system

Abstract

The system according to this embodiment aims to enable early detection of fraud and countermeasures against customer harassment in internal consultations and customer service. [Solution] The system according to this embodiment comprises a reception unit, a review unit, and a notification unit. The reception unit receives information from the person seeking advice. The review unit considers a course of action in accordance with company regulations and laws based on the information received by the reception unit. The notification unit notifies the relevant personnel within the company if, as a result of the review by the review unit, a serious misconduct has occurred.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that early detection of fraud and countermeasures against customer harassment are not sufficiently carried out in internal consultations and customer responses.

[0005] The system according to the embodiment aims to perform early detection of fraud and countermeasures against customer harassment in internal consultations and customer responses.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a review unit, and a notification unit. The reception unit receives information from the person seeking advice. The review unit considers a course of action based on the information received by the reception unit, in accordance with internal regulations and laws. The notification unit notifies the relevant personnel within the company if, as a result of the review by the review unit, a serious misconduct has occurred. [Effects of the Invention]

[0007] The system according to this embodiment can enable early detection of fraud and measures against customer harassment in internal consultations and customer service. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI-powered internal consultation and customer support tools according to the embodiment of the present invention are systems that are useful for the early detection of fraud and measures against customer harassment. This system allows users to consult with an AI in a metaverse space, enabling detailed investigation and problem resolution without direct involvement from the relevant department. The AI ​​considers response policies in accordance with internal regulations and laws, verifies whether there are any violations of those regulations or laws, and provides a response to the user. If serious fraud has occurred, the AI ​​relays the information to the appropriate internal person. This provides an environment where people who were unable to determine whether a violation occurred and therefore could not consult with the relevant department can easily seek advice. Furthermore, by introducing the system into a call center, it becomes possible to handle customer complaints. By learning the terms and conditions and contract details with customers, the AI ​​can respond to even minor customer inquiries, resolving situations where call centers are subjected to lengthy complaints. Thus, the AI-powered internal consultation and customer support tools are useful for the early detection of fraud and measures against customer harassment, contributing to improved efficiency and security throughout the organization. As a result, the AI-powered internal consultation and customer support tools enable quick and accurate responses, contributing to improved efficiency and security throughout the organization.

[0029] The AI-powered internal consultation and customer support tool according to this embodiment comprises a reception unit, a review unit, and a notification unit. The reception unit receives information from the person seeking consultation. The reception unit can, for example, receive information from the person seeking consultation in a metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, and the person seeking consultation can do so through an avatar. The review unit considers a response policy in accordance with internal regulations and laws based on the information received by the reception unit. The review unit can, for example, learn internal regulations and laws and check for violations. The review unit can learn internal regulations and laws using AI and consider an appropriate response policy. The notification unit informs the relevant person in charge if, as a result of the review by the review unit, a serious misconduct has occurred. The notification unit can notify the relevant person in charge using, for example, email or app notifications. The notification unit can generate notification content using AI and notify the appropriate person in charge. As a result, the AI-powered internal consultation and customer support tools according to this embodiment will receive information from those seeking advice, consider response policies based on internal regulations and laws, and notify if serious misconduct has occurred, thereby contributing to the early detection of misconduct and measures against customer harassment.

[0030] The reception desk receives information from clients. For example, the reception desk can receive information from clients in a metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where clients can conduct consultations through avatars. Specifically, clients wear a dedicated VR headset and access a consultation booth in the virtual space. There, they can operate their avatar to input consultation details or conduct consultations by voice. The reception desk receives this information in real time and stores it in a database. Furthermore, the reception desk can use natural language processing technology to automatically classify the consultation content and distribute it to the appropriate department or person in charge. For example, if the consultation content is related to human resources, it will be automatically forwarded to the human resources department. The reception desk can also refer to the client's past consultation history and related information to enable faster and more accurate responses. In this way, the reception desk can efficiently receive information from clients and quickly transmit it to the appropriate department or person in charge.

[0031] The review department considers response policies in accordance with company regulations and laws based on the information received by the reception department. For example, the review department can learn about company regulations and laws and check for violations. Specifically, it uses AI to learn about company regulations and laws and consider appropriate response policies. The AI ​​uses natural language processing technology to analyze company regulations and legal documents and evaluate their relevance to the content of the consultation. For example, if the consultation concerns working hours, it will refer to the Labor Standards Act and the company's working hours management regulations to check for violations. In addition, the AI ​​can propose response policies for similar cases based on past cases and precedents. Furthermore, the AI ​​can perform sentiment analysis of the consultation content and understand the emotional state of the person seeking advice, thereby considering more appropriate response policies. As a result, the review department can quickly consider appropriate response policies based on company regulations and laws and provide accurate advice to the person seeking advice.

[0032] The notification department, based on the review by the investigation department, will inform internal personnel if a serious misconduct has occurred. The notification department can notify internal personnel using methods such as email or app notifications. Specifically, it uses AI to generate notification content and send it to the appropriate personnel. The AI ​​automatically generates notification content based on information provided by the investigation department. For example, if a serious misconduct has occurred, it will create a notification document that includes details of the incident, its scope of impact, and its urgency. The AI ​​also refers to a list of internal personnel and sends the notification to the most appropriate person. Notifications may be sent using multiple methods, including not only email and app notifications, but also SMS and voice calls. Furthermore, the notification department can manage the notification sending history and confirm whether the notification was successfully received. This allows the notification department to quickly and reliably notify internal personnel when a serious misconduct occurs, encouraging early action.

[0033] The learning unit allows the AI ​​to learn company regulations and laws. For example, the learning unit can learn company regulations and laws using supervised learning. Supervised learning is a method of training the AI ​​using pre-labeled data and is used to detect violations of company regulations and laws. The learning unit can also learn company regulations and laws using unsupervised learning. Unsupervised learning is a method of training the AI ​​using unlabeled data and is used to detect patterns and anomalies. Furthermore, the learning unit can also learn company regulations and laws using reinforcement learning. Reinforcement learning is a method of learning the optimal action through trial and error and is used to detect violations of complex regulations and laws. As a result, the accuracy of response strategies improves as the AI ​​learns company regulations and laws.

[0034] The response unit allows AI to answer questions from callers. For example, the response unit can generate answers to callers' questions using natural language processing (NLP) technology. NLP is a technique for analyzing text data and understanding its meaning, and is used by the AI ​​to generate appropriate answers to callers' questions. The response unit can also answer callers using generative AI. Generative AI can generate answers to callers' questions using text generation AI (e.g., LLM). Generative AI has learned from large amounts of text data and possesses advanced natural language processing capabilities. Furthermore, the response unit can also answer callers using multimodal generative AI. Multimodal generative AI can handle multiple modals, including not only text but also images and audio. This allows for quick and appropriate responses from the AI ​​to callers.

