer persona. For example, the setting unit can suggest an appropriate persona by referring to the user's past customer service history when setting a customer persona. The past customer service history is acquired, for example, from a database. For example, the setting unit automatically suggests an optimal persona based on data on customers the user has dealt with in the past. The setting unit can also extract specific patterns from the user's past customer service history and suggest a persona based on the extracted patterns. Furthermore, the setting unit suggests an optimal persona by referring to customer service scenarios that the user has received high ratings for in the past. This makes it possible to suggest an optimal persona by referring to the user's past customer service history.

[0039] The setting unit can customize the persona based on the user's current work situation and goals when setting the customer persona. For example, the setting unit customizes the persona based on the user's current work situation and goals when setting the customer persona. The current work situation and goals are collected, for example, from a work report or a goal setting sheet. For example, the setting unit customizes the characteristics of the persona based on the user's current work goals. The setting unit can also set an optimal persona taking into account the user's work situation (busyness, work content, etc.). Furthermore, the setting unit adjusts the persona settings based on the user's short-term and long-term goals. This makes it possible to customize the persona based on the user's current work situation and goals.

[0040] The setting unit can improve the accuracy of the persona setting by reflecting user feedback when setting a customer persona. For example, the setting unit improves the accuracy of the persona setting by reflecting user feedback when setting a customer persona. User feedback is collected, for example, through questionnaires or interviews. For example, the setting unit improves the persona setting algorithm based on the feedback provided by the user. The setting unit can also improve the accuracy of the persona setting by reflecting user feedback in real time. Furthermore, the setting unit analyzes user feedback and optimizes parameters for persona setting. This makes it possible to improve the accuracy of the persona setting by reflecting user feedback.

[0041] The setting unit can prioritize a highly relevant persona in consideration of the user's geographical location information when setting a customer persona. For example, the setting unit prioritizes a highly relevant persona in consideration of the user's geographical location information when setting a customer persona. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the setting unit prioritizes a region-specific persona based on the user's current location. The setting unit can also suggest a persona suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the setting unit sets a persona according to the needs of the region in consideration of the user's location information. This makes it possible to prioritize a highly relevant persona in consideration of the user's geographical location information.

[0042] The setting unit can analyze the user's social media activity and set a related persona when setting a customer persona. For example, the setting unit analyzes the user's social media activity and sets a related persona when setting a customer persona. Social media activity is collected, for example, through an analysis of posted content and an analysis of followers. For example, the setting unit analyzes the content of the user's social media posts and sets a related persona. The setting unit can also set a related persona by referring to the activity of the user's friends on social media. Furthermore, the setting unit sets a related persona based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and a related persona can be set.

[0043] The setting unit can customize the setting method by reflecting the user's past feedback when setting a customer persona. For example, the setting unit customizes the setting method by reflecting the user's past feedback when setting a customer persona. Past feedback is collected, for example, through questionnaires or interviews. For example, the setting unit customizes the persona setting procedure based on the user's past feedback. The setting unit can also analyze the user's feedback and optimize the setting method. Furthermore, the setting unit improves the persona setting interface by referring to the user's past feedback. This makes it possible to customize the setting method by reflecting the user's past feedback.

[0044] The generation unit can adjust the accuracy of generation based on the level of detail of the persona when generating a customer avatar. For example, the generation unit adjusts the accuracy of generation based on the level of detail of the persona when generating a customer avatar. The level of detail of the persona is evaluated based on, for example, the number of attribute information pieces and detailed descriptions. For example, when the level of detail of the persona is high, the generation unit generates a more realistic customer avatar. Also, when the level of detail of the persona is low, the generation unit can generate a simple customer avatar. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar to be generated depending on the level of detail of the persona. This makes it possible to adjust the accuracy of generation based on the level of detail of the persona.

[0045] The generation unit can apply different generation algorithms depending on the category of the persona when generating a customer avatar. For example, the generation unit applies different generation algorithms depending on the category of the persona when generating a customer avatar. Persona categories are classified based on, for example, age group, occupation, hobby, etc. For example, the generation unit can apply an algorithm that generates a customer avatar with a professional appearance to a business person persona. Furthermore, the generation unit can apply an algorithm that generates a customer avatar with a casual appearance to a student persona. Furthermore, the generation unit can apply an algorithm that generates a customer avatar with a friendly appearance to an elderly person persona. In this way, different generation algorithms can be applied depending on the category of the persona.

[0046] The generation unit can improve the accuracy of generation when generating a customer avatar by referring to the user's past generation results. For example, when generating a customer avatar, the generation unit improves the accuracy of generation by referring to the user's past generation results. The past generation results are obtained, for example, from a database. For example, the generation unit improves the accuracy of generation based on data of customer avatars generated by the user in the past. The generation unit can also analyze the user's past generation results and optimize the generation algorithm. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar by referring to the user's past generation results. This makes it possible to improve the accuracy of generation by referring to the user's past generation results.

[0047] The generation unit can determine the generation priority based on the time of persona submission when generating a customer avatar. For example, the generation unit determines the generation priority based on the time of persona submission when generating a customer avatar. The time of persona submission is collected, for example, by recording the submission date and time or managing the submission order. For example, if a persona has been submitted recently, the generation unit preferentially generates a customer avatar based on that persona. The generation unit can also adjust the generation priority based on the time of persona submission. Furthermore, the generation unit sets a low generation priority for personas that have been submitted recently. This makes it possible to determine the generation priority based on the time of persona submission.

[0048] The generation unit can adjust the order of generation based on the relevance of personas when generating customer avatars. For example, the generation unit adjusts the order of generation based on the relevance of personas when generating customer avatars. The relevance of personas is evaluated based on, for example, common attributes or related interests. For example, if a persona has high relevance, the generation unit preferentially generates a customer avatar based on that persona. The generation unit can also adjust the order of generation based on the relevance of personas. Furthermore, the generation unit postpones the generation order for personas with low relevance. This makes it possible to adjust the order of generation based on the relevance of personas.

[0049] The generation unit can adjust the level of detail of the customer avatar generation in accordance with the user's level of expertise. For example, the generation unit adjusts the level of detail of the customer avatar generation in accordance with the user's level of expertise. The user's level of expertise is evaluated based on, for example, qualification information, work experience, etc. For example, the generation unit generates a detailed customer avatar when the user's level of expertise is high. Alternatively, the generation unit can generate a simple customer avatar when the user's level of expertise is low. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar to be generated in accordance with the user's level of expertise. This allows the level of detail of the customer avatar generation to be adjusted in accordance with the user's level of expertise.

[0050] The response unit can adjust the accuracy of the response based on the level of detail of the persona when generating a response for the customer avatar. For example, the response unit adjusts the accuracy of the response based on the level of detail of the persona when generating a response for the customer avatar. The level of detail of the persona is evaluated based on, for example, the number of attribute information items and detailed descriptions. For example, when the level of detail of the persona is high, the response unit generates more realistic response content. Furthermore, when the level of detail of the persona is low, the response unit can also generate simple response content. Furthermore, the response unit adjusts the level of detail of the response content to be generated depending on the level of detail of the persona. This makes it possible to adjust the accuracy of the response based on the level of detail of the persona.

[0051] The response unit can apply different response algorithms depending on the category of the persona when generating a response for the customer avatar. For example, the response unit applies different response algorithms depending on the category of the persona when generating a response for the customer avatar. Persona categories are classified based on, for example, age group, occupation, hobby, etc. For example, the response unit can apply an algorithm that generates professional response content to a business person persona. The response unit can also apply an algorithm that generates casual response content to a student persona. Furthermore, the response unit can apply an algorithm that generates friendly response content to an elderly persona. In this way, different response algorithms can be applied depending on the category of the persona.

[0052] The response unit can improve the accuracy of the response when generating a response for the customer avatar by referring to the user's past response results. For example, the response unit improves the accuracy of the response when generating a response for the customer avatar by referring to the user's past response results. The past response results are obtained, for example, from a database. For example, the response unit improves the accuracy of the response based on the responses generated by the user in the past. The response unit can also analyze the user's past response results and optimize the response algorithm. Furthermore, the response unit adjusts the response content of the customer avatar by referring to the user's past response results. This makes it possible to improve the accuracy of the response by referring to the user's past response results.

