system

Abstract

The system according to this embodiment aims to reduce the stress and tension experienced by call center operators while interacting with customers, and to improve customer satisfaction. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, a display unit, a promotion unit, and a feedback generation unit. The analysis unit analyzes the customer's voice and tone. The generation unit generates an avatar based on the information analyzed by the analysis unit. The display unit displays the avatar generated by the generation unit. The promotion unit promotes the operator's response based on the avatar displayed by the display unit. The feedback generation unit generates feedback regarding the response promoted by the promotion unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is no sufficient means to reduce the stress and tension felt by call center operators during customer service, and there is room for improvement.

[0005] The system according to the embodiment aims to reduce the stress and tension felt by call center operators during customer service and improve customer satisfaction.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, a display unit, a promotion unit, and a feedback generation unit. The analysis unit analyzes the customer's voice and tone. The generation unit generates an avatar based on the information analyzed by the analysis unit. The display unit displays the avatar generated by the generation unit. The promotion unit promotes the operator's response based on the avatar displayed by the display unit. The feedback generation unit generates feedback regarding the response promoted by the promotion unit. [Effects of the Invention]

[0007] The system according to this embodiment can reduce the stress and tension that call center operators feel while dealing with customers, and improve customer satisfaction. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The call center support system according to an embodiment of the present invention is a system for improving operator response quality and customer satisfaction. This system analyzes the customer's voice and tone, generates an avatar (video of a person), and displays it on the operator's screen. The avatar is displayed as a video with a gentler, smiling tone than the actual tone. This encourages operators to see the customer's smile and provide warm, gentle call support. Furthermore, in the case of complaints or angry customers, videos of animals or comedians are displayed. This eases the operator's tension and reduces stress. By easing the stiff atmosphere of complaint handling, customer satisfaction is also increased. In addition, after the call, feedback on the interaction is provided in gentle and humorous language. This makes operators look forward to receiving feedback and increases their motivation. Ultimately, this leads to improved response quality and customer satisfaction. For example, the call center support system uses AI to analyze the customer's voice and tone. The AI ​​analyzes the customer's voice tone and emotions and generates an avatar based on that. For example, if the customer is speaking in a calm tone, a gentle, smiling avatar is generated. On the other hand, in the case of a customer making a complaint or who is angry, a video of an animal or a comedian is generated. Next, the generated avatar or video is displayed on the operator's screen. The operator handles the call while viewing the customer's avatar or video. This encourages the operator to see the customer's smile, bringing out their kindness and promoting a warmer, more considerate call. Also, in the case of a customer making a complaint or who is angry, the display of a video of an animal or a comedian helps to ease the operator's tension and reduce stress. Furthermore, after the call, the AI ​​generates feedback on the interaction. This feedback is provided in kind and humorous language. For example, feedback such as "That was a great interaction! Please do your best next time!" is provided. This makes operators look forward to receiving feedback and increases their motivation. This system improves the quality of operator service and customer satisfaction in call centers. Operators are encouraged to see the customer's smile, bringing out their kindness and promoting a warmer, more considerate call.Furthermore, when handling complaints, displaying videos of animals or comedians helps to ease tension and reduce stress. In addition, providing gentle and humorous feedback boosts operator motivation, ultimately leading to improved service quality and customer satisfaction. Thus, call center support systems can improve both operator service quality and customer satisfaction.

[0029] The call center support system according to the embodiment comprises an analysis unit, a generation unit, a display unit, a promotion unit, and a feedback generation unit. The analysis unit analyzes the customer's voice and tone. The analysis unit analyzes the frequency and volume of the customer's voice, for example, using speech recognition technology. The analysis unit can also analyze the customer's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. The generation unit generates an avatar based on the information analyzed by the analysis unit. The generation unit generates an avatar, for example, using a 3D model. The generation unit can also generate an animated character. For example, the generation unit generates a gentle, smiling avatar based on the analyzed information. The display unit displays the avatar generated by the generation unit. The display unit displays the avatar, for example, on the operator's screen. The display unit can also display the generated avatar or video on the operator's screen. For example, the display unit displays the avatar at a specific position on the screen to make it easily visible to the operator. The Facilitation Unit facilitates the operator's response based on the avatar displayed by the Display Unit. The Facilitation Unit, for example, helps to alleviate the operator's tension and reduce stress. The Facilitation Unit can also provide information to support the operator's response. For example, the Facilitation Unit encourages the operator to respond gently and with a smile. The Feedback Generation Unit generates feedback regarding the response facilitated by the Facilitation Unit. The Feedback Generation Unit generates feedback, for example, in gentle and humorous language. The Feedback Generation Unit can also provide specific feedback regarding the operator's response. For example, the Feedback Generation Unit provides feedback such as, "That was a great response! Please do your best next time!" Thus, the call center support system according to this embodiment can analyze the customer's voice and tone, generate and display an avatar, facilitate the operator's response, and generate feedback.

[0030] The analysis unit analyzes the customer's voice and tone. For example, it uses speech recognition technology to analyze the frequency and volume of the customer's voice. Specifically, speech recognition technology converts the voice signal into digital data and analyzes that data to extract the characteristics of the customer's voice. This includes elements such as pitch, rhythm, and volume. The analysis unit can also analyze the customer's emotions using an emotion analysis algorithm. The emotion analysis algorithm analyzes the tone, tempo, and intonation of the voice to identify emotions such as whether the customer is angry, happy, or sad. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. This allows the analysis unit to quickly and accurately provide the information necessary for operators to respond. Furthermore, the analysis unit can learn from past call data to perform more accurate analyses. For example, it can learn the characteristics and emotional patterns of customers' voices based on past call data and perform highly accurate analyses on new calls. This allows the analysis unit to always provide highly accurate analyses based on the latest information, supporting operators in their responses.

[0031] The generation unit generates avatars based on information analyzed by the analysis unit. The generation unit generates avatars using, for example, 3D models. Specifically, it sets the appearance and facial expressions of the avatar based on the information provided by the analysis unit. For example, if the customer's voice tone is gentle, the generation unit generates a gentle, smiling avatar. The generation unit can also generate animated characters. Animated characters enable more realistic communication by having movement and facial expressions. For example, in addition to generating a gentle, smiling avatar based on the analyzed information, it can also reflect mouth and eye movements in real time when the avatar speaks. This allows the generation unit to facilitate more natural communication between the operator and the customer. Furthermore, the generation unit can also provide avatar customization functions. For example, by allowing operators to freely set the appearance and facial expressions of the avatar, more personalized responses become possible. This enables the generation unit to achieve flexible avatar generation according to the operator's needs and improve the overall effectiveness of the system.

[0032] The display unit displays avatars generated by the generation unit. For example, the display unit displays avatars on the operator's screen. Specifically, it displays avatars on the monitor or display used by the operator and positions them in a way that is easily visible to the operator. The display unit can also display generated avatars or videos on the operator's screen. For example, the display unit can display avatars in specific positions on the screen to make them easily visible to the operator, and the movement of the avatars can attract the operator's attention. Furthermore, the display unit can also provide a function to customize how avatars are displayed. For example, by allowing operators to freely adjust the size and position of avatars, a more comfortable working environment can be provided. The display unit can also display multiple avatars simultaneously, which allows for efficient handling of multiple customers. In this way, the display unit can provide an environment in which operators can effectively communicate with customers through avatars, thereby improving the overall effectiveness of the system.

[0033] The Facilitation Unit facilitates operator responses based on avatars displayed by the Display Unit. Specifically, it provides functions to alleviate operator tension and reduce stress. For example, the avatar can speak to the operator with a gentle smile to ease their tension. The Facilitation Unit can also provide information to support operator responses. For example, it can not only encourage operators to respond gently and with a smile, but also provide specific response methods and advice. Furthermore, the Facilitation Unit can provide training functions to improve operator performance. For example, it can provide simulations and feedback to allow operators to review past responses and learn areas for improvement. In this way, the Facilitation Unit can help operators respond to customers more effectively and improve the overall effectiveness of the system. In addition, the Facilitation Unit can collect operator feedback and use it to improve the system. For example, it can collect problems and areas for improvement that operators have noticed and reflect them in system updates and feature additions. In this way, the Facilitation Unit can always provide highly accurate support based on the latest information and facilitate operator responses.

