system

Abstract

The system according to this embodiment aims to respond to customer inquiries quickly and efficiently. [Solution] The system according to this embodiment comprises an understanding unit, a learning unit, a dialogue unit, an escalation unit, and a response unit. The understanding unit understands the content of customer inquiries. The learning unit improves the quality of responses based on the content of inquiries understood by the understanding unit. The dialogue unit interacts with multiple customers simultaneously based on the improved quality of responses provided by the learning unit. The escalation unit transfers inquiries to human operators as needed based on the content of the dialogues conducted by the dialogue unit. The response unit provides 24 / 7 support based on inquiries transferred by the escalation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] [[ID=,35]]In the conventional technology, responses to customer inquiries are not made quickly and efficiently, and there is a risk of long waiting times.

[0005] The system according to the embodiment aims to quickly and efficiently respond to customer inquiries.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an understanding unit, a learning unit, a dialogue unit, an escalation unit, and a response unit. The understanding unit understands the content of customer inquiries. The learning unit improves the quality of responses based on the inquiry content understood by the understanding unit. The dialogue unit interacts with multiple customers simultaneously based on the improved quality of responses by the learning unit. The escalation unit transfers inquiries to human operators as needed based on the content of the dialogues conducted by the dialogue unit. The response unit provides 24 / 7 support based on inquiries transferred by the escalation unit. [Effects of the Invention]

[0007] The system according to this embodiment can respond to customer inquiries quickly and efficiently. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple 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 reception 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 reception 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 interactive customer center agent according to an embodiment of the present invention is a system that utilizes advanced speech recognition technology of generative AI. This system has real-time response and high comprehension capabilities, enabling it to resolve customer inquiries immediately and reduce waiting times. Specifically, it uses natural language processing technology to understand the content of customer inquiries, has learning capabilities to improve the quality of its responses, and can converse with multiple customers simultaneously. It also has a seamless escalation process and is available 24 hours a day, 365 days a year. For example, the interactive customer center agent uses natural language processing technology based on generative AI to highly understand the content of customer inquiries. This allows it to accurately grasp what kind of questions the customer is asking and provide appropriate answers. For example, if a customer asks, "How do I return a product?", the agent will immediately explain the details of the return procedure. Next, the agent has learning capabilities and improves the quality of its responses based on past conversation data. This allows for more accurate and faster responses over time. For example, the agent will automatically provide the best answer to frequently asked questions. Furthermore, the agent can converse with multiple customers simultaneously. This allows for quick responses without causing waiting times when customers make inquiries. For example, even if multiple customers make inquiries simultaneously, the agent will handle each customer individually. Furthermore, the agent has a seamless escalation process and can transfer inquiries to human operators as needed. This allows for quick responses to complex issues that agents cannot handle. For instance, in cases of technical problems or those requiring special assistance, the agent will automatically transfer the inquiry to an operator. These agents are available 24 / 7, 365 days a year, ensuring constant customer support. This improves customer satisfaction and enhances the company's service quality. For example, if a customer makes an inquiry late at night or on a holiday, an agent can respond immediately. In the future, support will be expanded to other languages, enabling global support.This enables consistent support for customers worldwide. For example, agents can assist customers who speak languages ​​other than English. In this way, conversational customer center agents powered by generative AI are revolutionizing customer support, improving customer satisfaction and streamlining business operations. As a result, conversational customer center agents can efficiently understand customer inquiries, improve the quality of responses, interact with multiple customers simultaneously, escalate issues as needed, and provide 24 / 7 / 365 support.

[0029] The interactive customer center agent according to this embodiment comprises an understanding unit, a learning unit, a dialogue unit, an escalation unit, and a response unit. The understanding unit understands the content of customer inquiries. The understanding unit uses, for example, natural language processing technology to gain a high level of understanding of customer inquiries. For example, the understanding unit uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to accurately grasp the content of customer inquiries. The learning unit improves the quality of responses based on the content of inquiries understood by the understanding unit. The learning unit improves the quality of responses based on, for example, past dialogue data. For example, the learning unit analyzes past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. The dialogue unit interacts with multiple customers simultaneously based on the improved quality of responses by the learning unit. The dialogue unit interacts with multiple customers simultaneously using technologies such as chatbots and multithreading. For example, even if multiple customers make inquiries at the same time, the dialogue unit responds to each customer individually. The escalation unit transfers inquiries to human operators as needed based on the content of the dialogue conducted by the dialogue unit. The escalation department, for example, uses technologies such as real-time data transfer and collaborative systems to realize a seamless escalation process. For example, the escalation department transfers inquiries to operators when there are technical problems or when special attention is required. The response department provides 24 / 7 support based on inquiries transferred by the escalation department. The response department provides 24 / 7 support using technologies such as shift systems and automated systems. For example, the response department responds to customer inquiries even late at night or on holidays. As a result, the interactive customer center agent according to this embodiment can efficiently understand customer inquiries, improve the quality of support, interact with multiple customers simultaneously, escalate as needed, and provide 24 / 7 support.