[0035] The customer complaint handling department can use AI to handle customer complaints. For example, the customer complaint handling department can use natural language processing technology to analyze the content of customer complaints and provide appropriate responses. Natural language processing technology is a technology for analyzing text data and understanding its meaning, and is used by AI to provide appropriate responses to customer complaints. In addition, the customer complaint handling department can also use generative AI to handle customer complaints. Generative AI can generate responses to customer complaints using text generation AI (e.g., LLM). Generative AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. Furthermore, the customer complaint handling department can also use multimodal generative AI to handle customer complaints. Multimodal generative AI can handle multiple modals, such as images and audio, in addition to text. This improves the efficiency of customer complaint handling by allowing AI to handle customer complaints.

[0036] The reception desk can receive information from clients in the metaverse space. For example, the reception desk provides an interface for receiving information from clients in the metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where clients can conduct consultations through avatars. The reception desk provides a user-friendly interface to facilitate smooth consultations in the metaverse space. For example, the reception desk provides an intuitive interface that allows clients to easily input information. The reception desk can also record the content of consultations in the metaverse space for later reference. This provides an environment where clients can easily seek advice by receiving information in the metaverse space.

[0037] The review department can consider response policies based on internal regulations and laws. For example, the review department can learn internal regulations and laws and check for violations. The review department can use AI to learn internal regulations and laws and consider appropriate response policies. For example, the review department can consider response policies using an AI model that takes text data of internal regulations and laws as input and outputs whether or not there are violations. This makes it possible to take appropriate action by considering response policies based on internal regulations and laws.

[0038] The reception department can analyze a caller's past consultation history and select the most suitable reception method. For example, the reception department can automatically display relevant questions based on the topics the caller has frequently consulted about in the past. For example, the reception department can prioritize suggesting input methods (voice, text, etc.) that the caller has used in the past. For example, the reception department can predict and suggest input methods to be used during specific time periods based on the caller's past consultation history. In this way, by analyzing past consultation history, the reception department can provide the caller with the most suitable reception method. Some or all of the above processes in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input past consultation history data into a generating AI and have the generating AI select the most suitable reception method.

[0039] The reception desk can filter information based on the caller's current situation and areas of interest. For example, when a caller enters their current situation, the reception desk prioritizes displaying relevant information. For example, the reception desk filters and displays relevant information based on the caller's areas of interest. For example, if a caller is in a specific situation, the reception desk automatically filters and displays information related to that situation. This allows for more appropriate responses by providing information tailored to the caller's situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input data on the caller's current situation and areas of interest into a generating AI and have the generating AI perform the information filtering.

[0040] The reception desk can prioritize receiving highly relevant information by considering the caller's geographical location. For example, if the caller is in a specific region, the reception desk will prioritize receiving information related to that region. For example, if the caller is on the move, the reception desk will prioritize receiving relevant information based on the caller's current location. For example, if the caller is in a specific location, the reception desk will prioritize receiving information related to that location. In this way, by considering geographical location information, the reception desk can prioritize receiving information that is highly relevant to the caller. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the caller's geographical location information into a generating AI and have the generating AI select highly relevant information.

[0041] The reception department can analyze the social media activity of the person seeking advice and receive relevant information. For example, the reception department can receive relevant information based on information shared by the person seeking advice on social media. For example, the reception department can analyze the person seeking advice's areas of interest from their social media activity and receive relevant information. For example, the reception department can receive relevant information based on accounts followed by the person seeking advice on social media. In this way, by analyzing social media activity, the reception department can receive information relevant to the person seeking advice. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the person seeking advice's social media activity data into a generating AI and have the generating AI select relevant information.

[0042] The review department can adjust the level of detail in the response policy based on the importance of internal regulations and laws. For example, the review department will consider a detailed response policy if the regulations or laws are of high importance. For example, the review department will consider a simplified response policy if the regulations or laws are of low importance. For example, the review department will adjust the level of detail in the response policy in stages according to the importance of the regulations and laws. This allows for appropriate responses by adjusting the level of detail in the response policy according to the importance of internal regulations and laws. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input data on the importance of internal regulations and laws into a generating AI and have the generating AI perform the adjustment of the level of detail in the response policy.

[0043] The review unit can apply different review algorithms depending on the category of the consultation content. For example, in the case of a consultation regarding harassment, the review unit applies a specific review algorithm. For example, in the case of a consultation regarding misconduct, the review unit applies a different review algorithm. For example, the review unit selects and applies an appropriate review algorithm depending on other categories. This allows for the provision of more appropriate response policies by applying a review algorithm that matches the category of the consultation content. Some or all of the above processing in the review unit may be performed using AI, for example, or without AI. For example, the review unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate review algorithm.

[0044] The review department can determine the priority of response strategies based on when the consultation content is submitted. For example, if the consultation content is urgent, the review department will quickly consider response strategies. For example, if the consultation content is normal, the review department will consider response strategies with normal priority. For example, the review department will adjust the priority of response strategies in stages according to when the consultation content is submitted. This allows for a more appropriate response time by determining the priority of response strategies according to when the consultation content is submitted. Some or all of the above processing in the review department may be performed using AI, for example, or without AI. For example, the review department can input consultation content submission timing data into a generating AI and have the generating AI determine the priority of response strategies.

[0045] The review unit can adjust the order of response strategies based on the relevance of the consultation content. For example, if the consultation content is highly relevant, the review unit will prioritize considering the response strategy. For example, if the consultation content is less relevant, the review unit will postpone considering the response strategy. For example, the review unit can adjust the order of response strategies in stages according to the relevance of the consultation content. By adjusting the order of response strategies according to the relevance of the consultation content, more relevant content can be addressed preferentially. Some or all of the above processing in the review unit may be performed using AI, for example, or without using AI. For example, the review unit can input the relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of response strategies.

[0046] The notification unit can adjust the level of detail of a notification based on the importance of the consultation content. For example, the notification unit provides a detailed notification for highly important consultation content. For example, the notification unit provides a simplified notification for less important consultation content. The notification unit adjusts the level of detail of the notification in stages according to the importance of the consultation content. This allows for more appropriate notifications by adjusting the level of detail of the notification according to the importance of the consultation content. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the importance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the level of detail of the notification.

[0047] The notification unit can apply different notification algorithms depending on the category of the consultation content when sending a notification. For example, the notification unit applies a specific notification algorithm in the case of a consultation regarding harassment. For example, the notification unit applies a different notification algorithm in the case of a consultation regarding misconduct. For example, the notification unit selects and applies an appropriate notification algorithm depending on other categories. This makes it possible to send more appropriate notifications by applying a notification algorithm that matches the category of the consultation content. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate notification algorithm.

[0048] The notification unit can determine the priority of notifications based on when the consultation content was submitted. For example, if the consultation content is urgent, the notification unit will send a notification quickly. For example, if the consultation content is normal, the notification unit will send a notification with normal priority. For example, the notification unit will adjust the priority of notifications in stages according to when the consultation content was submitted. This makes it possible to send notifications at a more appropriate time by determining the priority of notifications according to when the consultation content was submitted. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the consultation content submission time data into a generating AI and have the generating AI perform the determination of the notification priority.