[0053] The response unit can determine the priority of responses based on the submission time of the persona when generating a response for the customer avatar. For example, the response unit determines the priority of responses based on the submission time of the persona when generating a response for the customer avatar. The submission time of the persona is collected, for example, by recording the submission date and time or managing the submission order. For example, if a persona has been submitted recently, the response unit preferentially generates a response based on that persona. The response unit can also adjust the priority of responses based on the submission time of the persona. Furthermore, the response unit sets a lower priority for a persona that was submitted earlier. This makes it possible to determine the priority of responses based on the submission time of the persona.

[0054] The response unit can adjust the order of responses based on the relevance of the persona when generating responses for the customer avatar. For example, the response unit adjusts the order of responses based on the relevance of the persona when generating responses for the customer avatar. The relevance of the persona is evaluated based on, for example, common attributes or related interests. For example, if the relevance of a persona is high, the response unit preferentially generates a response based on that persona. The response unit can also adjust the order of responses based on the relevance of the persona. Furthermore, the response unit postpones the order of responses for personas with low relevance. This makes it possible to adjust the order of responses based on the relevance of the persona.

[0055] The response unit can adjust the level of detail of the response according to the user's expertise level when generating a response for the customer avatar. For example, the response unit adjusts the level of detail of the response according to the user's expertise level when generating a response for the customer avatar. The user's expertise level is evaluated based on, for example, qualification information, work experience, etc. For example, the response unit generates a detailed response content when the user's expertise level is high. Furthermore, the response unit can also generate a simple response content when the user's expertise level is low. Furthermore, the response unit adjusts the level of detail of the generated response content according to the user's expertise level. This makes it possible to adjust the level of detail of the response according to the user's expertise level.

[0056] The experience unit can adjust the level of detail of the experience based on the response content of the customer avatar during the customer service experience. For example, the experience unit adjusts the level of detail of the experience based on the response content of the customer avatar during the customer service experience. The response content of the customer avatar is generated based on, for example, natural language processing technology, the tone and content of the response, etc. For example, the experience unit increases the level of detail of the experience when the response content of the customer avatar is detailed. Furthermore, the experience unit can decrease the level of detail of the experience when the response content of the customer avatar is simple. Furthermore, the experience unit adjusts the level of detail of the experience according to the response content of the customer avatar. In this way, the level of detail of the experience can be adjusted based on the response content of the customer avatar.

[0057] The experience unit can provide an optimal experiential scenario by referring to the user's past experience history during a customer service experience. For example, the experience unit can provide an optimal experiential scenario by referring to the user's past experience history during a customer service experience. The past experience history is acquired, for example, from a database. For example, the experience unit provides an optimal experiential scenario based on the user's past experience history. The experience unit can also extract a specific pattern from the user's past experience history and provide an experiential scenario based on that. Furthermore, the experience unit analyzes the user's past experience history and provides the most effective experiential scenario. This makes it possible to provide an optimal experiential scenario by referring to the user's past experience history.

[0058] The experience unit can improve the experience scenario by reflecting user feedback during the customer service experience. For example, the experience unit improves the experience scenario by reflecting user feedback during the customer service experience. User feedback is collected, for example, through questionnaires or interviews. For example, the experience unit improves the experience scenario based on the user feedback. The experience unit can also reflect user feedback in real time and optimize the experience scenario. Furthermore, the experience unit analyzes the user feedback and adjusts the parameters of the experience scenario. In this way, the experience scenario can be improved by reflecting user feedback.

[0059] The experience unit can provide a highly relevant experiential scenario by taking into account the user's geographical location information during a customer service experience. For example, the experience unit can provide a highly relevant experiential scenario by taking into account the user's geographical location information during a customer service experience. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the experience unit can provide a region-specific experiential scenario based on the user's current location. The experience unit can also provide an experiential scenario suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the experience unit can provide an experiential scenario tailored to the needs of the region by taking into account the user's location information. This makes it possible to provide a highly relevant experiential scenario by taking into account the user's geographical location information.

[0060] The experience unit can analyze the user's social media activity during the customer service experience and provide a related experience scenario. The experience unit, for example, analyzes the user's social media activity during the customer service experience and provides a related experience scenario. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the experience unit analyzes the user's social media posts and provides a related experience scenario. The experience unit can also provide a related experience scenario by referring to the activity of the user's friends on social media. Furthermore, the experience unit provides a related experience scenario based on the user's social media check-in information. In this way, the user's social media activity can be analyzed and a related experience scenario can be provided.

[0061] The experience unit can customize the experience scenario by reflecting the user's past feedback during the customer service experience. The experience unit, for example, customizes the experience scenario by reflecting the user's past feedback during the customer service experience. Past feedback is collected, for example, through questionnaires or interviews. For example, the experience unit customizes the experience scenario based on the user's past feedback. The experience unit can also analyze the user's feedback and optimize the experience scenario. Furthermore, the experience unit improves the interface of the experience scenario by referring to the user's past feedback. In this way, the experience scenario can be customized by reflecting the user's past feedback.

[0062] The determination unit can adjust the accuracy of the determination based on the response content of the customer avatar when determining the customer service experience. For example, the determination unit adjusts the accuracy of the determination based on the response content of the customer avatar when determining the customer service experience. The response content of the customer avatar is generated based on, for example, natural language processing technology, the tone and content of the response, etc. For example, the determination unit increases the accuracy of the determination when the response content of the customer avatar is detailed. Furthermore, the determination unit can also decrease the accuracy of the determination when the response content of the customer avatar is simple. Furthermore, the determination unit adjusts the accuracy of the determination according to the response content of the customer avatar. This makes it possible to adjust the accuracy of the determination based on the response content of the customer avatar.

[0063] The determination unit can improve the accuracy of the determination when determining the customer service experience by referring to the user's past determination results. For example, the determination unit improves the accuracy of the determination when determining the customer service experience by referring to the user's past determination results. The past determination results are acquired, for example, from a database. For example, the determination unit improves the accuracy of the determination based on the user's past determination results. The determination unit can also analyze the user's past determination results and optimize the determination algorithm. Furthermore, the determination unit adjusts the determination criteria by referring to the user's past determination results. This makes it possible to improve the accuracy of the determination by referring to the user's past determination results.

[0064] The determination unit can improve the determination criteria by reflecting user feedback when determining the customer service experience. For example, the determination unit improves the determination criteria by reflecting user feedback when determining the customer service experience. User feedback is collected, for example, through questionnaires or interviews. For example, the determination unit improves the determination criteria based on the user feedback. The determination unit can also reflect user feedback in real time and optimize the determination criteria. Furthermore, the determination unit analyzes the user feedback and adjusts the parameters of the determination criteria. This makes it possible to improve the determination criteria by reflecting user feedback.

[0065] The determination unit can provide a highly relevant determination result by taking into account the user's geographical location information when determining the customer service experience. For example, the determination unit can provide a highly relevant determination result by taking into account the user's geographical location information when determining the customer service experience. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the determination unit provides a region-specific determination result based on the user's current location. The determination unit can also provide a determination result suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the determination unit provides a determination result tailored to the needs of the region by taking into account the user's location information. This makes it possible to provide a highly relevant determination result by taking into account the user's geographical location information.

[0066] The determination unit can analyze the user's social media activity when determining the customer service experience and provide a related determination result. For example, the determination unit can analyze the user's social media activity when determining the customer service experience and provide a related determination result. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the determination unit can analyze the content of the user's social media posts and provide a related determination result. The determination unit can also provide a related determination result by referring to the activity of the user's friends on social media. Furthermore, the determination unit can provide a related determination result based on the user's social media check-in information. In this way, the user's social media activity can be analyzed and a related determination result can be provided.