[0030] The understanding unit understands the content of customer inquiries. For example, the understanding unit uses natural language processing technology to understand customer inquiries at a high level. Specifically, the understanding unit uses morphological analysis to break down the customer's inquiry sentence into individual words, grasps the sentence structure through grammatical analysis, and understands the meaning of the entire sentence through semantic analysis. This allows the understanding unit to accurately grasp the intent even if the customer's inquiry is ambiguous or contains complex expressions. Furthermore, the understanding unit achieves a higher level of accuracy by referring to the customer's past inquiry history and past response data for similar inquiries. For example, if a customer inquires, "I want to cancel my order," the understanding unit extracts the keywords "order" and "cancel," and refers to data on past cancellation procedures to understand the specific procedure. In addition, the understanding unit can analyze the customer's emotions and tone to determine how urgent the customer feels and what kind of response they expect. This makes it possible to quickly provide an appropriate response that meets the customer's needs.

[0031] The learning unit improves the quality of responses based on the inquiries understood by the understanding unit. For example, the learning unit improves the quality of responses based on past dialogue data. Specifically, the learning unit uses machine learning algorithms to analyze past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. For example, in response to a customer inquiry such as "How do I return a product?", the learning unit generates the most effective answer based on past dialogue data. The learning unit also collects customer feedback and continuously improves the accuracy of answers and the quality of responses. For example, if a customer rates a provided answer as "helpful," the learning unit prioritizes learning that answer pattern and incorporates it into future responses. Furthermore, the learning unit can automatically learn information about new products and services and provide responses based on the latest information. As a result, the learning unit can always provide high-quality responses based on the latest information and improve customer satisfaction.

[0032] The dialogue unit interacts with multiple customers simultaneously, based on the improved quality of responses provided by the learning unit. The dialogue unit uses technologies such as chatbots and multi-threading to interact with multiple customers simultaneously. Specifically, the dialogue unit receives customer inquiries in real time and quickly provides the optimal answer learned by the learning unit. For example, if multiple customers simultaneously inquire about product availability, the dialogue unit provides individual inventory information to each customer. Furthermore, the dialogue unit can automatically select the appropriate response based on the customer's inquiry, providing a quick and accurate answer. In addition, if a customer's inquiry is complex or requires special handling, the dialogue unit can transfer the inquiry to the escalation unit. This allows the dialogue unit to efficiently and effectively handle multiple customers, improving customer satisfaction.

[0033] The escalation department, based on the content of the conversation conducted by the dialogue department, transfers inquiries to human operators as needed. The escalation department achieves a seamless escalation process using technologies such as real-time data transfer and integrated systems. Specifically, the escalation department transfers inquiries to operators when there are technical problems that the dialogue department cannot handle or when special handling is required. For example, if a customer inquires, "I would like a detailed explanation about a product defect," the escalation department will transfer the customer's inquiry content and past conversation history collected by the dialogue department to the operator in real time, enabling the operator to respond quickly. The escalation department also provides operators with necessary information in real time during the response, improving the quality of service. As a result, the escalation department can respond to customer inquiries quickly and appropriately, improving customer satisfaction.

[0034] The customer support department provides 24 / 7 support based on inquiries handed over by the escalation department. The department utilizes technologies such as shift systems and automated systems to maintain 24 / 7 support. Specifically, the department maintains a shift system to ensure operators are always on standby to handle customer inquiries, even late at night and on holidays. Furthermore, the department reduces the burden on operators and achieves efficient service by implementing automated systems. For example, the department implements a system that automatically categorizes customer inquiries and assigns them to the appropriate operator. This allows the department to respond to customer inquiries quickly and accurately, improving customer satisfaction. Additionally, the department centrally manages customer inquiry content and response history, enabling it to provide optimal support based on past response data. This allows the department to provide high-quality support tailored to customer needs, further improving customer satisfaction.