[0049] The notification unit can adjust the order of notifications based on the relevance of the consultation content when sending notifications. For example, the notification unit will prioritize notifications for highly relevant consultation content. For example, the notification unit will postpone notifications for less relevant consultation content. For example, the notification unit will adjust the order of notifications in stages according to the relevance of the consultation content. By adjusting the order of notifications according to the relevance of the consultation content, more relevant content can be notified preferentially. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of notifications.

[0050] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data and perform learning. For example, the learning unit can extract effective learning patterns from past learning data and optimize the learning algorithm. For example, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm to optimize it. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0051] The learning unit can weight the learning data based on when the consultation content was submitted during the learning process. For example, if the consultation content was recently submitted, the learning unit will give it a higher weight during learning. For example, if the consultation content is old, the learning unit will give it a lower weight during learning. For example, the learning unit can adjust the weighting of the learning data in stages according to when the consultation content was submitted. This allows for more appropriate learning by weighting the learning data according to when the consultation content was submitted. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input the consultation content submission date data into a generating AI and have the generating AI perform the weighting of the learning data.

[0052] The response unit can adjust the level of detail in its response based on the importance of the consultation. For example, the response unit will provide a detailed response for highly important consultations. For example, the response unit will provide a simplified response for less important consultations. The response unit can adjust the level of detail in its response in stages according to the importance of the consultation. This allows for more appropriate responses by adjusting the level of detail according to the importance of the consultation. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the importance data of the consultation into a generating AI and have the generating AI perform the adjustment of the level of detail in the response.

[0053] The response unit can apply different response algorithms depending on the category of the consultation content when providing a response. For example, the response unit applies a specific response algorithm in the case of a consultation regarding harassment. For example, the response unit applies a different response algorithm in the case of a consultation regarding misconduct. For example, the response unit selects and applies an appropriate response algorithm depending on the other category. This makes it possible to provide a more appropriate response by applying a response algorithm that matches the category of the consultation content. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate response algorithm.

[0054] The response unit can determine the priority of responses based on when the consultation content was submitted. For example, if the consultation content is urgent, the response unit will respond quickly. For example, if the consultation content is normal, the response unit will respond with normal priority. For example, the response unit will adjust the priority of responses in stages according to when the consultation content was submitted. This allows for responses to be provided at a more appropriate time by determining the priority of responses according to when the consultation content was submitted. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input consultation content submission time data into a generating AI and have the generating AI perform the determination of the priority of responses.

[0055] The response unit can adjust the order of responses based on the relevance of the consultation content when providing answers. For example, the response unit will prioritize responses to highly relevant consultation content. For example, the response unit will postpone responses to less relevant consultation content. For example, the response unit can adjust the order of responses in stages according to the relevance of the consultation content. This allows for prioritizing responses to more relevant content by adjusting the order of responses according to the relevance of the consultation content. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of responses.

[0056] The claims handling unit can adjust the level of detail in its response based on the importance of the claim. For example, the claims handling unit will provide a detailed response for high-priority claims. For example, it will provide a simplified response for low-priority claims. The claims handling unit can adjust the level of detail in stages according to the importance of the claim. This allows for more appropriate claims handling by adjusting the level of detail according to the importance of the claim. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input data on the importance of the claim into a generating AI and have the generating AI perform the adjustment of the level of detail in the response.

[0057] The claims handling unit can apply different response algorithms depending on the category of the claims. For example, the claims handling unit applies a specific response algorithm to claims related to products. For example, it applies a different response algorithm to claims related to services. For example, the claims handling unit selects and applies an appropriate response algorithm depending on other categories. This allows for more appropriate claims handling by applying a response algorithm appropriate to the category of the claims. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input claim category data into a generating AI and have the generating AI select and apply an appropriate response algorithm.

[0058] The claims handling department can determine the priority of responses based on when the claims were submitted. For example, if the claims are urgent, the claims handling department will respond quickly. For example, if the claims are normal, the claims handling department will respond with normal priority. For example, the claims handling department can adjust the priority of responses in stages according to when the claims were submitted. This allows for more appropriate timing of claims by determining the priority of responses according to when the claims were submitted. Some or all of the above processing in the claims handling department may be performed using AI, for example, or without AI. For example, the claims handling department can input data on when the claims were submitted into a generating AI and have the generating AI determine the priority of responses.

[0059] The claims handling unit can adjust the order of handling claims based on the relevance of the claims. For example, the claims handling unit will prioritize handling claims that are highly relevant. For example, the claims handling unit will postpone handling claims that are less relevant. For example, the claims handling unit can adjust the order of handling claims in stages according to the relevance of the claims. This allows for prioritizing more relevant claims by adjusting the order of handling according to the relevance of the claims. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input relevance data of the claims into a generating AI and have the generating AI perform the adjustment of the order of handling.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The reception desk can analyze a caller's past consultation history and select the most suitable reception method. For example, it can automatically display relevant questions based on the topics the caller has frequently consulted about in the past. It can also prioritize suggesting input methods (voice, text, etc.) the caller has used in the past. Furthermore, it can predict and suggest input methods that the caller will use at specific times based on their past consultation history. In this way, by analyzing past consultation history, the reception desk can provide the caller with the most suitable reception method.

[0062] The review department can apply different review algorithms depending on the category of the consultation. For example, a specific review algorithm is applied to consultations regarding harassment. Another review algorithm is applied to consultations regarding misconduct. For other categories, an appropriate review algorithm is selected and applied. This allows for the provision of more appropriate response policies by applying a review algorithm that matches the category of the consultation.

[0063] The notification unit can adjust the level of detail in notifications based on the importance of the consultation content. For example, a detailed notification will be sent for highly important consultations, while a simplified notification will be sent for less important consultations. The level of detail in notifications is adjusted in stages according to the importance of the consultation content. This allows for more appropriate notifications by adjusting the level of detail according to the importance of the consultation content.

[0064] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can select the optimal learning algorithm based on past learning data and perform learning. It can extract effective learning patterns from past learning data and optimize the learning algorithm. It can analyze past learning data and adjust the parameters of the learning algorithm to optimize it. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved.

[0065] The response system can prioritize responses based on when the inquiry was submitted. For example, if the inquiry is urgent, a response will be given quickly. If the inquiry is not urgent, a response will be given with the usual priority. The priority of responses will be adjusted in stages according to when the inquiry was submitted. This allows for responses to be given at a more appropriate time by determining the priority of responses according to when the inquiry was submitted.