[0034] The feedback generation unit generates feedback regarding responses facilitated by the facilitation unit. Specifically, it generates feedback in a gentle and humorous tone. For example, if an operator provides a good response, it might say, "That was a great response! Please do your best next time!" The feedback generation unit can also provide specific feedback on the operator's response. For example, it might offer advice on how the operator can improve specific response methods. Furthermore, the feedback generation unit can generate information to evaluate operator performance and provide rewards and incentives. For example, it can calculate evaluation points based on the operator's number of responses and customer satisfaction, and then provide rewards and incentives. This allows the feedback generation unit to improve operator motivation and enhance the overall effectiveness of the system. In addition, the feedback generation unit can also provide a function to customize the content of the feedback. For example, by setting the style and content of feedback according to the operator's preferences, it can provide more personalized feedback. This allows the feedback generation unit to support operators in learning and growing more effectively and enhance the overall effectiveness of the system.

[0035] The generation unit can generate videos of animals or comedians in the case of complaints or angry customers. For example, the generation unit can analyze the voice and tone of a complaining or angry customer and generate videos of animals or comedians based on that information. For example, the generation unit can generate cute animal videos to ease the tension of operators when handling complaints. The generation unit can also generate humorous videos of comedians. For example, the generation unit can generate fun videos to help operators relax. In this way, videos that ease the tension of operators can be generated in the case of complaints or angry customers. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the voice and tone of a complaining or angry customer into a generation AI and have the generation AI perform the generation of videos of animals or comedians.

[0036] The display unit can display the generated avatars and videos on the operator's screen. For example, the display unit can display the generated avatars at a specific position on the operator's screen. The display unit can also display the generated videos on the operator's screen. For example, the display unit can display the avatars and videos in a position that is easily visible to the operator. This allows the display of generated avatars and videos on the operator's screen to support the operator's response. Some or all of the above processing in the display unit may be performed using a generation AI, for example, or without a generation AI. For example, the display unit can input the display position of the generated avatars and videos to the generation AI and have the generation AI select the optimal display position.

[0037] The feedback generation unit can generate feedback in a gentle and humorous manner. For example, it can provide feedback on an operator's response in a gentle and humorous way. The feedback generation unit can also generate feedback to improve the operator's motivation. For example, it can provide feedback such as, "That was a great response! Please do your best next time!" In this way, by generating gentle and humorous feedback, the operator's motivation can be improved. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input information about the operator's response into a generation AI and have the generation AI generate gentle and humorous feedback.

[0038] The Facilitation Unit can alleviate operator tension and reduce stress. For example, the Facilitation Unit can provide information to alleviate operator tension. The Facilitation Unit can also provide support to reduce operator stress. For example, the Facilitation Unit can provide relaxation techniques to the operator. This can improve the quality of service by alleviating operator tension and reducing stress. Some or all of the above processes in the Facilitation Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Facilitation Unit can input information about the operator's tension and stress into a generative AI and have the generative AI perform the provision of relaxation techniques.

[0039] The feedback generation unit can provide feedback to the operator. For example, the feedback generation unit can provide feedback regarding the operator's response. The feedback generation unit can also provide specific feedback to improve the quality of the operator's response. For example, the feedback generation unit can point out areas for improvement regarding the operator's response. By providing feedback to the operator, the quality of the operator's response can be improved. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input information about the operator's response into a generation AI and have the generation AI perform the generation of feedback.

[0040] The analysis unit can analyze the background sound of the customer's voice and provide information for generating an avatar appropriate to the environment. For example, if the background sound is quiet, the analysis unit can generate an avatar that simulates an office environment. If the background sound is noisy, the analysis unit can also generate an avatar that simulates an outdoor environment. Furthermore, if the background sound contains a specific sound (e.g., music or traffic noise), the analysis unit can generate an avatar that corresponds to that sound. By providing information for avatar generation based on the background sound, it is possible to generate a more appropriate avatar. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input background sound data into a generation AI and have the generation AI perform the task of providing information for avatar generation.

[0041] The analysis unit can improve the accuracy of its analysis by referring to past call history when analyzing customer voices. For example, the analysis unit can learn the characteristics of customer voices from past call history to improve the accuracy of its analysis. It can also learn customer emotional patterns from past call history to improve the accuracy of its analysis. Furthermore, the analysis unit can learn specific customer requests or problems from past call history to improve the accuracy of its analysis. In this way, the accuracy of the analysis can be improved by referring to past call history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input past call history data into a generative AI and have the generative AI perform the analysis accuracy improvement.

[0042] The analysis unit can perform analysis of customer voices while taking into account regional dialects and accents. For example, the analysis unit can learn regional dialects and perform analysis based on them. It can also learn regional accents and perform analysis based on accents. Furthermore, it can learn regional expressions and perform analysis based on those expressions. This allows for more accurate analysis by taking regional dialects and accents into account. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input regional dialect and accent data into a generative AI and have the generative AI perform the analysis.

[0043] The generation unit can customize the avatar's clothing and background based on the customer's voice tone. For example, if the tone is calm, the generation unit may give the avatar casual clothing and a relaxed background. If the tone is formal, the generation unit may give the avatar a business suit and an office background. Furthermore, if the tone is cheerful, the generation unit may give the avatar bright clothing and a cheerful background. This allows for the generation of more appropriate avatars by customizing the avatar's clothing and background based on the voice tone. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the customer's voice tone data into a generation AI and have the generation AI customize the avatar's clothing and background.

[0044] The generation unit can be configured to have the avatar perform specific gestures in response to the content of the customer's voice. For example, if the customer expresses gratitude, the generation unit can have the avatar smile and bow. The generation unit can also have the avatar assume a thinking pose if the customer asks a question. Furthermore, if the customer expresses anger, the generation unit can have the avatar perform a calming gesture. This allows for the generation of more appropriate avatars by having the avatar perform specific gestures in response to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI execute the avatar gesture settings.

[0045] The generation unit can change the gender and age of the avatar based on the analysis results of the customer's voice. For example, if the customer's voice sounds youthful, the generation unit can set the avatar to a young person. Also, if the customer's voice sounds calm, the generation unit can set the avatar to a middle-aged person. Furthermore, if the customer's voice sounds elderly, the generation unit can set the avatar to an elderly person. In this way, by changing the gender and age of the avatar based on the voice analysis results, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the customer's voice analysis data into a generation AI and have the generation AI perform the changes to the avatar's gender and age.

[0046] The generation unit can configure the avatar to hold specific tools or accessories depending on the content of the customer's voice. For example, if the customer is talking about travel, the generation unit can make the avatar hold a travel bag. Similarly, if the customer is talking about work, the avatar can hold a laptop. Furthermore, if the customer is talking about hobbies, the generation unit can make the avatar hold tools related to those hobbies. This allows for the generation of more appropriate avatars by having the avatar hold specific tools or accessories according to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI configure the avatar's tools and accessories.

[0047] The display unit can select the optimal display method when displaying an avatar by referring to the operator's past reaction history. For example, the display unit may prioritize display methods that the operator has preferred in the past. The display unit can also exclude display methods that the operator has avoided in the past. Furthermore, the display unit can select the most effective display method from the operator's past reaction history. In this way, the optimal display method can be selected by referring to the operator's past reaction history. Some or all of the above processing in the display unit may be performed using, for example, a generating AI, or without a generating AI. For example, the display unit can input the operator's past reaction history data into a generating AI and have the generating AI select the optimal display method.

[0048] The display unit can adjust the display position of the avatar according to the operator's screen layout when displaying it. For example, if the operator's screen layout is vertical, the display unit will display the avatar at the top of the screen. If the operator's screen layout is horizontal, the display unit can also display the avatar on the left side of the screen. Furthermore, if the operator's screen layout is divided, the display unit can display the avatar in the position with the highest visibility. In this way, visibility can be improved by adjusting the display position according to the operator's screen layout. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's screen layout data into a generation AI and have the generation AI perform the adjustment of the display position.