[0035] The understanding unit can highly understand customer inquiries using natural language processing technology. For example, the understanding unit accurately grasps customer inquiries using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For instance, the understanding unit uses morphological analysis to break down customer inquiries into individual words, grammatical analysis to analyze sentence structure, and semantic analysis to understand sentence meaning. This allows for a high level of understanding of customer inquiries through the use of natural language processing technology. Some or all of the above-described processes in the understanding unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the understanding unit can input customer inquiries into a generative AI, which can then analyze and understand the inquiries.

[0036] The learning unit can improve the quality of its responses based on past dialogue data. For example, the learning unit analyzes past dialogue data and prioritizes learning data that provides optimal answers to frequently asked questions. For example, the learning unit collects past dialogue data as text data or audio data and optimizes its learning algorithm based on it. By improving the quality of responses based on past dialogue data, it becomes possible to provide more accurate and faster responses over time. Some or all of the above processing in the learning unit may be performed using generative AI, or it may be performed without generative AI. For example, the learning unit can input past dialogue data into a generative AI, which can then analyze the data and optimize its learning algorithm.

[0037] The dialogue unit can interact with multiple customers simultaneously. The dialogue unit interacts with multiple customers simultaneously using technologies such as chatbots and multithreading. For example, even if multiple customers make inquiries at the same time, the dialogue unit will respond to each customer individually. This allows for quick responses without any waiting time when customers make inquiries by interacting with multiple customers simultaneously. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the content of inquiries from multiple customers into a generative AI, and the generative AI can respond to each inquiry individually.

[0038] The escalation unit can have a seamless process for transferring inquiries to human operators as needed. The escalation unit can achieve a seamless escalation process using technologies such as real-time data transfer and collaborative systems. For example, the escalation unit will transfer inquiries to operators when there are technical problems or when special handling is required. This allows for a seamless process of transferring inquiries to human operators as needed, enabling a rapid response even to complex problems that agents cannot handle. Some or all of the above-described processes in the escalation unit may be performed using generative AI, or not. For example, the escalation unit can input the inquiry content into a generative AI, which can then determine whether or not to transfer the inquiry to an operator.

[0039] The support department is available 24 hours a day, 365 days a year. The support department operates 24 hours a day, 365 days a year, using technologies such as shift systems and automated systems. For example, the support department responds to customer inquiries even late at night or on holidays. This ensures that customer inquiries are always addressed, as the support department is available 24 hours a day, 365 days a year. Some or all of the above-described processes in the support department may be performed using a generation AI, or they may be performed without a generation AI. For example, the support department can input the inquiry content into a generation AI, which can then propose the optimal method for 24 / 7 support.

[0040] The understanding unit can analyze a customer's past inquiry history and select the optimal understanding method. For example, if a customer has asked the same question in the past, the understanding unit can refer to that history and provide a quick answer. For example, if a customer has shown interest in a particular topic in the past, the understanding unit will prioritize understanding information related to that topic. For example, if a customer has asked multiple different questions in the past, the understanding unit can analyze the patterns and select the optimal understanding method. This allows the understanding unit to select the optimal understanding method and provide a quick answer by analyzing the customer's past inquiry history. Some or all of the above processing in the understanding unit may be performed using or without a generative AI. For example, the understanding unit can input the customer's past inquiry history into a generative AI, which can then select the optimal understanding method.

[0041] The understanding unit can filter the content of inquiries based on the customer's current situation and areas of interest. For example, if the customer describes their current situation, the understanding unit prioritizes understanding information related to that situation. For example, if the customer asks a question about a specific area of ​​interest, the understanding unit filters and provides information related to that area. For example, if the customer asks multiple questions, the understanding unit prioritizes understanding the most relevant question based on the customer's current situation and areas of interest. This allows the understanding unit to provide more relevant information by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the understanding unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the understanding unit can input data on the customer's current situation and areas of interest into a generative AI, which can then perform the filtering.