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

[0067] Step 1: The reception desk receives information from the client. For example, information can be received from the client in the metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where the client can conduct consultations through an avatar. Step 2: The review department considers a course of action based on the information received by the reception department, in accordance with internal regulations and laws. For example, it can learn about internal regulations and laws and check for any violations. The review department can use AI to learn about internal regulations and laws and consider an appropriate course of action. Step 3: The notification unit, based on the review by the investigation unit, will inform the relevant internal personnel if a serious fraud has occurred. For example, notifications can be sent via email or app notifications. The notification unit can use AI to generate notification content and send it to the appropriate personnel.

[0068] (Example of form 2) The AI-powered internal consultation and customer support tools according to the embodiment of the present invention are systems that are useful for the early detection of fraud and measures against customer harassment. This system allows users to consult with an AI in a metaverse space, enabling detailed investigation and problem resolution without direct involvement from the relevant department. The AI ​​considers response policies in accordance with internal regulations and laws, verifies whether there are any violations of those regulations or laws, and provides a response to the user. If serious fraud has occurred, the AI ​​relays the information to the appropriate internal person. This provides an environment where people who were unable to determine whether a violation occurred and therefore could not consult with the relevant department can easily seek advice. Furthermore, by introducing the system into a call center, it becomes possible to handle customer complaints. By learning the terms and conditions and contract details with customers, the AI ​​can respond to even minor customer inquiries, resolving situations where call centers are subjected to lengthy complaints. Thus, the AI-powered internal consultation and customer support tools are useful for the early detection of fraud and measures against customer harassment, contributing to improved efficiency and security throughout the organization. As a result, the AI-powered internal consultation and customer support tools enable quick and accurate responses, contributing to improved efficiency and security throughout the organization.

[0069] The AI-powered internal consultation and customer support tool according to this embodiment comprises a reception unit, a review unit, and a notification unit. The reception unit receives information from the person seeking consultation. The reception unit can, for example, receive information from the person seeking consultation in a metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, and the person seeking consultation can do so through an avatar. The review unit considers a response policy in accordance with internal regulations and laws based on the information received by the reception unit. The review unit can, for example, learn internal regulations and laws and check for violations. The review unit can learn internal regulations and laws using AI and consider an appropriate response policy. The notification unit informs the relevant person in charge if, as a result of the review by the review unit, a serious misconduct has occurred. The notification unit can notify the relevant person in charge using, for example, email or app notifications. The notification unit can generate notification content using AI and notify the appropriate person in charge. As a result, the AI-powered internal consultation and customer support tools according to this embodiment will receive information from those seeking advice, consider response policies based on internal regulations and laws, and notify if serious misconduct has occurred, thereby contributing to the early detection of misconduct and measures against customer harassment.

[0070] The reception desk receives information from clients. For example, the reception desk can receive information from clients in a metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where clients can conduct consultations through avatars. Specifically, clients wear a dedicated VR headset and access a consultation booth in the virtual space. There, they can operate their avatar to input consultation details or conduct consultations by voice. The reception desk receives this information in real time and stores it in a database. Furthermore, the reception desk can use natural language processing technology to automatically classify the consultation content and distribute it to the appropriate department or person in charge. For example, if the consultation content is related to human resources, it will be automatically forwarded to the human resources department. The reception desk can also refer to the client's past consultation history and related information to enable faster and more accurate responses. In this way, the reception desk can efficiently receive information from clients and quickly transmit it to the appropriate department or person in charge.

[0071] The review department considers response policies in accordance with company regulations and laws based on the information received by the reception department. For example, the review department can learn about company regulations and laws and check for violations. Specifically, it uses AI to learn about company regulations and laws and consider appropriate response policies. The AI ​​uses natural language processing technology to analyze company regulations and legal documents and evaluate their relevance to the content of the consultation. For example, if the consultation concerns working hours, it will refer to the Labor Standards Act and the company's working hours management regulations to check for violations. In addition, the AI ​​can propose response policies for similar cases based on past cases and precedents. Furthermore, the AI ​​can perform sentiment analysis of the consultation content and understand the emotional state of the person seeking advice, thereby considering more appropriate response policies. As a result, the review department can quickly consider appropriate response policies based on company regulations and laws and provide accurate advice to the person seeking advice.

[0072] The notification department, based on the review by the investigation department, will inform internal personnel if a serious misconduct has occurred. The notification department can notify internal personnel using methods such as email or app notifications. Specifically, it uses AI to generate notification content and send it to the appropriate personnel. The AI ​​automatically generates notification content based on information provided by the investigation department. For example, if a serious misconduct has occurred, it will create a notification document that includes details of the incident, its scope of impact, and its urgency. The AI ​​also refers to a list of internal personnel and sends the notification to the most appropriate person. Notifications may be sent using multiple methods, including not only email and app notifications, but also SMS and voice calls. Furthermore, the notification department can manage the notification sending history and confirm whether the notification was successfully received. This allows the notification department to quickly and reliably notify internal personnel when a serious misconduct occurs, encouraging early action.

[0073] The learning unit allows the AI ​​to learn company regulations and laws. For example, the learning unit can learn company regulations and laws using supervised learning. Supervised learning is a method of training the AI ​​using pre-labeled data and is used to detect violations of company regulations and laws. The learning unit can also learn company regulations and laws using unsupervised learning. Unsupervised learning is a method of training the AI ​​using unlabeled data and is used to detect patterns and anomalies. Furthermore, the learning unit can also learn company regulations and laws using reinforcement learning. Reinforcement learning is a method of learning the optimal action through trial and error and is used to detect violations of complex regulations and laws. As a result, the accuracy of response strategies improves as the AI ​​learns company regulations and laws.

[0074] The response unit allows AI to answer questions from callers. For example, the response unit can generate answers to callers' questions using natural language processing (NLP) technology. NLP is a technique for analyzing text data and understanding its meaning, and is used by the AI ​​to generate appropriate answers to callers' questions. The response unit can also answer callers using generative AI. Generative AI can generate answers to callers' questions using text generation AI (e.g., LLM). Generative AI has learned from large amounts of text data and possesses advanced natural language processing capabilities. Furthermore, the response unit can also answer callers using multimodal generative AI. Multimodal generative AI can handle multiple modals, including not only text but also images and audio. This allows for quick and appropriate responses from the AI ​​to callers.

[0075] The customer complaint handling department can use AI to handle customer complaints. For example, the customer complaint handling department can use natural language processing technology to analyze the content of customer complaints and provide appropriate responses. Natural language processing technology is a technology for analyzing text data and understanding its meaning, and is used by AI to provide appropriate responses to customer complaints. In addition, the customer complaint handling department can also use generative AI to handle customer complaints. Generative AI can generate responses to customer complaints using text generation AI (e.g., LLM). Generative AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. Furthermore, the customer complaint handling department can also use multimodal generative AI to handle customer complaints. Multimodal generative AI can handle multiple modals, such as images and audio, in addition to text. This improves the efficiency of customer complaint handling by allowing AI to handle customer complaints.