[0049] The display unit can select the optimal display method when displaying an avatar, taking into account the operator's device information. For example, if the operator is using a smartphone, the display unit can provide a display method that matches the screen size. Furthermore, if the operator is using a tablet, the display unit can provide a display method optimized for a larger screen. Additionally, if the operator is using a desktop, the display unit can provide a display method that supports multiple windows. This allows the optimal display method to be selected by considering the operator's device information. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's device information into the generation AI and have the generation AI select the optimal display method.

[0050] The display unit can dynamically change the display position of the avatar using the operator's eye-tracking data when displaying the avatar. For example, if the operator's gaze is focused on the left side of the screen, the display unit will display the avatar on the right side. The display unit can also display the avatar in the center if the operator's gaze is focused on the center of the screen. Furthermore, if the operator's gaze is focused on the right side of the screen, the display unit can display the avatar on the left side. In this way, the display position can be dynamically changed using the operator's eye-tracking data. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's eye-tracking data into a generation AI and have the generation AI perform the dynamic change of the display position.

[0051] The support unit can analyze the operator's past response history and propose the optimal response method. For example, the support unit can prioritize proposing response methods that the operator has successfully used in the past. It can also suggest that the operator avoid response methods that have failed in the past. Furthermore, the support unit can propose the most effective response method based on the operator's past response history. In this way, the support unit can propose the optimal response method by analyzing the operator's past response history. Some or all of the above processing in the support unit may be performed using, for example, a generative AI, or without a generative AI. For example, the support unit can input the operator's past response history data into a generative AI and have the generative AI propose the optimal response method.

[0052] The Facilitation Unit can monitor the operator's current stress level and provide appropriate response methods. For example, if the operator's stress level is high, the Facilitation Unit can provide a simple and effective response method. Furthermore, if the operator's stress level is low, the Facilitation Unit can provide a detailed response method. In addition, if the operator's stress level is moderate, the Facilitation Unit can provide a balanced response method. This allows for the provision of appropriate response methods by monitoring the operator's stress level. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Facilitation Unit can input operator stress level data into a generative AI and have the generative AI provide appropriate response methods.

[0053] The Facilitation Unit can provide real-time feedback to operators during their interactions, thereby improving the quality of their responses. For example, the Facilitation Unit can provide feedback at the appropriate time while the operator is interacting with the customer. It can also point out areas for improvement in real time while the operator is interacting with the customer. Furthermore, the Facilitation Unit can share successful cases in real time while the operator is interacting with the customer. This allows for improved quality of responses through the provision of real-time feedback. Some or all of the above processes in the Facilitation Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Facilitation Unit can input operator interaction data into a generative AI and have the generative AI provide real-time feedback.

[0054] The Facilitation Unit can suggest response methods by referring to successful case studies of other operators when an operator is handling a situation. For example, the Facilitation Unit can suggest response methods that have worked for other operators. It can also suggest avoiding response methods that have failed for other operators. Furthermore, the Facilitation Unit can suggest the optimal response method based on the successful case studies of other operators. In this way, the Facilitation Unit can suggest the optimal response method by referring to the successful case studies of other operators. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the Facilitation Unit can input data on successful case studies of other operators into a generating AI and have the generating AI execute the suggestion of response methods.

[0055] The feedback generation unit can provide optimal feedback by referring to the operator's past feedback history. For example, the feedback generation unit can provide optimal feedback based on feedback the operator has received in the past. It can also provide feedback based on improvements the operator has made in the past. Furthermore, the feedback generation unit can provide the most effective feedback from the operator's past feedback history. In this way, it can provide optimal feedback by referring to past feedback history. Some or all of the above processing in the feedback generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback generation unit can input the operator's past feedback history data into a generation AI and have the generation AI perform the task of providing optimal feedback.

[0056] The feedback generation unit can customize the content of feedback by considering the operator's current work situation when generating it. For example, if the operator is busy, the feedback generation unit can provide concise and to-the-point feedback. If the operator has time, the feedback generation unit can also provide detailed feedback. Furthermore, if the operator is stressed, the feedback generation unit can provide feedback that includes words of encouragement. In this way, more appropriate feedback can be provided by considering the operator's work situation. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input operator work situation data into the generation AI and have the generation AI perform the customization of the feedback content.

[0057] The feedback generation unit can adjust the content of the feedback while considering the operator's individual characteristics. For example, if the operator prefers positive feedback, the feedback generation unit will emphasize positive content. Furthermore, if the operator prefers detailed feedback, the feedback generation unit can provide detailed content. Additionally, if the operator prefers concise feedback, the feedback generation unit can provide concise content. This allows for the provision of more appropriate feedback by considering the operator's individual characteristics. Some or all of the above processing in the feedback generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback generation unit can input the operator's individual characteristics data into a generation AI and have the generation AI adjust the feedback content.

[0058] The feedback generation unit can provide optimal feedback by referring to the feedback content of other operators when generating feedback. For example, the feedback generation unit can refer to positive feedback received by other operators. It can also refer to areas for improvement received by other operators. Furthermore, the feedback generation unit can provide optimal feedback based on the feedback content of other operators. In this way, it can provide optimal feedback by referring to the feedback content of other operators. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input the feedback content data of other operators into a generation AI and have the generation AI perform the task of providing optimal feedback.

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

[0060] The analysis unit can analyze the background sound of the customer's voice and provide information for generating an avatar appropriate to the environment. For example, if the background sound is quiet, the analysis unit can generate an avatar that simulates an office environment. If the background sound is noisy, the analysis unit can also generate an avatar that simulates an outdoor environment. Furthermore, if the background sound contains a specific sound (e.g., music or traffic noise), the analysis unit can generate an avatar that corresponds to that sound. By providing information for avatar generation based on the background sound, it is possible to generate a more appropriate avatar. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input background sound data into a generation AI and have the generation AI perform the task of providing information for avatar generation.

[0061] The generation unit can customize the avatar's clothing and background based on the customer's voice tone. For example, if the tone is calm, the generation unit may give the avatar casual clothing and a relaxed background. If the tone is formal, the generation unit may give the avatar a business suit and an office background. Furthermore, if the tone is cheerful, the generation unit may give the avatar bright clothing and a cheerful background. This allows for the generation of more appropriate avatars by customizing the avatar's clothing and background based on the voice tone. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the customer's voice tone data into a generation AI and have the generation AI customize the avatar's clothing and background.

[0062] The generation unit can be configured to have the avatar perform specific gestures in response to the content of the customer's voice. For example, if the customer expresses gratitude, the generation unit can have the avatar smile and bow. The generation unit can also have the avatar assume a thinking pose if the customer asks a question. Furthermore, if the customer expresses anger, the generation unit can have the avatar perform a calming gesture. This allows for the generation of more appropriate avatars by having the avatar perform specific gestures in response to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI execute the avatar gesture settings.

[0063] The display unit can select the optimal display method when displaying an avatar by referring to the operator's past reaction history. For example, the display unit may prioritize display methods that the operator has preferred in the past. The display unit can also exclude display methods that the operator has avoided in the past. Furthermore, the display unit can select the most effective display method from the operator's past reaction history. In this way, the optimal display method can be selected by referring to the operator's past reaction history. Some or all of the above processing in the display unit may be performed using, for example, a generating AI, or without a generating AI. For example, the display unit can input the operator's past reaction history data into a generating AI and have the generating AI select the optimal display method.

[0064] The Facilitation Unit can monitor the operator's current stress level and provide appropriate response methods. For example, if the operator's stress level is high, the Facilitation Unit can provide a simple and effective response method. Furthermore, if the operator's stress level is low, the Facilitation Unit can provide a detailed response method. In addition, if the operator's stress level is moderate, the Facilitation Unit can provide a balanced response method. This allows for the provision of appropriate response methods by monitoring the operator's stress level. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Facilitation Unit can input operator stress level data into a generative AI and have the generative AI provide appropriate response methods.