[0042] The understanding unit can prioritize understanding highly relevant content by considering the customer's geographical location when understanding the content of an inquiry. For example, if the customer is in a specific region, the understanding unit will prioritize understanding information related to that region. For example, if the customer is traveling, the understanding unit will prioritize understanding information related to their travel destination. For example, if the customer is in a specific city, the understanding unit will prioritize understanding information related to that city. By prioritizing the understanding of highly relevant content while considering the customer's geographical location, the understanding unit can provide more appropriate information. Some or all of the above processing in the understanding unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the understanding unit can input the customer's geographical location information into a generative AI, which can then prioritize understanding highly relevant content.

[0043] The understanding unit can analyze the customer's social media activity and understand relevant content when understanding an inquiry. For example, if the customer is talking about a specific topic on social media, the understanding unit will prioritize understanding information related to that topic. For example, if the customer is mentioning a specific issue on social media, the understanding unit will prioritize understanding information related to that issue. For example, if the customer is talking about a specific product on social media, the understanding unit will prioritize understanding information related to that product. This allows the understanding unit to provide more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the understanding unit may be performed using generative AI, or not. For example, the understanding unit can input data on the customer's social media activity into a generative AI, which can then understand the relevant content.

[0044] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal algorithm. For example, the learning unit can adjust the algorithm parameters based on past learning data. For example, the learning unit can optimize the learning process by referring to past learning data. This improves the accuracy of learning by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input past learning data into a generative AI, and the generative AI can optimize the algorithm.

[0045] The learning unit can prioritize learning data that provides optimal answers to frequently asked questions during the learning process. For example, the learning unit can analyze frequently asked questions and prioritize learning the answer data. For example, the learning unit can prioritize learning relevant data to provide optimal answers to frequently asked questions. For example, the learning unit can prioritize learning relevant data to improve the quality of answers to frequently asked questions. This improves the quality of responses by prioritizing the learning of data that provides optimal answers to frequently asked questions. Some or all of the above processing in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input data on frequently asked questions into a generative AI, which can then learn data to provide optimal answers.

[0046] The learning unit can weight the training data based on the submission date of inquiries during training. For example, the learning unit can weight the training data based on recent inquiries. For example, the learning unit can weight the training data based on past inquiries. For example, the learning unit can weight the training data based on inquiries received during a specific period. By weighting the training data based on the submission date of inquiries, more appropriate data can be learned. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input data on the submission date of inquiries into a generative AI, and the generative AI can weight the training data.

[0047] The learning unit can select training data while considering customer attribute information during training. For example, the learning unit may select training data based on the customer's age. For example, the learning unit may select training data based on the customer's gender. For example, the learning unit may select training data based on the customer's region. By selecting training data while considering customer attribute information, more appropriate data can be learned. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input customer attribute information into a generative AI, and the generative AI can select training data.

[0048] The dialogue unit can adjust the level of detail in the conversation based on the customer's importance. For example, the dialogue unit provides detailed information to important customers, standard information to general customers, and concise information to low-priority customers. By adjusting the level of detail in the conversation based on the customer's importance, more appropriate information can be provided. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input customer importance data into a generative AI, which can then adjust the level of detail in the conversation.

[0049] The dialogue unit can apply different dialogue algorithms depending on the customer's category during a conversation. For example, the dialogue unit might apply an algorithm that provides basic information to new customers, an algorithm that provides detailed information to repeat customers, and an algorithm that provides special information to VIP customers. By applying different dialogue algorithms depending on the customer's category, more appropriate conversations become possible. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input customer category data into a generative AI, and the generative AI can apply different dialogue algorithms.

[0050] The dialogue unit can determine the priority of a conversation based on the customer's inquiry. For example, it will prioritize urgent inquiries. For example, it will prioritize general inquiries. For example, it will postpone inquiries. By determining the priority of conversations based on the customer's inquiry, it is possible to conduct conversations in a more appropriate order. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input customer inquiry data into a generative AI, and the generative AI can determine the priority of the conversation.

[0051] The dialogue unit can adjust the order of conversations based on customer relevance during a conversation. For example, the dialogue unit will respond to important customers first. For example, the dialogue unit will respond to general customers in the normal order. For example, the dialogue unit will respond to lower-priority customers later. By adjusting the order of conversations based on customer relevance, conversations can be conducted in a more appropriate order. Some or all of the above processing in the dialogue unit may be performed using generative AI, or it may be performed without generative AI. For example, the dialogue unit can input customer relevance data into the generative AI, and the generative AI can adjust the order of conversations.