[0076] The reception desk can receive information from clients in the metaverse space. For example, the reception desk provides an interface for receiving information from clients in the metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where clients can conduct consultations through avatars. The reception desk provides a user-friendly interface to facilitate smooth consultations in the metaverse space. For example, the reception desk provides an intuitive interface that allows clients to easily input information. The reception desk can also record the content of consultations in the metaverse space for later reference. This provides an environment where clients can easily seek advice by receiving information in the metaverse space.

[0077] The review department can consider response policies based on internal regulations and laws. For example, the review department can learn internal regulations and laws and check for violations. The review department can use AI to learn internal regulations and laws and consider appropriate response policies. For example, the review department can consider response policies using an AI model that takes text data of internal regulations and laws as input and outputs whether or not there are violations. This makes it possible to take appropriate action by considering response policies based on internal regulations and laws.

[0078] The reception desk can estimate the caller's emotions and adjust the information processing method based on the estimated emotions. For example, if the caller is nervous, the reception desk can provide a relaxing interface and simplify the input procedure. For example, if the caller is angry, the reception desk can provide a calming interface and allow for quick input. For example, if the caller is feeling anxious, the reception desk can provide a reassuring interface and guide the input procedure carefully. By adjusting the information processing method according to the caller's emotions, the caller can provide information more comfortably. 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.

[0079] The reception department can analyze a caller's past consultation history and select the most suitable reception method. For example, the reception department can automatically display relevant questions based on the topics the caller has frequently consulted about in the past. For example, the reception department can prioritize suggesting input methods (voice, text, etc.) that the caller has used in the past. For example, the reception department can predict and suggest input methods to be used during specific time periods based on the caller's past consultation history. In this way, by analyzing past consultation history, the reception department can provide the caller with the most suitable reception method. Some or all of the above processes in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input past consultation history data into a generating AI and have the generating AI select the most suitable reception method.

[0080] The reception desk can filter information based on the caller's current situation and areas of interest. For example, when a caller enters their current situation, the reception desk prioritizes displaying relevant information. For example, the reception desk filters and displays relevant information based on the caller's areas of interest. For example, if a caller is in a specific situation, the reception desk automatically filters and displays information related to that situation. This allows for more appropriate responses by providing information tailored to the caller's situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input data on the caller's current situation and areas of interest into a generating AI and have the generating AI perform the information filtering.

[0081] The reception desk can estimate the caller's emotions and determine the priority of information to receive based on the estimated emotions. For example, if the caller feels urgent, the reception desk will prioritize receiving information of high urgency. For example, if the caller is relaxed, the reception desk will prioritize receiving detailed information. For example, if the caller is anxious, the reception desk will prioritize receiving information that provides reassurance. In this way, by prioritizing information according to the caller's emotions, it is possible to receive more urgent information first. 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.

[0082] The reception desk can prioritize receiving highly relevant information by considering the caller's geographical location. For example, if the caller is in a specific region, the reception desk will prioritize receiving information related to that region. For example, if the caller is on the move, the reception desk will prioritize receiving relevant information based on the caller's current location. For example, if the caller is in a specific location, the reception desk will prioritize receiving information related to that location. In this way, by considering geographical location information, the reception desk can prioritize receiving information that is highly relevant to the caller. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the caller's geographical location information into a generating AI and have the generating AI select highly relevant information.

[0083] The reception department can analyze the social media activity of the person seeking advice and receive relevant information. For example, the reception department can receive relevant information based on information shared by the person seeking advice on social media. For example, the reception department can analyze the person seeking advice's areas of interest from their social media activity and receive relevant information. For example, the reception department can receive relevant information based on accounts followed by the person seeking advice on social media. In this way, by analyzing social media activity, the reception department can receive information relevant to the person seeking advice. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the person seeking advice's social media activity data into a generating AI and have the generating AI select relevant information.

[0084] The review unit can estimate the client's emotions and adjust the method of considering a response strategy based on the estimated emotions. For example, if the client is tense, the review unit will consider a response strategy that will help them relax. For example, if the client is angry, the review unit will consider a response strategy that will allow them to respond calmly. For example, if the client is feeling anxious, the review unit will consider a response strategy that will provide a sense of security. By adjusting the method of considering a response strategy according to the client's emotions, a more appropriate response strategy can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The review department can adjust the level of detail in the response policy based on the importance of internal regulations and laws. For example, the review department will consider a detailed response policy if the regulations or laws are of high importance. For example, the review department will consider a simplified response policy if the regulations or laws are of low importance. For example, the review department will adjust the level of detail in the response policy in stages according to the importance of the regulations and laws. This allows for appropriate responses by adjusting the level of detail in the response policy according to the importance of internal regulations and laws. Some or all of the above processes in the review department may be performed using AI, for example, or not using AI. For example, the review department can input data on the importance of internal regulations and laws into a generating AI and have the generating AI perform the adjustment of the level of detail in the response policy.

[0086] The review unit can apply different review algorithms depending on the category of the consultation content. For example, in the case of a consultation regarding harassment, the review unit applies a specific review algorithm. For example, in the case of a consultation regarding misconduct, the review unit applies a different review algorithm. For example, the review unit selects and applies an appropriate review algorithm depending on other categories. This allows for the provision of more appropriate response policies by applying a review algorithm that matches the category of the consultation content. Some or all of the above processing in the review unit may be performed using AI, for example, or without AI. For example, the review unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate review algorithm.

[0087] The review unit can estimate the client's emotions and determine the priority of response strategies based on the estimated emotions. For example, if the client feels a sense of urgency, the review unit will prioritize considering response strategies that are of high urgency. For example, if the client is relaxed, the review unit will prioritize considering detailed response strategies. For example, if the client is anxious, the review unit will prioritize considering response strategies that provide a sense of security. In this way, by determining the priority of response strategies according to the client's emotions, it is possible to provide the most urgent response strategies first. 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.

[0088] The review department can determine the priority of response strategies based on when the consultation content is submitted. For example, if the consultation content is urgent, the review department will quickly consider response strategies. For example, if the consultation content is normal, the review department will consider response strategies with normal priority. For example, the review department will adjust the priority of response strategies in stages according to when the consultation content is submitted. This allows for a more appropriate response time by determining the priority of response strategies according to when the consultation content is submitted. Some or all of the above processing in the review department may be performed using AI, for example, or without AI. For example, the review department can input consultation content submission timing data into a generating AI and have the generating AI determine the priority of response strategies.

[0089] The review unit can adjust the order of response strategies based on the relevance of the consultation content. For example, if the consultation content is highly relevant, the review unit will prioritize considering the response strategy. For example, if the consultation content is less relevant, the review unit will postpone considering the response strategy. For example, the review unit can adjust the order of response strategies in stages according to the relevance of the consultation content. By adjusting the order of response strategies according to the relevance of the consultation content, more relevant content can be addressed preferentially. Some or all of the above processing in the review unit may be performed using AI, for example, or without using AI. For example, the review unit can input the relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of response strategies.