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

[0066] Step 1: The analysis unit analyzes the customer's voice and tone. The analysis unit can analyze the frequency and volume of the customer's voice using speech recognition technology and analyze the customer's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. Step 2: The generation unit generates an avatar based on the information analyzed by the analysis unit. The generation unit can generate avatars using 3D models or animated characters. For example, it can generate a gentle, smiling avatar based on the analyzed information. Step 3: The display unit displays the avatar generated by the generation unit. The display unit displays the avatar and video on the operator's screen and places them in a specific position on the screen so that they are easily visible to the operator. Step 4: The facilitator facilitates the operator's response based on the avatar displayed by the display unit. The facilitator helps to ease the operator's tension, reduce stress, and encourage a gentle, smiling response. Step 5: The feedback generation unit generates feedback regarding the response facilitated by the facilitation unit. The feedback generation unit generates feedback in gentle and humorous language, providing specific feedback on the operator's response. For example, it might provide feedback such as, "That was a great response! Keep up the good work next time!"

[0067] (Example of form 2) The call center support system according to an embodiment of the present invention is a system for improving operator response quality and customer satisfaction. This system analyzes the customer's voice and tone, generates an avatar (video of a person), and displays it on the operator's screen. The avatar is displayed as a video with a gentler, smiling tone than the actual tone. This encourages operators to see the customer's smile and provide warm, gentle call support. Furthermore, in the case of complaints or angry customers, videos of animals or comedians are displayed. This eases the operator's tension and reduces stress. By easing the stiff atmosphere of complaint handling, customer satisfaction is also increased. In addition, after the call, feedback on the interaction is provided in gentle and humorous language. This makes operators look forward to receiving feedback and increases their motivation. Ultimately, this leads to improved response quality and customer satisfaction. For example, the call center support system uses AI to analyze the customer's voice and tone. The AI ​​analyzes the customer's voice tone and emotions and generates an avatar based on that. For example, if the customer is speaking in a calm tone, a gentle, smiling avatar is generated. On the other hand, in the case of a customer making a complaint or who is angry, a video of an animal or a comedian is generated. Next, the generated avatar or video is displayed on the operator's screen. The operator handles the call while viewing the customer's avatar or video. This encourages the operator to see the customer's smile, bringing out their kindness and promoting a warmer, more considerate call. Also, in the case of a customer making a complaint or who is angry, the display of a video of an animal or a comedian helps to ease the operator's tension and reduce stress. Furthermore, after the call, the AI ​​generates feedback on the interaction. This feedback is provided in kind and humorous language. For example, feedback such as "That was a great interaction! Please do your best next time!" is provided. This makes operators look forward to receiving feedback and increases their motivation. This system improves the quality of operator service and customer satisfaction in call centers. Operators are encouraged to see the customer's smile, bringing out their kindness and promoting a warmer, more considerate call.Furthermore, when handling complaints, displaying videos of animals or comedians helps to ease tension and reduce stress. In addition, providing gentle and humorous feedback boosts operator motivation, ultimately leading to improved service quality and customer satisfaction. Thus, call center support systems can improve both operator service quality and customer satisfaction.

[0068] The call center support system according to the embodiment comprises an analysis unit, a generation unit, a display unit, a promotion unit, and a feedback generation unit. The analysis unit analyzes the customer's voice and tone. The analysis unit analyzes the frequency and volume of the customer's voice, for example, using speech recognition technology. The analysis unit can also analyze the customer's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. The generation unit generates an avatar based on the information analyzed by the analysis unit. The generation unit generates an avatar, for example, using a 3D model. The generation unit can also generate an animated character. For example, the generation unit generates a gentle, smiling avatar based on the analyzed information. The display unit displays the avatar generated by the generation unit. The display unit displays the avatar, for example, on the operator's screen. The display unit can also display the generated avatar or video on the operator's screen. For example, the display unit displays the avatar at a specific position on the screen to make it easily visible to the operator. The Facilitation Unit facilitates the operator's response based on the avatar displayed by the Display Unit. The Facilitation Unit, for example, helps to alleviate the operator's tension and reduce stress. The Facilitation Unit can also provide information to support the operator's response. For example, the Facilitation Unit encourages the operator to respond gently and with a smile. The Feedback Generation Unit generates feedback regarding the response facilitated by the Facilitation Unit. The Feedback Generation Unit generates feedback, for example, in gentle and humorous language. The Feedback Generation Unit can also provide specific feedback regarding the operator's response. For example, the Feedback Generation Unit provides feedback such as, "That was a great response! Please do your best next time!" Thus, the call center support system according to this embodiment can analyze the customer's voice and tone, generate and display an avatar, facilitate the operator's response, and generate feedback.

[0069] The analysis unit analyzes the customer's voice and tone. For example, it uses speech recognition technology to analyze the frequency and volume of the customer's voice. Specifically, speech recognition technology converts the voice signal into digital data and analyzes that data to extract the characteristics of the customer's voice. This includes elements such as pitch, rhythm, and volume. The analysis unit can also analyze the customer's emotions using an emotion analysis algorithm. The emotion analysis algorithm analyzes the tone, tempo, and intonation of the voice to identify emotions such as whether the customer is angry, happy, or sad. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. This allows the analysis unit to quickly and accurately provide the information necessary for operators to respond. Furthermore, the analysis unit can learn from past call data to perform more accurate analyses. For example, it can learn the characteristics and emotional patterns of customers' voices based on past call data and perform highly accurate analyses on new calls. This allows the analysis unit to always provide highly accurate analyses based on the latest information, supporting operators in their responses.

[0070] The generation unit generates avatars based on information analyzed by the analysis unit. The generation unit generates avatars using, for example, 3D models. Specifically, it sets the appearance and facial expressions of the avatar based on the information provided by the analysis unit. For example, if the customer's voice tone is gentle, the generation unit generates a gentle, smiling avatar. The generation unit can also generate animated characters. Animated characters enable more realistic communication by having movement and facial expressions. For example, in addition to generating a gentle, smiling avatar based on the analyzed information, it can also reflect mouth and eye movements in real time when the avatar speaks. This allows the generation unit to facilitate more natural communication between the operator and the customer. Furthermore, the generation unit can also provide avatar customization functions. For example, by allowing operators to freely set the appearance and facial expressions of the avatar, more personalized responses become possible. This enables the generation unit to achieve flexible avatar generation according to the operator's needs and improve the overall effectiveness of the system.

[0071] The display unit displays avatars generated by the generation unit. For example, the display unit displays avatars on the operator's screen. Specifically, it displays avatars on the monitor or display used by the operator and positions them in a way that is easily visible to the operator. The display unit can also display generated avatars or videos on the operator's screen. For example, the display unit can display avatars in specific positions on the screen to make them easily visible to the operator, and the movement of the avatars can attract the operator's attention. Furthermore, the display unit can also provide a function to customize how avatars are displayed. For example, by allowing operators to freely adjust the size and position of avatars, a more comfortable working environment can be provided. The display unit can also display multiple avatars simultaneously, which allows for efficient handling of multiple customers. In this way, the display unit can provide an environment in which operators can effectively communicate with customers through avatars, thereby improving the overall effectiveness of the system.

[0072] The Facilitation Unit facilitates operator responses based on avatars displayed by the Display Unit. Specifically, it provides functions to alleviate operator tension and reduce stress. For example, the avatar can speak to the operator with a gentle smile to ease their tension. The Facilitation Unit can also provide information to support operator responses. For example, it can not only encourage operators to respond gently and with a smile, but also provide specific response methods and advice. Furthermore, the Facilitation Unit can provide training functions to improve operator performance. For example, it can provide simulations and feedback to allow operators to review past responses and learn areas for improvement. In this way, the Facilitation Unit can help operators respond to customers more effectively and improve the overall effectiveness of the system. In addition, the Facilitation Unit can collect operator feedback and use it to improve the system. For example, it can collect problems and areas for improvement that operators have noticed and reflect them in system updates and feature additions. In this way, the Facilitation Unit can always provide highly accurate support based on the latest information and facilitate operator responses.