[0067] The determination unit can customize the determination criteria by reflecting the user's past feedback when determining the customer service experience. For example, the determination unit customizes the determination criteria by reflecting the user's past feedback when determining the customer service experience. Past feedback is collected, for example, through questionnaires, interviews, etc. For example, the determination unit customizes the determination criteria based on the user's past feedback. The determination unit can also analyze the user's feedback and optimize the determination criteria. Furthermore, the determination unit improves the interface of the determination criteria by referring to the user's past feedback. In this way, the determination criteria can be customized by reflecting the user's past feedback.

[0068] The feedback unit can adjust the level of detail of the feedback based on the assessment result of the customer service experience when providing the feedback. For example, the feedback unit adjusts the level of detail of the feedback based on the assessment result of the customer service experience when providing the feedback. The assessment result of the customer service experience is generated based on, for example, evaluation criteria or a assessment algorithm. For example, the feedback unit provides detailed feedback when the assessment result is detailed. Furthermore, the feedback unit can also provide simple feedback when the assessment result is simple. Furthermore, the feedback unit adjusts the level of detail of the feedback according to the assessment result. This makes it possible to adjust the level of detail of the feedback based on the assessment result of the customer service experience.

[0069] The feedback unit can provide optimal feedback by referring to the user's past feedback history when providing feedback. For example, the feedback unit can provide optimal feedback by referring to the user's past feedback history when providing feedback. The past feedback history is obtained, for example, from a database. For example, the feedback unit can provide optimal feedback based on the user's past feedback history. The feedback unit can also extract a specific pattern from the user's past feedback history and provide feedback based on that. Furthermore, the feedback unit can analyze the user's past feedback history and provide the most effective feedback. This makes it possible to provide optimal feedback by referring to the user's past feedback history.

[0070] The feedback unit can improve the feedback content by reflecting the user's feedback when providing the feedback. For example, the feedback unit improves the feedback content by reflecting the user's feedback when providing the feedback. User feedback is collected, for example, through a questionnaire or an interview. For example, the feedback unit improves the feedback content based on the user's feedback. The feedback unit can also reflect the user's feedback in real time and optimize the feedback content. Furthermore, the feedback unit analyzes the user's feedback and adjusts parameters of the feedback content. In this way, the feedback content can be improved by reflecting the user's feedback.

[0071] The feedback unit may provide highly relevant feedback by taking into account the user's geographical location information when providing feedback. For example, the feedback unit may provide highly relevant feedback by taking into account the user's geographical location information when providing feedback. The geographical location information may be collected, for example, from GPS data, location information services, or the like. For example, the feedback unit may provide region-specific feedback based on the user's current location. The feedback unit may also provide feedback suited to local culture and customs based on the user's geographical location information. Furthermore, the feedback unit may provide feedback tailored to local needs by taking into account the user's location information. This allows highly relevant feedback to be provided by taking into account the user's geographical location information.

[0072] The feedback unit may analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit may analyze the user's social media activity and provide relevant feedback when providing feedback. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the feedback unit may analyze the user's social media posted content and provide relevant feedback. The feedback unit may also provide relevant feedback by referring to the activity of the user's friends on social media. Furthermore, the feedback unit may provide relevant feedback based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and relevant feedback can be provided.

[0073] The feedback unit can customize the feedback content by reflecting the user's past feedback when providing feedback. For example, the feedback unit customizes the feedback content by reflecting the user's past feedback when providing feedback. Past feedback is collected, for example, through questionnaires or interviews. For example, the feedback unit customizes the feedback content based on the user's past feedback. The feedback unit can also analyze the user's feedback and optimize the feedback content. Furthermore, the feedback unit improves the interface of the feedback content by referring to the user's past feedback. In this way, the feedback content can be customized by reflecting the user's past feedback.

[0074] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0075] The setting unit can suggest an appropriate persona by referring to the user's past customer service history. For example, the setting unit can automatically suggest an optimal persona based on data on customers the user has dealt with in the past. The setting unit can also extract specific patterns from the user's past customer service history and suggest a persona based on those patterns. Furthermore, it can also suggest an optimal persona by referring to customer service scenarios that the user has received high ratings for in the past. This makes it possible to suggest an optimal persona by referring to the user's past customer service history.

[0076] When generating a response from the customer avatar, the response unit can adjust the accuracy of the response based on the level of detail of the persona. For example, if the level of detail of the persona is high, a more realistic response content can be generated. On the other hand, if the level of detail of the persona is low, a simple response content can be generated. Furthermore, the level of detail of the response content to be generated can be adjusted according to the level of detail of the persona. This makes it possible to adjust the accuracy of the response based on the level of detail of the persona.

[0077] When determining the customer service experience, the determination unit can adjust the accuracy of the determination based on the response content of the customer avatar. For example, if the response content of the customer avatar is detailed, the accuracy of the determination can be increased. Also, if the response content of the customer avatar is simple, the accuracy of the determination can be decreased. Furthermore, the accuracy of the determination can be adjusted according to the response content of the customer avatar. This makes it possible to adjust the accuracy of the determination based on the response content of the customer avatar.

[0078] When setting a customer persona, the setting unit can customize the persona based on the user's current work situation and goals. For example, the characteristics of the persona can be customized based on the user's current work goals. The setting unit can also set an optimal persona taking into account the user's work situation (busyness, work content, etc.). Furthermore, the setting unit can adjust the persona settings based on the user's short-term and long-term goals. This makes it possible to customize the persona based on the user's current work situation and goals.

[0079] When generating a customer avatar, the generation unit can apply different generation algorithms depending on the category of the persona. For example, an algorithm that generates a customer avatar with a professional appearance can be applied to a business person persona. Also, an algorithm that generates a customer avatar with a casual appearance can be applied to a student persona. Furthermore, an algorithm that generates a customer avatar with a friendly appearance can be applied to an elderly person persona. In this way, different generation algorithms can be applied depending on the category of the persona.

[0080] The experience unit can provide an optimal experience scenario by referring to the user's past experience history during the customer service experience. For example, the optimal experience scenario is provided based on the user's past experience history. It can also extract specific patterns from the user's past experience history and provide an experience scenario based on those patterns. Furthermore, it can analyze the user's past experience history and provide the most effective experience scenario. This makes it possible to provide an optimal experience scenario by referring to the user's past experience history.

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

[0082] Step 1: The setting unit sets a customer persona. The customer persona includes, but is not limited to, information such as age, gender, occupation, and hobbies. Step 2: The generation unit uses the generation AI to generate a customer avatar based on the persona set by the setting unit. The generation AI generates the customer avatar using technologies such as deep learning and generative models. Step 3: The response unit uses the generation AI to generate a response for the customer avatar generated by the generation unit. The generation AI generates the response for the customer avatar using, for example, natural language processing technology. Step 4: The experience unit performs a customer service experience based on the responses of the generated customer avatar. The customer service experience includes, but is not limited to, a scenario and an interaction method. Step 5: The evaluation unit evaluates the results of the customer service experience, including, but not limited to, evaluation criteria such as customer satisfaction and accuracy of responses. Step 6: The feedback unit provides feedback based on the judgment result obtained by the judgment unit. The feedback may include, but is not limited to, specific improvements and training methods.

[0083] (Example 2) The VR customer simulation service according to an embodiment of the present invention is a system that uses a generative AI to generate customer avatars and responses. By setting a customer persona in advance, users can recreate various situations and engage in customer service experiences. After the customer service experience, they can receive AI evaluations and feedback, enabling them to improve their customer service level. Furthermore, using the VR customer simulator allows for employee training anytime, anywhere, resulting in higher quality service. For example, a user sets a customer persona and inputs information such as age, gender, occupation, and hobbies. The generative AI then generates a customer avatar and responses based on this information. For example, a young female customer avatar is generated, and a scenario is recreated in which the avatar asks the user a question or makes a request. After the customer service experience ends, the AI ​​evaluates the user's response and provides feedback, including whether the user's response was appropriate and what needs improvement. This allows users to improve their customer service skills. Furthermore, using the VR customer simulator enables employee training independent of physical location. For example, employees can receive training anywhere, such as their office or home, simply by wearing a VR headset. This improves training efficiency and enables the provision of higher quality service. As a result, the VR customer simulation service can perform everything from customer persona creation to customer service experience, judgment, and feedback in a consistent manner. This allows users to improve their customer service skills. It also makes it possible to conduct employee training without relying on physical locations, improving training efficiency and enabling the provision of higher quality service.