[0090] The notification unit can estimate the caller's emotions and adjust the notification method based on the estimated emotions. For example, if the caller is nervous, the notification unit provides a notification method that helps them relax. For example, if the caller is angry, the notification unit provides a notification method that helps them respond calmly. For example, if the caller is feeling anxious, the notification unit provides a notification method that provides reassurance. By adjusting the notification method according to the caller's emotions, more appropriate notifications become possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The notification unit can adjust the level of detail of a notification based on the importance of the consultation content. For example, the notification unit provides a detailed notification for highly important consultation content. For example, the notification unit provides a simplified notification for less important consultation content. The notification unit adjusts the level of detail of the notification in stages according to the importance of the consultation content. This allows for more appropriate notifications by adjusting the level of detail of the notification according to the importance of the consultation content. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the importance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the level of detail of the notification.

[0092] The notification unit can apply different notification algorithms depending on the category of the consultation content when sending a notification. For example, the notification unit applies a specific notification algorithm in the case of a consultation regarding harassment. For example, the notification unit applies a different notification algorithm in the case of a consultation regarding misconduct. For example, the notification unit selects and applies an appropriate notification algorithm depending on other categories. This makes it possible to send more appropriate notifications by applying a notification algorithm that matches the category of the consultation content. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate notification algorithm.

[0093] The notification unit can estimate the caller's emotions and determine the priority of notifications based on the estimated emotions. For example, if the caller feels urgent, the notification unit will prioritize urgent notifications. For example, if the caller is relaxed, the notification unit will prioritize detailed notifications. For example, if the caller is anxious, the notification unit will prioritize reassuring notifications. In this way, by determining the priority of notifications according to the caller's emotions, it is possible to prioritize more urgent notifications. 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.

[0094] The notification unit can determine the priority of notifications based on when the consultation content was submitted. For example, if the consultation content is urgent, the notification unit will send a notification quickly. For example, if the consultation content is normal, the notification unit will send a notification with normal priority. For example, the notification unit will adjust the priority of notifications in stages according to when the consultation content was submitted. This makes it possible to send notifications at a more appropriate time by determining the priority of notifications according to when the consultation content was submitted. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the consultation content submission time data into a generating AI and have the generating AI perform the determination of the notification priority.

[0095] The notification unit can adjust the order of notifications based on the relevance of the consultation content when sending notifications. For example, the notification unit will prioritize notifications for highly relevant consultation content. For example, the notification unit will postpone notifications for less relevant consultation content. For example, the notification unit will adjust the order of notifications in stages according to the relevance of the consultation content. By adjusting the order of notifications according to the relevance of the consultation content, more relevant content can be notified preferentially. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of notifications.

[0096] The learning unit can estimate the client's emotions and select training data based on the estimated emotions. For example, if the client is nervous, the learning unit will select training data that helps them relax. For example, if the client is angry, the learning unit will select training data that helps them respond calmly. For example, if the client is feeling anxious, the learning unit will select training data that provides a sense of security. By selecting training data according to the client's emotions, more appropriate learning becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data and perform learning. For example, the learning unit can extract effective learning patterns from past learning data and optimize the learning algorithm. For example, the learning unit can analyze past learning data and adjust the parameters of the learning algorithm to optimize it. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0098] The learning unit can estimate the client's emotions and adjust the learning frequency based on the estimated emotions. For example, if the client is tense, the learning unit will lower the learning frequency to help them relax. For example, if the client is relaxed, the learning unit will increase the learning frequency to conduct more detailed learning. For example, if the client is feeling anxious, the learning unit will adjust the learning frequency to provide a sense of security. By adjusting the learning frequency according to the client's emotions, more appropriate learning becomes possible. 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.

[0099] The learning unit can weight the learning data based on when the consultation content was submitted during the learning process. For example, if the consultation content was recently submitted, the learning unit will give it a higher weight during learning. For example, if the consultation content is old, the learning unit will give it a lower weight during learning. For example, the learning unit can adjust the weighting of the learning data in stages according to when the consultation content was submitted. This allows for more appropriate learning by weighting the learning data according to when the consultation content was submitted. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input the consultation content submission date data into a generating AI and have the generating AI perform the weighting of the learning data.

[0100] The response unit can estimate the caller's emotions and adjust the expression of its response based on the estimated emotions. For example, if the caller is nervous, the response unit will respond in a way that helps them relax. For example, if the caller is angry, the response unit will respond in a way that allows them to respond calmly. For example, if the caller is feeling anxious, the response unit will respond in a way that provides reassurance. By adjusting the expression of the response according to the caller's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0101] The response unit can adjust the level of detail in its response based on the importance of the consultation. For example, the response unit will provide a detailed response for highly important consultations. For example, the response unit will provide a simplified response for less important consultations. The response unit can adjust the level of detail in its response in stages according to the importance of the consultation. This allows for more appropriate responses by adjusting the level of detail according to the importance of the consultation. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the importance data of the consultation into a generating AI and have the generating AI perform the adjustment of the level of detail in the response.

[0102] The response unit can apply different response algorithms depending on the category of the consultation content when providing a response. For example, the response unit applies a specific response algorithm in the case of a consultation regarding harassment. For example, the response unit applies a different response algorithm in the case of a consultation regarding misconduct. For example, the response unit selects and applies an appropriate response algorithm depending on the other category. This makes it possible to provide a more appropriate response by applying a response algorithm that matches the category of the consultation content. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the category data of the consultation content into a generating AI and have the generating AI select and apply an appropriate response algorithm.

[0103] The response unit can estimate the caller's emotions and determine the priority of responses based on the estimated emotions. For example, if the caller feels urgent, the response unit will prioritize responses of high urgency. For example, if the caller is relaxed, the response unit will prioritize detailed responses. For example, if the caller is anxious, the response unit will prioritize responses that provide reassurance. In this way, by determining the priority of responses according to the caller's emotions, it is possible to prioritize responses of higher urgency. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0104] The response unit can determine the priority of responses based on when the consultation content was submitted. For example, if the consultation content is urgent, the response unit will respond quickly. For example, if the consultation content is normal, the response unit will respond with normal priority. For example, the response unit will adjust the priority of responses in stages according to when the consultation content was submitted. This allows for responses to be provided at a more appropriate time by determining the priority of responses according to when the consultation content was submitted. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input consultation content submission time data into a generating AI and have the generating AI perform the determination of the priority of responses.

[0105] The response unit can adjust the order of responses based on the relevance of the consultation content when providing answers. For example, the response unit will prioritize responses to highly relevant consultation content. For example, the response unit will postpone responses to less relevant consultation content. For example, the response unit can adjust the order of responses in stages according to the relevance of the consultation content. This allows for prioritizing responses to more relevant content by adjusting the order of responses according to the relevance of the consultation content. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input relevance data of the consultation content into a generating AI and have the generating AI perform the adjustment of the order of responses.