[0073] The feedback generation unit generates feedback regarding responses facilitated by the facilitation unit. Specifically, it generates feedback in a gentle and humorous tone. For example, if an operator provides a good response, it might say, "That was a great response! Please do your best next time!" The feedback generation unit can also provide specific feedback on the operator's response. For example, it might offer advice on how the operator can improve specific response methods. Furthermore, the feedback generation unit can generate information to evaluate operator performance and provide rewards and incentives. For example, it can calculate evaluation points based on the operator's number of responses and customer satisfaction, and then provide rewards and incentives. This allows the feedback generation unit to improve operator motivation and enhance the overall effectiveness of the system. In addition, the feedback generation unit can also provide a function to customize the content of the feedback. For example, by setting the style and content of feedback according to the operator's preferences, it can provide more personalized feedback. This allows the feedback generation unit to support operators in learning and growing more effectively and enhance the overall effectiveness of the system.

[0074] The generation unit can generate videos of animals or comedians in the case of complaints or angry customers. For example, the generation unit can analyze the voice and tone of a complaining or angry customer and generate videos of animals or comedians based on that information. For example, the generation unit can generate cute animal videos to ease the tension of operators when handling complaints. The generation unit can also generate humorous videos of comedians. For example, the generation unit can generate fun videos to help operators relax. In this way, videos that ease the tension of operators can be generated in the case of complaints or angry customers. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the voice and tone of a complaining or angry customer into a generation AI and have the generation AI perform the generation of videos of animals or comedians.

[0075] The display unit can display the generated avatars and videos on the operator's screen. For example, the display unit can display the generated avatars at a specific position on the operator's screen. The display unit can also display the generated videos on the operator's screen. For example, the display unit can display the avatars and videos in a position that is easily visible to the operator. This allows the display of generated avatars and videos on the operator's screen to support the operator's response. Some or all of the above processing in the display unit may be performed using a generation AI, for example, or without a generation AI. For example, the display unit can input the display position of the generated avatars and videos to the generation AI and have the generation AI select the optimal display position.

[0076] The feedback generation unit can generate feedback in a gentle and humorous manner. For example, it can provide feedback on an operator's response in a gentle and humorous way. The feedback generation unit can also generate feedback to improve the operator's motivation. For example, it can provide feedback such as, "That was a great response! Please do your best next time!" In this way, by generating gentle and humorous feedback, the operator's motivation can be improved. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input information about the operator's response into a generation AI and have the generation AI generate gentle and humorous feedback.

[0077] The Facilitation Unit can alleviate operator tension and reduce stress. For example, the Facilitation Unit can provide information to alleviate operator tension. The Facilitation Unit can also provide support to reduce operator stress. For example, the Facilitation Unit can provide relaxation techniques to the operator. This can improve the quality of service by alleviating operator tension and reducing stress. Some or all of the above processes in the Facilitation Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Facilitation Unit can input information about the operator's tension and stress into a generative AI and have the generative AI perform the provision of relaxation techniques.

[0078] The feedback generation unit can provide feedback to the operator. For example, the feedback generation unit can provide feedback regarding the operator's response. The feedback generation unit can also provide specific feedback to improve the quality of the operator's response. For example, the feedback generation unit can point out areas for improvement regarding the operator's response. By providing feedback to the operator, the quality of the operator's response can be improved. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input information about the operator's response into a generation AI and have the generation AI perform the generation of feedback.

[0079] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is angry, the emotion engine can set the emotion intensity high and perform a detailed analysis. If the user is relaxed, the emotion engine can set the emotion intensity low and perform a simpler analysis. Furthermore, if the user is tense, the emotion engine can track emotional fluctuations in real time and dynamically adjust the accuracy of the analysis. This allows for more accurate analysis results by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the analysis accuracy.

[0080] The analysis unit can analyze the background sound of the customer's voice and provide information for generating an avatar appropriate to the environment. For example, if the background sound is quiet, the analysis unit can generate an avatar that simulates an office environment. If the background sound is noisy, the analysis unit can also generate an avatar that simulates an outdoor environment. Furthermore, if the background sound contains a specific sound (e.g., music or traffic noise), the analysis unit can generate an avatar that corresponds to that sound. By providing information for avatar generation based on the background sound, it is possible to generate a more appropriate avatar. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input background sound data into a generation AI and have the generation AI perform the task of providing information for avatar generation.

[0081] The analysis unit can analyze the speed and rhythm of the customer's voice and detect changes in emotion in real time. For example, if the speed of the voice suddenly increases, the emotion engine can detect anger or impatience. The analysis unit can also detect anxiety or tension if the rhythm of the voice is inconsistent. Furthermore, if the speed of the voice slows down, the emotion engine can detect relaxation or relief. This allows for more appropriate responses by detecting changes in emotion based on the speed and rhythm of the voice. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not. For example, the analysis unit can input voice speed and rhythm data into a generative AI and have the generative AI perform emotion change detection.

[0082] The analysis unit can estimate the user's emotions and determine the priority of analysis results based on the estimated user emotions. For example, if the user is angry, the emotion engine will prioritize displaying analysis results related to anger. Similarly, if the user is relaxed, the emotion engine can prioritize displaying analysis results related to relaxation. Furthermore, if the user is stressed, the emotion engine can prioritize displaying analysis results related to stress. This allows for the priority of important information to be provided by prioritizing analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using a generative AI, or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of analysis results.

[0083] The analysis unit can improve the accuracy of its analysis by referring to past call history when analyzing customer voices. For example, the analysis unit can learn the characteristics of customer voices from past call history to improve the accuracy of its analysis. It can also learn customer emotional patterns from past call history to improve the accuracy of its analysis. Furthermore, the analysis unit can learn specific customer requests or problems from past call history to improve the accuracy of its analysis. In this way, the accuracy of the analysis can be improved by referring to past call history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input past call history data into a generative AI and have the generative AI perform the analysis accuracy improvement.

[0084] The analysis unit can perform analysis of customer voices while taking into account regional dialects and accents. For example, the analysis unit can learn regional dialects and perform analysis based on them. It can also learn regional accents and perform analysis based on accents. Furthermore, it can learn regional expressions and perform analysis based on those expressions. This allows for more accurate analysis by taking regional dialects and accents into account. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input regional dialect and accent data into a generative AI and have the generative AI perform the analysis.

[0085] The generation unit can estimate the user's emotions and adjust the avatar's facial expressions and movements based on the estimated emotions. For example, if the user is relaxed, the avatar will have a calm facial expression and relaxed movements. The generation unit can also make the avatar have a calm facial expression and gentle movements if the user is angry. Furthermore, if the user is tense, the avatar can have a reassuring facial expression and movements. This allows for the generation of a more appropriate avatar by adjusting its facial expressions and movements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input user emotion data into a generation AI and have the generation AI adjust the avatar's facial expressions and movements.

[0086] The generation unit can customize the avatar's clothing and background based on the customer's voice tone. For example, if the tone is calm, the generation unit may give the avatar casual clothing and a relaxed background. If the tone is formal, the generation unit may give the avatar a business suit and an office background. Furthermore, if the tone is cheerful, the generation unit may give the avatar bright clothing and a cheerful background. This allows for the generation of more appropriate avatars by customizing the avatar's clothing and background based on the voice tone. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the customer's voice tone data into a generation AI and have the generation AI customize the avatar's clothing and background.

[0087] The generation unit can be configured to have the avatar perform specific gestures in response to the content of the customer's voice. For example, if the customer expresses gratitude, the generation unit can have the avatar smile and bow. The generation unit can also have the avatar assume a thinking pose if the customer asks a question. Furthermore, if the customer expresses anger, the generation unit can have the avatar perform a calming gesture. This allows for the generation of more appropriate avatars by having the avatar perform specific gestures in response to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI execute the avatar gesture settings.