[0084] A VR customer simulation service according to an embodiment includes a setting unit, a generation unit, a response unit, an experience unit, a determination unit, and a feedback unit. The setting unit sets a customer persona. The customer persona includes, for example, but is not limited to, information such as age, gender, occupation, and hobbies. The generation unit uses a generation AI to generate a customer avatar based on the persona set by the setting unit. The generation AI generates the customer avatar using, for example, technology such as deep learning or a generative model. The response unit uses the generation AI to generate responses for the customer avatar generated by the generation unit. The generation AI generates responses for the customer avatar using, for example, natural language processing technology. The experience unit provides a customer service experience based on the responses of the generated customer avatar. The customer service experience includes, for example, but is not limited to, a scenario and an interaction method. The determination unit determines the result of the customer service experience. The determination includes, for example, but is not limited to, evaluation criteria such as customer satisfaction and response accuracy. The feedback unit provides feedback based on the determination result obtained by the determination unit. The feedback may include, but is not limited to, specific improvements and training methods. As a result, the VR customer simulation service according to the embodiment can consistently perform everything from customer persona setting to customer service experience, evaluation, and feedback.

[0085] The setting unit can set the age, gender, occupation, hobbies, and other information of the customer. For example, the setting unit can set the age, gender, occupation, hobbies, and other information of the customer. For example, the setting unit can collect customer information using a questionnaire. The setting unit can also acquire customer information from a database. Furthermore, the setting unit can also allow the user to manually input customer information. This makes it possible to set detailed persona information of the customer.

[0086] The generation unit can generate a customer avatar using a generation AI. The generation unit generates a customer avatar using, for example, the generation AI. The generation AI generates a customer avatar using, for example, deep learning technology. The generation unit can also generate a customer avatar using a generative model. For example, the generation unit inputs customer persona information into the generation AI to generate a customer avatar. This makes it possible to generate a realistic customer avatar using the generation AI.

[0087] The response unit can generate a response for the customer avatar using a generation AI. The response unit generates a response for the customer avatar using, for example, a generation AI. The generation AI generates a response for the customer avatar using, for example, natural language processing technology. The response unit can also generate a response for the customer avatar using a generative model. For example, the response unit inputs information about the customer avatar into the generation AI to generate a response. This allows the generation AI to generate a response for the customer avatar.

[0088] The experience unit can provide a customer service experience based on the responses of the generated customer avatar. The experience unit provides a customer service experience based on, for example, the responses of the generated customer avatar. The customer service experience includes, for example, a scenario and an interaction method. For example, the experience unit provides a scenario in which the user can have a customer service experience based on the responses of the customer avatar. The experience unit also sets an interaction method so that the user can interact with the customer avatar. This allows a customer service experience to be provided based on the responses of the generated customer avatar.

[0089] The determination unit can determine the result of the customer service experience. The determination unit, for example, determines the result of the customer service experience. The determination includes evaluation criteria such as customer satisfaction and accuracy of response. For example, the determination unit determines whether the user's response was appropriate based on the result of the customer service experience. The determination unit can also identify areas for improvement in the user's response based on the result of the customer service experience. This makes it possible to determine the result of the customer service experience.

[0090] The feedback unit can provide feedback based on the determination result. The feedback unit provides feedback based on, for example, the determination result. The feedback includes, for example, specific areas for improvement and training methods. For example, the feedback unit indicates specific areas for improvement in the user's response based on the determination result. The feedback unit can also suggest training methods for improving the user's customer service skills. In this way, feedback can be provided based on the determination result.

[0091] The experience unit can provide a customer service experience using a VR customer simulator. The experience unit can provide a customer service experience using, for example, a VR customer simulator. The VR customer simulator includes, for example, a simulation environment and an interaction method. For example, the experience unit can enable a user to provide a customer service experience in a virtual environment by wearing a VR headset. The experience unit can also use the VR customer simulator to enable a user to provide a customer service experience independent of a physical location. This allows the customer service experience to be provided using the VR customer simulator.

[0092] The feedback unit can provide feedback that contributes to improving customer service skills. The feedback unit provides, for example, feedback that contributes to improving customer service skills. The feedback includes, for example, specific areas for improvement and training methods. For example, the feedback unit can specifically indicate areas for improvement in the user's response, contributing to improving customer service skills. The feedback unit can also suggest training methods for improving the user's customer service skills. In this way, it is possible to provide feedback that contributes to improving customer service skills.

[0093] The setting unit can estimate the user's emotions and adjust the customer's persona settings based on the estimated user's emotions. For example, the setting unit can estimate the user's emotions and adjust the customer's persona settings based on the estimated user's emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, if the user is nervous, the setting unit can provide a simple and intuitive interface to simplify the persona setting procedure. Furthermore, if the user is relaxed, the setting unit can provide detailed persona setting options and suggest a customizable setting method. Furthermore, if the user is in a hurry, the setting unit can prioritize voice input to enable quick persona setting. This makes it possible to adjust the customer's persona settings based on the user's emotions.

[0094] The setting unit can suggest an appropriate persona by referring to the user's past customer service history when setting a customer persona. For example, the setting unit can suggest an appropriate persona by referring to the user's past customer service history when setting a customer persona. The past customer service history is acquired, for example, from a database. For example, the setting unit automatically suggests an optimal persona based on data on customers the user has dealt with in the past. The setting unit can also extract specific patterns from the user's past customer service history and suggest a persona based on the extracted patterns. Furthermore, the setting unit suggests an optimal persona by referring to customer service scenarios that the user has received high ratings for in the past. This makes it possible to suggest an optimal persona by referring to the user's past customer service history.

[0095] The setting unit can customize the persona based on the user's current work situation and goals when setting the customer persona. For example, the setting unit customizes the persona based on the user's current work situation and goals when setting the customer persona. The current work situation and goals are collected, for example, from a work report or a goal setting sheet. For example, the setting unit customizes the characteristics of the persona based on the user's current work goals. The setting unit can also set an optimal persona taking into account the user's work situation (busyness, work content, etc.). Furthermore, the setting unit adjusts the persona settings based on the user's short-term and long-term goals. This makes it possible to customize the persona based on the user's current work situation and goals.

[0096] The setting unit can improve the accuracy of the persona setting by reflecting user feedback when setting a customer persona. For example, the setting unit improves the accuracy of the persona setting by reflecting user feedback when setting a customer persona. User feedback is collected, for example, through questionnaires or interviews. For example, the setting unit improves the persona setting algorithm based on the feedback provided by the user. The setting unit can also improve the accuracy of the persona setting by reflecting user feedback in real time. Furthermore, the setting unit analyzes user feedback and optimizes parameters for persona setting. This makes it possible to improve the accuracy of the persona setting by reflecting user feedback.

[0097] The setting unit can estimate the user's emotions and determine the priority of persona settings based on the estimated user emotions. The setting unit, for example, estimates the user's emotions and determines the priority of persona settings based on the estimated user emotions. The user's emotions are estimated using techniques such as facial expression recognition and voice analysis. For example, the setting unit can prioritize displaying important persona setting items when the user is feeling stressed. Furthermore, the setting unit can sequentially display detailed persona setting items when the user is relaxed. Furthermore, the setting unit can display the most important persona setting item first when the user is in a hurry. This makes it possible to determine the priority of persona settings based on the user's emotions.

[0098] The setting unit can prioritize a highly relevant persona in consideration of the user's geographical location information when setting a customer persona. For example, the setting unit prioritizes a highly relevant persona in consideration of the user's geographical location information when setting a customer persona. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the setting unit prioritizes a region-specific persona based on the user's current location. The setting unit can also suggest a persona suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the setting unit sets a persona according to the needs of the region in consideration of the user's location information. This makes it possible to prioritize a highly relevant persona in consideration of the user's geographical location information.