[0106] The customer service department can estimate the customer's emotions and adjust its complaint handling methods based on those estimated emotions. For example, if the customer is angry, the department can provide a calm and composed complaint handling method. For example, if the customer is feeling anxious, the department can provide a reassuring complaint handling method. For example, if the customer is feeling stressed, the department can provide a relaxing complaint handling method. By adjusting the complaint handling method according to the customer's emotions, more appropriate complaint handling becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The claims handling unit can adjust the level of detail in its response based on the importance of the claim. For example, the claims handling unit will provide a detailed response for high-priority claims. For example, it will provide a simplified response for low-priority claims. The claims handling unit can adjust the level of detail in stages according to the importance of the claim. This allows for more appropriate claims handling by adjusting the level of detail according to the importance of the claim. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input data on the importance of the claim into a generating AI and have the generating AI perform the adjustment of the level of detail in the response.

[0108] The claims handling unit can apply different response algorithms depending on the category of the claims. For example, the claims handling unit applies a specific response algorithm to claims related to products. For example, it applies a different response algorithm to claims related to services. For example, the claims handling unit selects and applies an appropriate response algorithm depending on other categories. This allows for more appropriate claims handling by applying a response algorithm appropriate to the category of the claims. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input claim category data into a generating AI and have the generating AI select and apply an appropriate response algorithm.

[0109] The customer service department can estimate the customer's emotions and determine the priority of complaint handling based on those emotions. For example, if the customer feels a sense of urgency, the customer service department will prioritize handling high-priority complaints. For example, if the customer feels relaxed, the customer service department will prioritize handling detailed complaints. For example, if the customer feels anxious, the customer service department will prioritize handling complaints that provide reassurance. By determining the priority of complaint handling according to the customer's emotions, it is possible to prioritize handling more urgent complaints. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The claims handling department can determine the priority of responses based on when the claims were submitted. For example, if the claims are urgent, the claims handling department will respond quickly. For example, if the claims are normal, the claims handling department will respond with normal priority. For example, the claims handling department can adjust the priority of responses in stages according to when the claims were submitted. This allows for more appropriate timing of claims by determining the priority of responses according to when the claims were submitted. Some or all of the above processing in the claims handling department may be performed using AI, for example, or without AI. For example, the claims handling department can input data on when the claims were submitted into a generating AI and have the generating AI determine the priority of responses.

[0111] The claims handling unit can adjust the order of handling claims based on the relevance of the claims. For example, the claims handling unit will prioritize handling claims that are highly relevant. For example, the claims handling unit will postpone handling claims that are less relevant. For example, the claims handling unit can adjust the order of handling claims in stages according to the relevance of the claims. This allows for prioritizing more relevant claims by adjusting the order of handling according to the relevance of the claims. Some or all of the above processing in the claims handling unit may be performed using AI, for example, or without AI. For example, the claims handling unit can input relevance data of the claims into a generating AI and have the generating AI perform the adjustment of the order of handling.

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

[0113] The reception desk can estimate the client's emotions and suggest an appropriate avatar based on those estimates. For example, if the client is nervous, an avatar with a calm expression that promotes relaxation will be suggested. If the client is angry, an avatar with a composed expression that suggests a calm response will be suggested. If the client is feeling anxious, an avatar with a gentle expression that provides a sense of security will be suggested. By suggesting an avatar that matches the client's emotions, a more comfortable consultation environment can be provided.

[0114] The review department can estimate the client's emotions and adjust the approach to developing a response plan based on those estimated emotions. For example, if the client is nervous, the department will consider a response plan that helps them relax. If the client is angry, the department will consider a response plan that allows them to respond calmly. If the client is feeling anxious, the department will consider a response plan that provides a sense of security. By adjusting the approach to develop a response plan according to the client's emotions, the department can provide a more appropriate response plan.

[0115] The notification unit can estimate the caller's emotions and adjust the notification method based on those emotions. For example, if the caller is nervous, it can provide a notification method that helps them relax. If the caller is angry, it can provide a notification method that allows them to respond calmly. If the caller is feeling anxious, it can provide a notification method that provides reassurance. By adjusting the notification method according to the caller's emotions, more appropriate notifications can be provided.

[0116] The response unit can estimate the caller's emotions and adjust the way it expresses its response based on those emotions. For example, if the caller is nervous, it will respond in a way that helps them relax. If the caller is angry, it will respond in a way that encourages a calm response. If the caller is feeling anxious, it will respond in a way that provides reassurance. By adjusting the way the response is expressed according to the caller's emotions, it becomes possible to provide a more appropriate response.

[0117] The customer service department can estimate the customer's emotions and adjust its complaint handling methods based on those estimates. For example, if a customer is angry, it can provide a calm and composed complaint handling method. If a customer is feeling anxious, it can provide a reassuring method. If a customer is feeling stressed, it can provide a relaxing method. By adjusting complaint handling methods according to the customer's emotions, more appropriate complaint handling becomes possible.

[0118] The reception desk can analyze a caller's past consultation history and select the most suitable reception method. For example, it can automatically display relevant questions based on the topics the caller has frequently consulted about in the past. It can also prioritize suggesting input methods (voice, text, etc.) the caller has used in the past. Furthermore, it can predict and suggest input methods that the caller will use at specific times based on their past consultation history. In this way, by analyzing past consultation history, the reception desk can provide the caller with the most suitable reception method.

[0119] The review department can apply different review algorithms depending on the category of the consultation. For example, a specific review algorithm is applied to consultations regarding harassment. Another review algorithm is applied to consultations regarding misconduct. For other categories, an appropriate review algorithm is selected and applied. This allows for the provision of more appropriate response policies by applying a review algorithm that matches the category of the consultation.

[0120] The notification unit can adjust the level of detail in notifications based on the importance of the consultation content. For example, a detailed notification will be sent for highly important consultations, while a simplified notification will be sent for less important consultations. The level of detail in notifications is adjusted in stages according to the importance of the consultation content. This allows for more appropriate notifications by adjusting the level of detail according to the importance of the consultation content.

[0121] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can select the optimal learning algorithm based on past learning data and perform learning. It can extract effective learning patterns from past learning data and optimize the learning algorithm. It can analyze past learning data and adjust the parameters of the learning algorithm to optimize it. In this way, by referring to past learning data, the learning algorithm can be optimized and the accuracy of learning can be improved.

[0122] The response system can prioritize responses based on when the inquiry was submitted. For example, if the inquiry is urgent, a response will be given quickly. If the inquiry is not urgent, a response will be given with the usual priority. The priority of responses will be adjusted in stages according to when the inquiry was submitted. This allows for responses to be given at a more appropriate time by determining the priority of responses according to when the inquiry was submitted.