[0088] The generation unit can estimate the user's emotions and adjust the frequency of avatar generation based on the estimated emotions. For example, if the user is relaxed, the generation unit may set the avatar generation frequency low. If the user is angry, the generation unit may set the avatar generation frequency high. Furthermore, if the user is stressed, the generation unit may set the avatar generation frequency to a moderate level. By adjusting the avatar generation frequency based on the user's emotions, a more appropriate avatar can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input user emotion data into a generation AI and have the generation AI perform the avatar generation frequency adjustment.

[0089] The generation unit can change the gender and age of the avatar based on the analysis results of the customer's voice. For example, if the customer's voice sounds youthful, the generation unit can set the avatar to a young person. Also, if the customer's voice sounds calm, the generation unit can set the avatar to a middle-aged person. Furthermore, if the customer's voice sounds elderly, the generation unit can set the avatar to an elderly person. In this way, by changing the gender and age of the avatar based on the voice analysis results, a more appropriate avatar can be generated. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the customer's voice analysis data into a generation AI and have the generation AI perform the changes to the avatar's gender and age.

[0090] The generation unit can configure the avatar to hold specific tools or accessories depending on the content of the customer's voice. For example, if the customer is talking about travel, the generation unit can make the avatar hold a travel bag. Similarly, if the customer is talking about work, the avatar can hold a laptop. Furthermore, if the customer is talking about hobbies, the generation unit can make the avatar hold tools related to those hobbies. This allows for the generation of more appropriate avatars by having the avatar hold specific tools or accessories according to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI configure the avatar's tools and accessories.

[0091] The display unit can estimate the user's emotions and adjust the avatar's display method based on the estimated emotions. For example, if the user is tense, the display unit can display the avatar smaller to reduce visual strain. Conversely, if the user is relaxed, the display unit can display the avatar larger to emphasize friendliness. Furthermore, if the user is angry, the display unit can display the avatar at a medium size to maintain balance. This allows for a more appropriate display by adjusting the avatar's display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the display unit may be performed using, for example, a generative AI, or without one. For example, the display unit can input user emotion data into a generative AI and have the generative AI adjust the avatar's display method.

[0092] The display unit can select the optimal display method when displaying an avatar by referring to the operator's past reaction history. For example, the display unit may prioritize display methods that the operator has preferred in the past. The display unit can also exclude display methods that the operator has avoided in the past. Furthermore, the display unit can select the most effective display method from the operator's past reaction history. In this way, the optimal display method can be selected by referring to the operator's past reaction history. Some or all of the above processing in the display unit may be performed using, for example, a generating AI, or without a generating AI. For example, the display unit can input the operator's past reaction history data into a generating AI and have the generating AI select the optimal display method.

[0093] The display unit can adjust the display position of the avatar according to the operator's screen layout when displaying it. For example, if the operator's screen layout is vertical, the display unit will display the avatar at the top of the screen. If the operator's screen layout is horizontal, the display unit can also display the avatar on the left side of the screen. Furthermore, if the operator's screen layout is divided, the display unit can display the avatar in the position with the highest visibility. In this way, visibility can be improved by adjusting the display position according to the operator's screen layout. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's screen layout data into a generation AI and have the generation AI perform the adjustment of the display position.

[0094] The display unit can estimate the user's emotions and adjust the avatar's display time based on the estimated emotions. For example, if the user is tense, the display unit can set the avatar's display time to be shorter. Conversely, if the user is relaxed, the display unit can set the avatar's display time to be longer. Furthermore, if the user is angry, the display unit can set the avatar's display time to be moderate. This allows for a more appropriate display by adjusting the avatar's display time based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the display unit may be performed using a generative AI, or not. For example, the display unit can input user emotion data into a generative AI and have the generative AI adjust the avatar's display time.

[0095] The display unit can select the optimal display method when displaying an avatar, taking into account the operator's device information. For example, if the operator is using a smartphone, the display unit can provide a display method that matches the screen size. Furthermore, if the operator is using a tablet, the display unit can provide a display method optimized for a larger screen. Additionally, if the operator is using a desktop, the display unit can provide a display method that supports multiple windows. This allows the optimal display method to be selected by considering the operator's device information. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's device information into the generation AI and have the generation AI select the optimal display method.

[0096] The display unit can dynamically change the display position of the avatar using the operator's eye-tracking data when displaying the avatar. For example, if the operator's gaze is focused on the left side of the screen, the display unit will display the avatar on the right side. The display unit can also display the avatar in the center if the operator's gaze is focused on the center of the screen. Furthermore, if the operator's gaze is focused on the right side of the screen, the display unit can display the avatar on the left side. In this way, the display position can be dynamically changed using the operator's eye-tracking data. Some or all of the above processing in the display unit may be performed using, for example, a generation AI, or without a generation AI. For example, the display unit can input the operator's eye-tracking data into a generation AI and have the generation AI perform the dynamic change of the display position.

[0097] The facilitator can estimate the user's emotions and adjust the operator's response based on the estimated emotions. For example, if the user is angry, the facilitator can prompt the operator to respond calmly and politely. It can also prompt the operator to respond in a friendly manner if the user is relaxed. Furthermore, if the user is tense, the facilitator can prompt the operator to respond in a reassuring manner. This allows for more appropriate responses by adjusting the operator's response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the facilitator may be performed using, for example, a generative AI, or not. For example, the facilitator can input user emotion data into a generative AI and have the generative AI adjust the operator's response.

[0098] The support unit can analyze the operator's past response history and propose the optimal response method. For example, the support unit can prioritize proposing response methods that the operator has successfully used in the past. It can also suggest that the operator avoid response methods that have failed in the past. Furthermore, the support unit can propose the most effective response method based on the operator's past response history. In this way, the support unit can propose the optimal response method by analyzing the operator's past response history. Some or all of the above processing in the support unit may be performed using, for example, a generative AI, or without a generative AI. For example, the support unit can input the operator's past response history data into a generative AI and have the generative AI propose the optimal response method.

[0099] The Facilitation Unit can monitor the operator's current stress level and provide appropriate response methods. For example, if the operator's stress level is high, the Facilitation Unit can provide a simple and effective response method. Furthermore, if the operator's stress level is low, the Facilitation Unit can provide a detailed response method. In addition, if the operator's stress level is moderate, the Facilitation Unit can provide a balanced response method. This allows for the provision of appropriate response methods by monitoring the operator's stress level. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Facilitation Unit can input operator stress level data into a generative AI and have the generative AI provide appropriate response methods.

[0100] The facilitation unit can estimate the user's emotions and determine the operator's response priority based on the estimated emotions. For example, if the user is angry, the facilitation unit can instruct the operator to prioritize that user. If the user is relaxed, the facilitation unit can also instruct the operator to respond normally. Furthermore, if the user is tense, the facilitation unit can instruct the operator to respond quickly. This allows important responses to be prioritized by determining the response priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the facilitation unit may be performed using a generative AI, or not using a generative AI. For example, the facilitation unit can input user emotion data into a generative AI and have the generative AI determine the response priority.

[0101] The Facilitation Unit can provide real-time feedback to operators during their interactions, thereby improving the quality of their responses. For example, the Facilitation Unit can provide feedback at the appropriate time while the operator is interacting with the customer. It can also point out areas for improvement in real time while the operator is interacting with the customer. Furthermore, the Facilitation Unit can share successful cases in real time while the operator is interacting with the customer. This allows for improved quality of responses through the provision of real-time feedback. Some or all of the above processes in the Facilitation Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Facilitation Unit can input operator interaction data into a generative AI and have the generative AI provide real-time feedback.

[0102] The Facilitation Unit can suggest response methods by referring to successful case studies of other operators when an operator is handling a situation. For example, the Facilitation Unit can suggest response methods that have worked for other operators. It can also suggest avoiding response methods that have failed for other operators. Furthermore, the Facilitation Unit can suggest the optimal response method based on the successful case studies of other operators. In this way, the Facilitation Unit can suggest the optimal response method by referring to the successful case studies of other operators. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the Facilitation Unit can input data on successful case studies of other operators into a generating AI and have the generating AI execute the suggestion of response methods.