[0099] The setting unit can analyze the user's social media activity and set a related persona when setting a customer persona. For example, the setting unit analyzes the user's social media activity and sets a related persona when setting a customer persona. Social media activity is collected, for example, through an analysis of posted content and an analysis of followers. For example, the setting unit analyzes the content of the user's social media posts and sets a related persona. The setting unit can also set a related persona by referring to the activity of the user's friends on social media. Furthermore, the setting unit sets a related persona based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and a related persona can be set.

[0100] The setting unit can customize the setting method by reflecting the user's past feedback when setting a customer persona. For example, the setting unit customizes the setting method by reflecting the user's past feedback when setting a customer persona. Past feedback is collected, for example, through questionnaires or interviews. For example, the setting unit customizes the persona setting procedure based on the user's past feedback. The setting unit can also analyze the user's feedback and optimize the setting method. Furthermore, the setting unit improves the persona setting interface by referring to the user's past feedback. This makes it possible to customize the setting method by reflecting the user's past feedback.

[0101] The generation unit can estimate the user's emotion and adjust the customer avatar generation method based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the customer avatar generation method based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice analysis. For example, the generation unit generates a friendly customer avatar when the user is relaxed. Furthermore, the generation unit can generate a customer avatar with a calm demeanor when the user is nervous. Furthermore, the generation unit generates a customer avatar that can respond quickly when the user is in a hurry. This makes it possible to adjust the customer avatar generation method based on the user's emotion.

[0102] The generation unit can adjust the accuracy of generation based on the level of detail of the persona when generating a customer avatar. For example, the generation unit adjusts the accuracy of generation based on the level of detail of the persona when generating a customer avatar. The level of detail of the persona is evaluated based on, for example, the number of attribute information pieces and detailed descriptions. For example, when the level of detail of the persona is high, the generation unit generates a more realistic customer avatar. Also, when the level of detail of the persona is low, the generation unit can generate a simple customer avatar. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar to be generated depending on the level of detail of the persona. This makes it possible to adjust the accuracy of generation based on the level of detail of the persona.

[0103] The generation unit can apply different generation algorithms depending on the category of the persona when generating a customer avatar. For example, the generation unit applies different generation algorithms depending on the category of the persona when generating a customer avatar. Persona categories are classified based on, for example, age group, occupation, hobby, etc. For example, the generation unit can apply an algorithm that generates a customer avatar with a professional appearance to a business person persona. Furthermore, the generation unit can apply an algorithm that generates a customer avatar with a casual appearance to a student persona. Furthermore, the generation unit can apply an algorithm that generates a customer avatar with a friendly appearance to an elderly person persona. In this way, different generation algorithms can be applied depending on the category of the persona.

[0104] The generation unit can improve the accuracy of generation when generating a customer avatar by referring to the user's past generation results. For example, when generating a customer avatar, the generation unit improves the accuracy of generation by referring to the user's past generation results. The past generation results are obtained, for example, from a database. For example, the generation unit improves the accuracy of generation based on data of customer avatars generated by the user in the past. The generation unit can also analyze the user's past generation results and optimize the generation algorithm. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar by referring to the user's past generation results. This makes it possible to improve the accuracy of generation by referring to the user's past generation results.

[0105] The generation unit can estimate the user's emotion and adjust the appearance of the customer avatar based on the estimated user's emotion. For example, the generation unit can estimate the user's emotion and adjust the appearance of the customer avatar based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice analysis. For example, if the user is relaxed, the generation unit can generate a customer avatar with a friendly appearance. Furthermore, if the user is nervous, the generation unit can generate a customer avatar with a calm appearance. Furthermore, if the user is in a hurry, the generation unit can generate a customer avatar with an appearance that can respond quickly. This makes it possible to adjust the appearance of the customer avatar based on the user's emotion.

[0106] The generation unit can determine the generation priority based on the time of persona submission when generating a customer avatar. For example, the generation unit determines the generation priority based on the time of persona submission when generating a customer avatar. The time of persona submission is collected, for example, by recording the submission date and time or managing the submission order. For example, if a persona has been submitted recently, the generation unit preferentially generates a customer avatar based on that persona. The generation unit can also adjust the generation priority based on the time of persona submission. Furthermore, the generation unit sets a low generation priority for personas that have been submitted recently. This makes it possible to determine the generation priority based on the time of persona submission.

[0107] The generation unit can adjust the order of generation based on the relevance of personas when generating customer avatars. For example, the generation unit adjusts the order of generation based on the relevance of personas when generating customer avatars. The relevance of personas is evaluated based on, for example, common attributes or related interests. For example, if a persona has high relevance, the generation unit preferentially generates a customer avatar based on that persona. The generation unit can also adjust the order of generation based on the relevance of personas. Furthermore, the generation unit postpones the generation order for personas with low relevance. This makes it possible to adjust the order of generation based on the relevance of personas.

[0108] The generation unit can adjust the level of detail of the customer avatar generation in accordance with the user's level of expertise. For example, the generation unit adjusts the level of detail of the customer avatar generation in accordance with the user's level of expertise. The user's level of expertise is evaluated based on, for example, qualification information, work experience, etc. For example, the generation unit generates a detailed customer avatar when the user's level of expertise is high. Alternatively, the generation unit can generate a simple customer avatar when the user's level of expertise is low. Furthermore, the generation unit adjusts the appearance and personality of the customer avatar to be generated in accordance with the user's level of expertise. This allows the level of detail of the customer avatar generation to be adjusted in accordance with the user's level of expertise.

[0109] The response unit can estimate the user's emotions and adjust the response content of the customer avatar based on the estimated user emotions. The response unit, for example, estimates the user's emotions and adjusts the response content of the customer avatar based on the estimated user emotions. The user's emotions are estimated using techniques such as facial expression recognition and voice analysis. For example, the response unit generates a friendly response content when the user is relaxed. Furthermore, the response unit can also generate a calm response content when the user is nervous. Furthermore, the response unit generates a response content that allows a quick response when the user is in a hurry. This makes it possible to adjust the response content of the customer avatar based on the user's emotions.

[0110] The response unit can adjust the accuracy of the response based on the level of detail of the persona when generating a response for the customer avatar. For example, the response unit adjusts the accuracy of the response based on the level of detail of the persona when generating a response for the customer avatar. The level of detail of the persona is evaluated based on, for example, the number of attribute information items and detailed descriptions. For example, when the level of detail of the persona is high, the response unit generates more realistic response content. Furthermore, when the level of detail of the persona is low, the response unit can also generate simple response content. Furthermore, the response unit adjusts the level of detail of the response content to be generated depending on the level of detail of the persona. This makes it possible to adjust the accuracy of the response based on the level of detail of the persona.

[0111] The response unit can apply different response algorithms depending on the category of the persona when generating a response for the customer avatar. For example, the response unit applies different response algorithms depending on the category of the persona when generating a response for the customer avatar. Persona categories are classified based on, for example, age group, occupation, hobby, etc. For example, the response unit can apply an algorithm that generates professional response content to a business person persona. The response unit can also apply an algorithm that generates casual response content to a student persona. Furthermore, the response unit can apply an algorithm that generates friendly response content to an elderly persona. In this way, different response algorithms can be applied depending on the category of the persona.

[0112] The response unit can improve the accuracy of the response when generating a response for the customer avatar by referring to the user's past response results. For example, the response unit improves the accuracy of the response when generating a response for the customer avatar by referring to the user's past response results. The past response results are obtained, for example, from a database. For example, the response unit improves the accuracy of the response based on the responses generated by the user in the past. The response unit can also analyze the user's past response results and optimize the response algorithm. Furthermore, the response unit adjusts the response content of the customer avatar by referring to the user's past response results. This makes it possible to improve the accuracy of the response by referring to the user's past response results.