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

[0124] Step 1: The reception desk receives information from the client. For example, information can be received from the client in the metaverse space. The metaverse space is a virtual space constructed using virtual reality technology, where the client can conduct consultations through an avatar. Step 2: The review department considers a course of action based on the information received by the reception department, in accordance with internal regulations and laws. For example, it can learn about internal regulations and laws and check for any violations. The review department can use AI to learn about internal regulations and laws and consider an appropriate course of action. Step 3: The notification unit, based on the review by the investigation unit, will inform the relevant internal personnel if a serious fraud has occurred. For example, notifications can be sent via email or app notifications. The notification unit can use AI to generate notification content and send it to the appropriate personnel.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include 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.

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

[0128] Each of the multiple elements described above, including the reception unit, review unit, notification unit, learning unit, response unit, and complaint handling unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives information from the consultant in the metaverse space. The review unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and considers a response policy in accordance with internal regulations and laws. The notification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and notifies the relevant personnel in the company if a serious misconduct has occurred. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns internal regulations and laws. The response unit is implemented by, for example, the control unit 46A of the smart device 14 and responds to the consultant using natural language processing technology. The complaint handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and responds to customer complaints. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

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

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

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

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

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

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

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the reception unit, review unit, notification unit, learning unit, response unit, and complaint handling unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives information from the consultant in the metaverse space. The review unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and considers a response policy in accordance with company regulations and laws. The notification unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and notifies the relevant personnel in the company if a serious misconduct has occurred. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and learns company regulations and laws. The response unit is implemented, for example, by the control unit 46A of the smart glasses 214 and responds to the consultant using natural language processing technology. The complaint handling unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and responds to customer complaints. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

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

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

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

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

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

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

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

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

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the reception unit, review unit, notification unit, learning unit, response unit, and complaint handling unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives information from the caller in the metaverse space. The review unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and considers a response policy in accordance with company regulations and laws. The notification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and notifies the relevant personnel in the company if a serious misconduct has occurred. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns company regulations and laws. The response unit is implemented by, for example, the control unit 46A of the headset terminal 314 and responds to the caller using natural language processing technology. The complaint handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and responds to customer complaints. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

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

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

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

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

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

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

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the reception unit, review unit, notification unit, learning unit, response unit, and complaint handling unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives information from the consultant in the metaverse space. The review unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and considers a response policy in accordance with company regulations and laws. The notification unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and notifies the relevant personnel in the company if a serious misconduct has occurred. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns company regulations and laws. The response unit is implemented by, for example, the control unit 46A of the robot 414 and responds to the consultant using natural language processing technology. The complaint handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and responds to customer complaints. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

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

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

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

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

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

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

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

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

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

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

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

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

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

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

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

[0196] (Note 1) The reception department receives information from those seeking advice, Based on the information received by the aforementioned reception department, the review department considers a response plan in accordance with internal regulations and laws, The system includes a notification unit that, if a serious misconduct has occurred as a result of the review by the aforementioned review unit, notifies the relevant personnel within the company. A system characterized by the following features. (Note 2) The AI ​​has a learning unit that learns company regulations and laws. The system described in Appendix 1, characterized by the features described herein. (Note 3) Equipped with an AI-powered answering function to respond to inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 4) The company has a customer complaints department where AI handles customer complaints. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is Information from clients is received in the metaverse space. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned examination unit is We will consider our response policy based on internal regulations and applicable laws. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is We estimate the client's emotions and adjust the method of receiving information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze the client's past consultation history and select the most suitable method of acceptance. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is Information is filtered based on the client's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the client's emotions and prioritizes the information to be received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is We prioritize receiving information that is highly relevant to the caller, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is We analyze the social media activity of the person seeking advice and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned examination unit is We estimate the client's emotions and adjust the approach to consider based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned examination unit is We adjust the level of detail in our response policies based on the importance of internal regulations and laws. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned examination unit is Apply different analysis algorithms depending on the category of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned examination unit is We estimate the client's emotions and determine the priority of the response plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned examination unit is Prioritizing response strategies based on when the consultation details were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned examination unit is The order of response strategies will be adjusted based on the relevance of the consultation topics. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned notification unit, The system estimates the caller's emotions and adjusts the notification method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned notification unit, When sending a notification, the level of detail will be adjusted based on the importance of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned notification unit, When sending notifications, different notification algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned notification unit, The system estimates the caller's emotions and determines the priority of notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned notification unit, When notifying, the priority of notifications will be determined based on when the consultation details were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned notification unit, When sending notifications, the order of notifications will be adjusted based on the relevance of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, The system estimates the client's emotions and selects training data based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned learning unit, The system estimates the client's emotions and adjusts the frequency of learning based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned learning unit, During the learning process, the learning data is weighted based on when the consultation content was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned response section is, We estimate the client's emotions and adjust the way we express our response based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned response section is, When responding, adjust the level of detail in your response based on the importance of the issue. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned response section is, When responding, different response algorithms are applied depending on the category of the inquiry. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned response section is, We estimate the client's emotions and determine the priority of our responses based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned response section is, When responding, we will prioritize responses based on when the inquiry was submitted. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned response section is, When responding, adjust the order of your answers based on the relevance of the topics you are asking about. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned claims handling unit is We estimate the customer's emotions and adjust our complaint handling methods based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned claims handling unit is When handling complaints, adjust the level of detail in the response based on the severity of the complaint. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned claims handling unit is Apply different response algorithms depending on the category of the claim. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned claims handling unit is Estimate customer emotions and determine complaint handling priorities based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned claims handling unit is When handling complaints, prioritize responses based on when the complaint was submitted. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned claims handling unit is When handling complaints, adjust the order of responses based on the relevance of the complaint content. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

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

Claims

1. The reception department receives information from those seeking advice, Based on the information received by the aforementioned reception department, the review department considers a response plan in accordance with internal regulations and laws, The system includes a notification unit that, if a serious misconduct has occurred as a result of the review by the aforementioned review unit, notifies the relevant personnel within the company. A system characterized by the following features.

2. The company has a learning unit where AI learns company regulations and laws. The system according to feature 1.

3. It features an AI-powered response section that answers questions from users. The system according to feature 1.

4. The company has a customer complaints department where AI handles customer complaints. The system according to feature 1.

5. The aforementioned reception unit is Information from clients is received in the metaverse space. The system according to feature 1.

6. The aforementioned examination unit is We will consider our response policy based on internal regulations and applicable laws. The system according to feature 1.

7. The aforementioned reception unit is We estimate the client's emotions and adjust the method of receiving information based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze the client's past consultation history and select the most suitable method of acceptance. The system according to feature 1.

9. The aforementioned reception unit is Information is filtered based on the client's current situation and areas of interest. The system according to feature 1.

Images