[0103] The feedback generation unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is satisfied, the feedback generation unit will provide positive feedback. If the user is dissatisfied, the feedback generation unit can also provide feedback that includes areas for improvement. Furthermore, if the user is neutral, the feedback generation unit can provide balanced feedback. This allows for the provision of more appropriate feedback by adjusting the content of the feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the feedback generation unit may be performed using a generative AI, or not using a generative AI. For example, the feedback generation unit can input user emotion data into a generative AI and have the generative AI adjust the content of the feedback.

[0104] The feedback generation unit can provide optimal feedback by referring to the operator's past feedback history. For example, the feedback generation unit can provide optimal feedback based on feedback the operator has received in the past. It can also provide feedback based on improvements the operator has made in the past. Furthermore, the feedback generation unit can provide the most effective feedback from the operator's past feedback history. In this way, it can provide optimal feedback by referring to past feedback history. Some or all of the above processing in the feedback generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback generation unit can input the operator's past feedback history data into a generation AI and have the generation AI perform the task of providing optimal feedback.

[0105] The feedback generation unit can customize the content of feedback by considering the operator's current work situation when generating it. For example, if the operator is busy, the feedback generation unit can provide concise and to-the-point feedback. If the operator has time, the feedback generation unit can also provide detailed feedback. Furthermore, if the operator is stressed, the feedback generation unit can provide feedback that includes words of encouragement. In this way, more appropriate feedback can be provided by considering the operator's work situation. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input operator work situation data into the generation AI and have the generation AI perform the customization of the feedback content.

[0106] The feedback generation unit can estimate the user's emotions and adjust the timing of feedback based on the estimated emotions. For example, if the user is satisfied, the feedback generation unit can provide feedback immediately. If the user is dissatisfied, the feedback generation unit can provide feedback after a cooling-off period. Furthermore, if the user is neutral, the feedback generation unit can provide feedback at an appropriate time. This allows for more appropriate timing of feedback by adjusting the timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the feedback generation unit may be performed using a generative AI, or not. For example, the feedback generation unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the feedback timing.

[0107] The feedback generation unit can adjust the content of the feedback while considering the operator's individual characteristics. For example, if the operator prefers positive feedback, the feedback generation unit will emphasize positive content. Furthermore, if the operator prefers detailed feedback, the feedback generation unit can provide detailed content. Additionally, if the operator prefers concise feedback, the feedback generation unit can provide concise content. This allows for the provision of more appropriate feedback by considering the operator's individual characteristics. Some or all of the above processing in the feedback generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the feedback generation unit can input the operator's individual characteristics data into a generation AI and have the generation AI adjust the feedback content.

[0108] The feedback generation unit can provide optimal feedback by referring to the feedback content of other operators when generating feedback. For example, the feedback generation unit can refer to positive feedback received by other operators. It can also refer to areas for improvement received by other operators. Furthermore, the feedback generation unit can provide optimal feedback based on the feedback content of other operators. In this way, it can provide optimal feedback by referring to the feedback content of other operators. Some or all of the above processing in the feedback generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the feedback generation unit can input the feedback content data of other operators into a generation AI and have the generation AI perform the task of providing optimal feedback.

[0109] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0110] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is angry, the emotion engine can set the emotion intensity high and perform a detailed analysis. If the user is relaxed, the emotion engine can set the emotion intensity low and perform a simpler analysis. Furthermore, if the user is tense, the emotion engine can track emotional fluctuations in real time and dynamically adjust the accuracy of the analysis. This allows for more accurate analysis results by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the analysis accuracy.

[0111] The generation unit can estimate the user's emotions and adjust the avatar's facial expressions and movements based on the estimated emotions. For example, if the user is relaxed, the avatar will have a calm facial expression and relaxed movements. The generation unit can also make the avatar have a calm facial expression and gentle movements if the user is angry. Furthermore, if the user is tense, the avatar can have a reassuring facial expression and movements. This allows for the generation of a more appropriate avatar by adjusting its facial expressions and movements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input user emotion data into a generation AI and have the generation AI adjust the avatar's facial expressions and movements.

[0112] The display unit can estimate the user's emotions and adjust the avatar's display method based on the estimated emotions. For example, if the user is tense, the display unit can display the avatar smaller to reduce visual strain. Conversely, if the user is relaxed, the display unit can display the avatar larger to emphasize friendliness. Furthermore, if the user is angry, the display unit can display the avatar at a medium size to maintain balance. This allows for a more appropriate display by adjusting the avatar's display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the display unit may be performed using, for example, a generative AI, or without one. For example, the display unit can input user emotion data into a generative AI and have the generative AI adjust the avatar's display method.

[0113] The facilitator can estimate the user's emotions and adjust the operator's response based on the estimated emotions. For example, if the user is angry, the facilitator can prompt the operator to respond calmly and politely. It can also prompt the operator to respond in a friendly manner if the user is relaxed. Furthermore, if the user is tense, the facilitator can prompt the operator to respond in a reassuring manner. This allows for more appropriate responses by adjusting the operator's response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the facilitator may be performed using, for example, a generative AI, or not. For example, the facilitator can input user emotion data into a generative AI and have the generative AI adjust the operator's response.

[0114] The feedback generation unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is satisfied, the feedback generation unit will provide positive feedback. If the user is dissatisfied, the feedback generation unit can also provide feedback that includes areas for improvement. Furthermore, if the user is neutral, the feedback generation unit can provide balanced feedback. This allows for the provision of more appropriate feedback by adjusting the content of the feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the feedback generation unit may be performed using a generative AI, or not using a generative AI. For example, the feedback generation unit can input user emotion data into a generative AI and have the generative AI adjust the content of the feedback.

[0115] The analysis unit can analyze the background sound of the customer's voice and provide information for generating an avatar appropriate to the environment. For example, if the background sound is quiet, the analysis unit can generate an avatar that simulates an office environment. If the background sound is noisy, the analysis unit can also generate an avatar that simulates an outdoor environment. Furthermore, if the background sound contains a specific sound (e.g., music or traffic noise), the analysis unit can generate an avatar that corresponds to that sound. By providing information for avatar generation based on the background sound, it is possible to generate a more appropriate avatar. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input background sound data into a generation AI and have the generation AI perform the task of providing information for avatar generation.

[0116] The generation unit can customize the avatar's clothing and background based on the customer's voice tone. For example, if the tone is calm, the generation unit may give the avatar casual clothing and a relaxed background. If the tone is formal, the generation unit may give the avatar a business suit and an office background. Furthermore, if the tone is cheerful, the generation unit may give the avatar bright clothing and a cheerful background. This allows for the generation of more appropriate avatars by customizing the avatar's clothing and background based on the voice tone. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input the customer's voice tone data into a generation AI and have the generation AI customize the avatar's clothing and background.

[0117] The generation unit can be configured to have the avatar perform specific gestures in response to the content of the customer's voice. For example, if the customer expresses gratitude, the generation unit can have the avatar smile and bow. The generation unit can also have the avatar assume a thinking pose if the customer asks a question. Furthermore, if the customer expresses anger, the generation unit can have the avatar perform a calming gesture. This allows for the generation of more appropriate avatars by having the avatar perform specific gestures in response to the content of the voice. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input customer voice content data into a generation AI and have the generation AI execute the avatar gesture settings.

[0118] The display unit can select the optimal display method when displaying an avatar by referring to the operator's past reaction history. For example, the display unit may prioritize display methods that the operator has preferred in the past. The display unit can also exclude display methods that the operator has avoided in the past. Furthermore, the display unit can select the most effective display method from the operator's past reaction history. In this way, the optimal display method can be selected by referring to the operator's past reaction history. Some or all of the above processing in the display unit may be performed using, for example, a generating AI, or without a generating AI. For example, the display unit can input the operator's past reaction history data into a generating AI and have the generating AI select the optimal display method.