[0113] The response unit can estimate the user's emotion and adjust the tone of the customer avatar's response based on the estimated user's emotion. The response unit, for example, estimates the user's emotion and adjusts the tone of the customer avatar's response based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice analysis. For example, the response unit responds in a friendly tone when the user is relaxed. The response unit can also respond in a calm tone when the user is nervous. Furthermore, the response unit responds in a tone that allows for quick response when the user is in a hurry. This makes it possible to adjust the tone of the customer avatar's response based on the user's emotion.

[0114] The response unit can determine the priority of responses based on the submission time of the persona when generating a response for the customer avatar. For example, the response unit determines the priority of responses based on the submission time of the persona when generating a response for the customer avatar. The submission time of the persona is collected, for example, by recording the submission date and time or managing the submission order. For example, if a persona has been submitted recently, the response unit preferentially generates a response based on that persona. The response unit can also adjust the priority of responses based on the submission time of the persona. Furthermore, the response unit sets a lower priority for a persona that was submitted earlier. This makes it possible to determine the priority of responses based on the submission time of the persona.

[0115] The response unit can adjust the order of responses based on the relevance of the persona when generating responses for the customer avatar. For example, the response unit adjusts the order of responses based on the relevance of the persona when generating responses for the customer avatar. The relevance of the persona is evaluated based on, for example, common attributes or related interests. For example, if the relevance of a persona is high, the response unit preferentially generates a response based on that persona. The response unit can also adjust the order of responses based on the relevance of the persona. Furthermore, the response unit postpones the order of responses for personas with low relevance. This makes it possible to adjust the order of responses based on the relevance of the persona.

[0116] The response unit can adjust the level of detail of the response according to the user's expertise level when generating a response for the customer avatar. For example, the response unit adjusts the level of detail of the response according to the user's expertise level when generating a response for the customer avatar. The user's expertise level is evaluated based on, for example, qualification information, work experience, etc. For example, the response unit generates a detailed response content when the user's expertise level is high. Furthermore, the response unit can also generate a simple response content when the user's expertise level is low. Furthermore, the response unit adjusts the level of detail of the generated response content according to the user's expertise level. This makes it possible to adjust the level of detail of the response according to the user's expertise level.

[0117] The experience unit can estimate the user's emotions and adjust the customer service experience scenario based on the estimated user emotions. The experience unit, for example, estimates the user's emotions and adjusts the customer service experience scenario based on the estimated user emotions. The user's emotions are estimated using techniques such as facial expression recognition and voice analysis. For example, the experience unit provides a friendly scenario when the user is relaxed. The experience unit can also provide a calm scenario when the user is nervous. Furthermore, the experience unit provides a scenario that allows for quick response when the user is in a hurry. This makes it possible to adjust the customer service experience scenario based on the user's emotions.

[0118] The experience unit can adjust the level of detail of the experience based on the response content of the customer avatar during the customer service experience. For example, the experience unit adjusts the level of detail of the experience based on the response content of the customer avatar during the customer service experience. The response content of the customer avatar is generated based on, for example, natural language processing technology, the tone and content of the response, etc. For example, the experience unit increases the level of detail of the experience when the response content of the customer avatar is detailed. Furthermore, the experience unit can decrease the level of detail of the experience when the response content of the customer avatar is simple. Furthermore, the experience unit adjusts the level of detail of the experience according to the response content of the customer avatar. In this way, the level of detail of the experience can be adjusted based on the response content of the customer avatar.

[0119] The experience unit can provide an optimal experiential scenario by referring to the user's past experience history during a customer service experience. For example, the experience unit can provide an optimal experiential scenario by referring to the user's past experience history during a customer service experience. The past experience history is acquired, for example, from a database. For example, the experience unit provides an optimal experiential scenario based on the user's past experience history. The experience unit can also extract a specific pattern from the user's past experience history and provide an experiential scenario based on that. Furthermore, the experience unit analyzes the user's past experience history and provides the most effective experiential scenario. This makes it possible to provide an optimal experiential scenario by referring to the user's past experience history.

[0120] The experience unit can improve the experience scenario by reflecting user feedback during the customer service experience. For example, the experience unit improves the experience scenario by reflecting user feedback during the customer service experience. User feedback is collected, for example, through questionnaires or interviews. For example, the experience unit improves the experience scenario based on the user feedback. The experience unit can also reflect user feedback in real time and optimize the experience scenario. Furthermore, the experience unit analyzes the user feedback and adjusts the parameters of the experience scenario. In this way, the experience scenario can be improved by reflecting user feedback.

[0121] The experience unit can estimate the user's emotions and determine the priority of customer service experiences based on the estimated user emotions. The experience unit, for example, estimates the user's emotions and determines the priority of customer service experiences based on the estimated user emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice analysis. For example, the experience unit can provide important experience scenarios preferentially when the user is feeling stressed. Furthermore, the experience unit can sequentially provide detailed experience scenarios when the user is relaxed. Furthermore, the experience unit can provide the most important experience scenario first when the user is in a hurry. This makes it possible to determine the priority of customer service experiences based on the user's emotions.

[0122] The experience unit can provide a highly relevant experiential scenario by taking into account the user's geographical location information during a customer service experience. For example, the experience unit can provide a highly relevant experiential scenario by taking into account the user's geographical location information during a customer service experience. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the experience unit can provide a region-specific experiential scenario based on the user's current location. The experience unit can also provide an experiential scenario suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the experience unit can provide an experiential scenario tailored to the needs of the region by taking into account the user's location information. This makes it possible to provide a highly relevant experiential scenario by taking into account the user's geographical location information.

[0123] The experience unit can analyze the user's social media activity during the customer service experience and provide a related experience scenario. The experience unit, for example, analyzes the user's social media activity during the customer service experience and provides a related experience scenario. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the experience unit analyzes the user's social media posts and provides a related experience scenario. The experience unit can also provide a related experience scenario by referring to the activity of the user's friends on social media. Furthermore, the experience unit provides a related experience scenario based on the user's social media check-in information. In this way, the user's social media activity can be analyzed and a related experience scenario can be provided.

[0124] The experience unit can customize the experience scenario by reflecting the user's past feedback during the customer service experience. The experience unit, for example, customizes the experience scenario by reflecting the user's past feedback during the customer service experience. Past feedback is collected, for example, through questionnaires or interviews. For example, the experience unit customizes the experience scenario based on the user's past feedback. The experience unit can also analyze the user's feedback and optimize the experience scenario. Furthermore, the experience unit improves the interface of the experience scenario by referring to the user's past feedback. In this way, the experience scenario can be customized by reflecting the user's past feedback.

[0125] The determination unit can estimate the user's emotions and adjust the criteria for the customer service experience based on the estimated user emotions. The determination unit, for example, estimates the user's emotions and adjusts the criteria for the customer service experience based on the estimated user emotions. The user's emotions are estimated using techniques such as facial expression recognition and voice analysis. For example, the determination unit applies a friendly determination criterion when the user is relaxed. The determination unit can also apply a calm determination criterion when the user is nervous. Furthermore, the determination unit applies a criterion that allows for quick response when the user is in a hurry. This makes it possible to adjust the criteria for the customer service experience based on the user's emotions.

[0126] The determination unit can adjust the accuracy of the determination based on the response content of the customer avatar when determining the customer service experience. For example, the determination unit adjusts the accuracy of the determination based on the response content of the customer avatar when determining the customer service experience. The response content of the customer avatar is generated based on, for example, natural language processing technology, the tone and content of the response, etc. For example, the determination unit increases the accuracy of the determination when the response content of the customer avatar is detailed. Furthermore, the determination unit can also decrease the accuracy of the determination when the response content of the customer avatar is simple. Furthermore, the determination unit adjusts the accuracy of the determination according to the response content of the customer avatar. This makes it possible to adjust the accuracy of the determination based on the response content of the customer avatar.

[0127] The determination unit can improve the accuracy of the determination when determining the customer service experience by referring to the user's past determination results. For example, the determination unit improves the accuracy of the determination when determining the customer service experience by referring to the user's past determination results. The past determination results are acquired, for example, from a database. For example, the determination unit improves the accuracy of the determination based on the user's past determination results. The determination unit can also analyze the user's past determination results and optimize the determination algorithm. Furthermore, the determination unit adjusts the determination criteria by referring to the user's past determination results. This makes it possible to improve the accuracy of the determination by referring to the user's past determination results.

[0128] The determination unit can improve the determination criteria by reflecting user feedback when determining the customer service experience. For example, the determination unit improves the determination criteria by reflecting user feedback when determining the customer service experience. User feedback is collected, for example, through questionnaires or interviews. For example, the determination unit improves the determination criteria based on the user feedback. The determination unit can also reflect user feedback in real time and optimize the determination criteria. Furthermore, the determination unit analyzes the user feedback and adjusts the parameters of the determination criteria. This makes it possible to improve the determination criteria by reflecting user feedback.

[0129] The determination unit can estimate the user's emotions and adjust the order in which the customer service experience assessment results are displayed based on the estimated user emotions. The determination unit, for example, estimates the user's emotions and adjusts the order in which the customer service experience assessment results are displayed based on the estimated user emotions. The user's emotions are estimated using techniques such as facial expression recognition and voice analysis. For example, if the user is relaxed, the determination unit can display the assessment results in a friendly order. Furthermore, if the user is nervous, the determination unit can also display the assessment results in a calm order. Furthermore, if the user is in a hurry, the determination unit displays the assessment results in an order that allows for a quick response. This makes it possible to adjust the order in which the customer service experience assessment results are displayed based on the user's emotions.

[0130] The determination unit can provide a highly relevant determination result by taking into account the user's geographical location information when determining the customer service experience. For example, the determination unit can provide a highly relevant determination result by taking into account the user's geographical location information when determining the customer service experience. Geographical location information is collected, for example, from GPS data, location information services, etc. For example, the determination unit provides a region-specific determination result based on the user's current location. The determination unit can also provide a determination result suited to the culture and customs of the region based on the user's geographical location information. Furthermore, the determination unit provides a determination result tailored to the needs of the region by taking into account the user's location information. This makes it possible to provide a highly relevant determination result by taking into account the user's geographical location information.

[0131] The determination unit can analyze the user's social media activity when determining the customer service experience and provide a related determination result. For example, the determination unit can analyze the user's social media activity when determining the customer service experience and provide a related determination result. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the determination unit can analyze the content of the user's social media posts and provide a related determination result. The determination unit can also provide a related determination result by referring to the activity of the user's friends on social media. Furthermore, the determination unit can provide a related determination result based on the user's social media check-in information. In this way, the user's social media activity can be analyzed and a related determination result can be provided.

[0132] The determination unit can customize the determination criteria by reflecting the user's past feedback when determining the customer service experience. For example, the determination unit customizes the determination criteria by reflecting the user's past feedback when determining the customer service experience. Past feedback is collected, for example, through questionnaires, interviews, etc. For example, the determination unit customizes the determination criteria based on the user's past feedback. The determination unit can also analyze the user's feedback and optimize the determination criteria. Furthermore, the determination unit improves the interface of the determination criteria by referring to the user's past feedback. In this way, the determination criteria can be customized by reflecting the user's past feedback.

[0133] The feedback unit can estimate the user's emotion and adjust the feedback content based on the estimated user's emotion. The feedback unit, for example, estimates the user's emotion and adjusts the feedback content based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice analysis. For example, the feedback unit can provide friendly feedback content when the user is relaxed. Furthermore, the feedback unit can also provide calm feedback content when the user is nervous. Furthermore, the feedback unit can provide feedback content that allows for a quick response when the user is in a hurry. This makes it possible to adjust the feedback content based on the user's emotion.

[0134] The feedback unit can adjust the level of detail of the feedback based on the assessment result of the customer service experience when providing the feedback. For example, the feedback unit adjusts the level of detail of the feedback based on the assessment result of the customer service experience when providing the feedback. The assessment result of the customer service experience is generated based on, for example, evaluation criteria or a assessment algorithm. For example, the feedback unit provides detailed feedback when the assessment result is detailed. Furthermore, the feedback unit can also provide simple feedback when the assessment result is simple. Furthermore, the feedback unit adjusts the level of detail of the feedback according to the assessment result. This makes it possible to adjust the level of detail of the feedback based on the assessment result of the customer service experience.

[0135] The feedback unit can provide optimal feedback by referring to the user's past feedback history when providing feedback. For example, the feedback unit can provide optimal feedback by referring to the user's past feedback history when providing feedback. The past feedback history is obtained, for example, from a database. For example, the feedback unit can provide optimal feedback based on the user's past feedback history. The feedback unit can also extract a specific pattern from the user's past feedback history and provide feedback based on that. Furthermore, the feedback unit can analyze the user's past feedback history and provide the most effective feedback. This makes it possible to provide optimal feedback by referring to the user's past feedback history.

[0136] The feedback unit can improve the feedback content by reflecting the user's feedback when providing the feedback. For example, the feedback unit improves the feedback content by reflecting the user's feedback when providing the feedback. User feedback is collected, for example, through a questionnaire or an interview. For example, the feedback unit improves the feedback content based on the user's feedback. The feedback unit can also reflect the user's feedback in real time and optimize the feedback content. Furthermore, the feedback unit analyzes the user's feedback and adjusts parameters of the feedback content. In this way, the feedback content can be improved by reflecting the user's feedback.

[0137] The feedback unit can estimate the user's emotion and determine the priority of feedback based on the estimated user's emotion. The feedback unit, for example, estimates the user's emotion and determines the priority of feedback based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice analysis. For example, the feedback unit can provide important feedback preferentially when the user is feeling stressed. The feedback unit can also provide detailed feedback sequentially when the user is relaxed. Furthermore, the feedback unit can provide the most important feedback first when the user is in a hurry. This makes it possible to determine the priority of feedback based on the user's emotion.

[0138] The feedback unit may provide highly relevant feedback by taking into account the user's geographical location information when providing feedback. For example, the feedback unit may provide highly relevant feedback by taking into account the user's geographical location information when providing feedback. The geographical location information may be collected, for example, from GPS data, location information services, or the like. For example, the feedback unit may provide region-specific feedback based on the user's current location. The feedback unit may also provide feedback suited to local culture and customs based on the user's geographical location information. Furthermore, the feedback unit may provide feedback tailored to local needs by taking into account the user's location information. This allows highly relevant feedback to be provided by taking into account the user's geographical location information.

[0139] The feedback unit may analyze the user's social media activity and provide relevant feedback when providing feedback. For example, the feedback unit may analyze the user's social media activity and provide relevant feedback when providing feedback. Social media activity is collected, for example, through analysis of posted content and follower analysis. For example, the feedback unit may analyze the user's social media posted content and provide relevant feedback. The feedback unit may also provide relevant feedback by referring to the activity of the user's friends on social media. Furthermore, the feedback unit may provide relevant feedback based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and relevant feedback can be provided.