[0119] The Facilitation Unit can monitor the operator's current stress level and provide appropriate response methods. For example, if the operator's stress level is high, the Facilitation Unit can provide a simple and effective response method. Furthermore, if the operator's stress level is low, the Facilitation Unit can provide a detailed response method. In addition, if the operator's stress level is moderate, the Facilitation Unit can provide a balanced response method. This allows for the provision of appropriate response methods by monitoring the operator's stress level. Some or all of the above processing in the Facilitation Unit may be performed using, for example, a generative AI, or without a generative AI. For example, the Facilitation Unit can input operator stress level data into a generative AI and have the generative AI provide appropriate response methods.

[0120] The following briefly describes the processing flow for example form 2.

[0121] Step 1: The analysis unit analyzes the customer's voice and tone. The analysis unit can analyze the frequency and volume of the customer's voice using speech recognition technology and analyze the customer's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes the tone and emotional expression of the customer's voice and provides information for avatar generation. Step 2: The generation unit generates an avatar based on the information analyzed by the analysis unit. The generation unit can generate avatars using 3D models or animated characters. For example, it can generate a gentle, smiling avatar based on the analyzed information. Step 3: The display unit displays the avatar generated by the generation unit. The display unit displays the avatar and video on the operator's screen and places them in a specific position on the screen so that they are easily visible to the operator. Step 4: The facilitator facilitates the operator's response based on the avatar displayed by the display unit. The facilitator helps to ease the operator's tension, reduce stress, and encourage a gentle, smiling response. Step 5: The feedback generation unit generates feedback regarding the response facilitated by the facilitation unit. The feedback generation unit generates feedback in gentle and humorous language, providing specific feedback on the operator's response. For example, it might provide feedback such as, "That was a great response! Keep up the good work next time!"

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0124] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] Each of the multiple elements described above, including the analysis unit, generation unit, display unit, acceleration unit, and feedback generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit acquires the customer's voice using the microphone 38B of the smart device 14 and analyzes it using the specific processing unit 290 of the data processing unit 12. The generation unit generates an avatar using the specific processing unit 290 of the data processing unit 12. The display unit displays the generated avatar using the display 40A of the smart device 14. The acceleration unit facilitates the operator's response using the control unit 46A of the smart device 14. The feedback generation unit generates feedback using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0126] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0127] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0136] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements described above, including the analysis unit, generation unit, display unit, acceleration unit, and feedback generation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit acquires the customer's voice using the microphone 238 of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing unit 12. The generation unit generates an avatar using the specific processing unit 290 of the data processing unit 12, for example. The display unit displays the generated avatar using the display of the smart glasses 214, for example. The acceleration unit facilitates the operator's response using the control unit 46A of the smart glasses 214, for example. The feedback generation unit generates feedback using the specific processing unit 290 of the data processing unit 12, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0142] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0143] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0145] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0150] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the analysis unit, generation unit, display unit, acceleration unit, and feedback generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit acquires the customer's voice using the microphone 238 of the headset terminal 314 and analyzes it using the specific processing unit 290 of the data processing unit 12. The generation unit generates an avatar using the specific processing unit 290 of the data processing unit 12. The display unit displays the generated avatar using the display 343 of the headset terminal 314. The acceleration unit facilitates the operator's response using the control unit 46A of the headset terminal 314. The feedback generation unit generates feedback using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0158] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0159] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0165] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0166] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0167] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0172] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements described above, including the analysis unit, generation unit, display unit, acceleration unit, and feedback generation unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit acquires the customer's voice using the microphone 238 of the robot 414 and analyzes it using the specific processing unit 290 of the data processing unit 12. The generation unit generates an avatar using the specific processing unit 290 of the data processing unit 12, for example. The display unit displays the generated avatar using the display of the robot 414, for example. The acceleration unit facilitates the operator's response using the control unit 46A of the robot 414, for example. The feedback generation unit generates feedback using the specific processing unit 290 of the data processing unit 12, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0175] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0177] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0178] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0179] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0183] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0184] 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.

[0185] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0186] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0187] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0188] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0190] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0191] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0192] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0193] (Note 1) The analysis unit analyzes customer feedback and tone, A generation unit that generates an avatar based on the information analyzed by the analysis unit, A display unit that displays the avatar generated by the generation unit, A promotion unit that facilitates the operator's response based on the avatar displayed by the aforementioned display unit, The system includes a feedback generation unit that generates feedback regarding the response facilitated by the aforementioned acceleration unit. A system characterized by the following features. (Note 2) The generating unit is In case of complaints or angry customers, we generate videos of animals or comedians. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned display unit is The generated avatars and videos are displayed on the operator's screen. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback generation unit, Generate feedback with gentle and humorous words. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned promotion unit is To alleviate operator tension and reduce stress. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned feedback generation unit, Provide feedback to the operator The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, We analyze the background sounds of customer voices and provide information for generating avatars that are appropriate for the environment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It analyzes the speed and rhythm of the customer's voice and detects changes in emotion in real time. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing customer feedback, we refer to past call history to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing customer feedback, the analysis takes into account regional dialects and accents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the user's emotions and adjusts the avatar's facial expressions and movements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is Customize the avatar's clothing and background based on the tone of the customer's voice. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is The avatar can be configured to perform specific gestures based on the content of customer feedback. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the frequency of avatar generation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is Based on the analysis of customer feedback, we will change the gender and age of the avatar. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is Based on customer feedback, we can configure avatars to hold specific tools or accessories. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned display unit is It estimates the user's emotions and adjusts how the avatar is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned display unit is When displaying the avatar, the system selects the optimal display method by referring to the operator's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned display unit is When displaying the avatar, adjust its display position according to the operator's screen layout. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned display unit is It estimates the user's emotions and adjusts the avatar's display time based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned display unit is When displaying the avatar, the optimal display method is selected considering the operator's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned display unit is When displaying the avatar, the display position is dynamically changed using the operator's eye-tracking data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned promotion unit is The system estimates the user's emotions and adjusts the operator's response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned promotion unit is We analyze the operator's past interaction history and propose the most suitable response method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned promotion unit is Monitor the operator's current stress level and provide appropriate support. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned promotion unit is The system estimates the user's emotions and determines the operator's response priority based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned promotion unit is Provide real-time feedback to operators during their interactions to improve the quality of service. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned promotion unit is When an operator is handling a case, they should refer to successful case studies from other operators to suggest a solution. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned feedback generation unit, It estimates the user's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned feedback generation unit, Refer to the operator's past feedback history to provide the best possible feedback. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned feedback generation unit, When generating feedback, customize the content to take into account the operator's current work situation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned feedback generation unit, It estimates the user's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned feedback generation unit, When generating feedback, adjust the content to take into account the individual characteristics of the operator. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned feedback generation unit, When generating feedback, refer to the feedback content of other operators to provide the most optimal content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes customer feedback and tone, A generation unit that generates an avatar based on the information analyzed by the analysis unit, A display unit that displays the avatar generated by the generation unit, A promotion unit that facilitates the operator's response based on the avatar displayed by the aforementioned display unit, The system includes a feedback generation unit that generates feedback regarding the response facilitated by the aforementioned acceleration unit. A system characterized by the following features.

2. The generating unit is In case of complaints or angry customers, we generate videos of animals or comedians. The system according to feature 1.

3. The aforementioned display unit is The generated avatars and videos are displayed on the operator's screen. The system according to feature 1.

4. The aforementioned feedback generation unit, Generate feedback with gentle and humorous words. The system according to feature 1.

5. The aforementioned promotion unit is To alleviate operator tension and reduce stress. The system according to feature 1.

6. The aforementioned feedback generation unit, Provide feedback to the operator The system according to feature 1.

7. The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system according to feature 1.

8. The aforementioned analysis unit, We analyze the background sounds of customer voices and provide information for generating avatars that are appropriate for the environment. The system according to feature 1.

9. The aforementioned analysis unit, It analyzes the speed and rhythm of the customer's voice and detects changes in emotion in real time. The system according to feature 1.

Images