[0140] The feedback unit can customize the feedback content by reflecting the user's past feedback when providing feedback. For example, the feedback unit customizes the feedback content by reflecting the user's past feedback when providing feedback. Past feedback is collected, for example, through questionnaires or interviews. For example, the feedback unit customizes the feedback content based on the user's past feedback. The feedback unit can also analyze the user's feedback and optimize the feedback content. Furthermore, the feedback unit improves the interface of the feedback content by referring to the user's past feedback. In this way, the feedback content can be customized by reflecting the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the setting unit, generation unit, response unit, experience unit, determination unit, and feedback unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the smart device 14, and a user sets a customer persona. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a customer avatar using a generation AI. The response unit is realized by the specific processing unit 290 of the data processing device 12, and generates a response of the generated customer avatar. The experience unit is realized by the control unit 46A of the smart device 14, and provides a customer service experience based on the response of the generated customer avatar. The determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines the result of the customer service experience. The feedback unit is realized by the specific processing unit 290 of the data processing device 12, and provides feedback based on the determination result. === Hard Collateral 1-2 === Each of the multiple elements including the setting unit, generation unit, response unit, experience unit, determination unit, and feedback unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the smart glasses 214, and a user sets a customer persona. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a customer avatar using a generation AI. The response unit is realized by the specific processing unit 290 of the data processing device 12, and generates a response of the generated customer avatar. The experience unit is realized by the control unit 46A of the smart glasses 214, and provides a customer service experience based on the response of the generated customer avatar. The determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines the result of the customer service experience. The feedback unit is realized by the specific processing unit 290 of the data processing device 12, and provides feedback based on the determination result. === Hard Collateral 1-3 === Each of the multiple elements including the setting unit, generation unit, response unit, experience unit, determination unit, and feedback unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the headset type terminal 314, and a user sets a customer persona. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a customer avatar using a generation AI. The response unit is realized by the specific processing unit 290 of the data processing device 12, and generates a response of the generated customer avatar. The experience unit is realized by the control unit 46A of the headset type terminal 314, and provides a customer service experience based on the response of the generated customer avatar. The determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines the result of the customer service experience. The feedback unit is realized by the specific processing unit 290 of the data processing device 12, and provides feedback based on the determination result. === Hard Collateral 1-4 === Each of the multiple elements including the setting unit, generation unit, response unit, experience unit, determination unit, and feedback unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the robot 414, and a user sets a customer persona. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a customer avatar using a generation AI. The response unit is realized by the specific processing unit 290 of the data processing device 12, and generates a response of the generated customer avatar. The experience unit is realized by the control unit 46A of the robot 414, and provides a customer service experience based on the response of the generated customer avatar. The determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines the result of the customer service experience. The feedback unit is realized by the specific processing unit 290 of the data processing device 12, and provides feedback based on the determination result.

[0141] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0142] The setting unit can suggest an appropriate persona by referring to the user's past customer service history. For example, the setting unit can automatically suggest an optimal persona based on data on customers the user has dealt with in the past. The setting unit can also extract specific patterns from the user's past customer service history and suggest a persona based on those patterns. Furthermore, it can also suggest an optimal persona by referring to customer service scenarios that the user has received high ratings for in the past. This makes it possible to suggest an optimal persona by referring to the user's past customer service history.

[0143] The generation unit can estimate the user's emotions and adjust the customer avatar generation method based on the estimated user's emotions. For example, if the user is relaxed, a friendly customer avatar can be generated. If the user is nervous, a customer avatar with a calm demeanor can be generated. Furthermore, if the user is in a hurry, a customer avatar that can respond quickly can be generated. In this way, the customer avatar generation method can be adjusted based on the user's emotions.

[0144] When generating a response from the customer avatar, the response unit can adjust the accuracy of the response based on the level of detail of the persona. For example, if the level of detail of the persona is high, a more realistic response content can be generated. On the other hand, if the level of detail of the persona is low, a simple response content can be generated. Furthermore, the level of detail of the response content to be generated can be adjusted according to the level of detail of the persona. This makes it possible to adjust the accuracy of the response based on the level of detail of the persona.

[0145] The experience unit can estimate the user's emotions and adjust the customer service experience scenario based on the estimated user emotions. For example, if the user is relaxed, a friendly scenario can be provided. If the user is nervous, a calm scenario can be provided. Furthermore, if the user is in a hurry, a scenario that allows for a quick response can be provided. In this way, the customer service experience scenario can be adjusted based on the user's emotions.

[0146] When determining the customer service experience, the determination unit can adjust the accuracy of the determination based on the response content of the customer avatar. For example, if the response content of the customer avatar is detailed, the accuracy of the determination can be increased. Also, if the response content of the customer avatar is simple, the accuracy of the determination can be decreased. Furthermore, the accuracy of the determination can be adjusted according to the response content of the customer avatar. This makes it possible to adjust the accuracy of the determination based on the response content of the customer avatar.

[0147] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. For example, if the user is relaxed, friendly feedback content can be provided. If the user is nervous, calm feedback content can be provided. Furthermore, if the user is in a hurry, feedback content that allows for a quick response can be provided. In this way, the content of the feedback can be adjusted based on the user's emotions.

[0148] When setting a customer persona, the setting unit can customize the persona based on the user's current work situation and goals. For example, the characteristics of the persona can be customized based on the user's current work goals. The setting unit can also set an optimal persona taking into account the user's work situation (busyness, work content, etc.). Furthermore, the setting unit can adjust the persona settings based on the user's short-term and long-term goals. This makes it possible to customize the persona based on the user's current work situation and goals.

[0149] When generating a customer avatar, the generation unit can apply different generation algorithms depending on the category of the persona. For example, an algorithm that generates a customer avatar with a professional appearance can be applied to a business person persona. Also, an algorithm that generates a customer avatar with a casual appearance can be applied to a student persona. Furthermore, an algorithm that generates a customer avatar with a friendly appearance can be applied to an elderly person persona. In this way, different generation algorithms can be applied depending on the category of the persona.

[0150] The response unit can estimate the user's emotions and adjust the tone of the customer avatar's response based on the estimated user's emotions. For example, if the user is relaxed, the response unit can respond in a friendly tone. If the user is nervous, the response unit can respond in a calm tone. Furthermore, if the user is in a hurry, the response unit can respond in a tone that allows for quick response. In this way, the tone of the customer avatar's response can be adjusted based on the user's emotions.

[0151] The experience unit can provide an optimal experience scenario by referring to the user's past experience history during the customer service experience. For example, the optimal experience scenario is provided based on the user's past experience history. It can also extract specific patterns from the user's past experience history and provide an experience scenario based on those patterns. Furthermore, it can analyze the user's past experience history and provide the most effective experience scenario. This makes it possible to provide an optimal experience scenario by referring to the user's past experience history.

[0152] The processing flow of the second embodiment will be briefly explained below.

[0153] Step 1: The setting unit sets a customer persona. The customer persona includes, but is not limited to, information such as age, gender, occupation, and hobbies. Step 2: The generation unit uses the generation AI to generate a customer avatar based on the persona set by the setting unit. The generation AI generates the customer avatar using technologies such as deep learning and generative models. Step 3: The response unit uses the generation AI to generate a response for the customer avatar generated by the generation unit. The generation AI generates the response for the customer avatar using, for example, natural language processing technology. Step 4: The experience unit performs a customer service experience based on the responses of the generated customer avatar. The customer service experience includes, but is not limited to, a scenario and an interaction method. Step 5: The evaluation unit evaluates the results of the customer service experience, including, but not limited to, evaluation criteria such as customer satisfaction and accuracy of responses. Step 6: The feedback unit provides feedback based on the judgment result obtained by the judgment unit. The feedback may include, but is not limited to, specific improvements and training methods.

[0154] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0159] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0174] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0175] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0177] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0178] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0181] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0182] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0184] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0188] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0190] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0191] 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.

[0192] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0193] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0194] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0195] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0196] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0197] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0198] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0199] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0200] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0201] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0202] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0203] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0204] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0205] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0206] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0207] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0208] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0209] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0210] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0211] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0212] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0213] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0214] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0215] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0216] 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.

[0217] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0218] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0219] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0220] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0221] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0222] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0223] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0224] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0225] [Explanation of symbols]

[0226] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A setting section for setting the customer persona; a generation unit that generates a customer avatar based on the persona set by the setting unit; a response unit that generates a response of the customer avatar generated by the generation unit; an experience unit that provides a customer service experience based on the response generated by the response unit; a determination unit for determining the customer service experience performed by the experience unit; a feedback unit that provides feedback based on the determination result obtained by the determination unit; Equipped with A system characterized by:

2. The setting unit Set the customer's age, gender, occupation, hobbies, and other information 2. The system of claim 1.

3. The generation unit Generate customer avatars using generative AI 2. The system of claim 1.

4. The response unit Generate customer avatar responses using generative AI 2. The system of claim 1.

5. The experience section includes: Providing customer service experiences based on the responses of generated customer avatars 2. The system of claim 1.

6. The determination unit Determine the outcome of the customer experience 2. The system of claim 1.

7. The feedback unit Providing feedback based on the results 2. The system of claim 1.

8. The experience section includes: Experience customer service using a VR customer simulator 2. The system of claim 1.

Images