[0052] The escalation unit can improve the accuracy of escalation by considering the relationships between customers during the escalation process. For example, if a customer is related to other customers, the escalation unit will consider those relationships when escalating. For example, if a customer belongs to a specific group, the escalation unit will consider the information of that group when escalating. For example, if a customer is involved in a specific project, the escalation unit will consider the information of that project when escalating. By improving the accuracy of escalation by considering the relationships between customers, more appropriate escalation becomes possible. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the relationships between customers into a generative AI, which can then improve the accuracy of escalation.

[0053] The escalation unit can perform escalations while considering customer attribute information. For example, the escalation unit may perform escalations based on the customer's age. For example, the escalation unit may perform escalations based on the customer's gender. For example, the escalation unit may perform escalations based on the customer's region. By performing escalations while considering customer attribute information, more appropriate escalations become possible. Some or all of the above processing in the escalation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the escalation unit can input customer attribute information into a generation AI, and the generation AI can perform the escalation.

[0054] The escalation unit can perform escalations while considering the geographical distribution of customers. For example, if a customer is in a specific region, the escalation unit will perform escalations while considering information related to that region. For example, if a customer is traveling, the escalation unit will perform escalations while considering information related to the travel destination. For example, if a customer is in a specific city, the escalation unit will perform escalations while considering information related to that city. This makes it possible to perform more appropriate escalations by considering the geographical distribution of customers. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the geographical distribution of customers into a generative AI, and the generative AI can perform escalations.

[0055] The escalation unit can improve the accuracy of escalations by referring to the customer's relevant literature during the escalation process. For example, if the customer refers to a specific document, the escalation unit will take that document into consideration when escalating. For example, if the customer is conducting a specific research project, the escalation unit will take that research into consideration when escalating. For example, if the customer is involved in a specific project, the escalation unit will take that project's literature into consideration when escalating. By improving the accuracy of escalations by referring to the customer's relevant literature, more appropriate escalations become possible. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the customer's relevant literature into a generative AI, which can then improve the accuracy of the escalation.

[0056] The response unit can select the optimal response method by referring to the customer's past inquiry history when responding to an inquiry. For example, if the customer has asked the same question in the past, the response unit can refer to that history and provide a quick answer. For example, if the customer has shown interest in a particular topic in the past, the response unit can prioritize providing information related to that topic. For example, if the customer has asked multiple different questions in the past, the response unit can analyze the pattern and select the optimal response method. This enables faster and more appropriate responses by referring to the customer's past inquiry history and selecting the optimal response method. Some or all of the above processing in the response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the response unit can input data from the customer's past inquiry history into a generative AI, which can then select the optimal response method.

[0057] The response unit can customize its response methods based on the customer's current situation when responding. For example, if the customer describes their current situation, the response unit will prioritize providing information relevant to that situation. For example, if the customer asks about a specific area of ​​interest, the response unit will provide information relevant to that area. For example, if the customer asks multiple questions, the response unit will prioritize responding to the most relevant question based on the customer's current situation. This allows for a more appropriate response by customizing the response methods based on the customer's current situation. Some or all of the above processing in the response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the response unit can input data on the customer's current situation into a generative AI, which can then customize the response methods.

[0058] The response unit can select the optimal response method when responding to a customer, taking into account the customer's geographical location information. For example, if the customer is in a specific region, the response unit will prioritize providing information related to that region. For example, if the customer is traveling, the response unit will prioritize providing information related to their travel destination. For example, if the customer is in a specific city, the response unit will prioritize providing information related to that city. By selecting the optimal response method considering the customer's geographical location information, more appropriate information can be provided. Some or all of the above processing in the response unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the response unit can input the customer's geographical location data into a generation AI, which can then select the optimal response method.

[0059] The response unit can analyze the customer's social media activity and propose a course of action when responding. For example, if the customer is talking about a specific topic on social media, the response unit will prioritize providing information related to that topic. For example, if the customer is mentioning a specific issue on social media, the response unit will prioritize providing information related to that issue. For example, if the customer is talking about a specific product on social media, the response unit will prioritize providing information related to that product. This allows the response unit to provide more appropriate information by analyzing the customer's social media activity and proposing a course of action. Some or all of the above processing in the response unit may be performed using or without a generative AI. For example, the response unit can input data on the customer's social media activity into a generative AI, which can then propose a course of action.

[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] Interactive customer center agents can analyze a customer's past purchase history and provide optimal suggestions. For example, if a customer has previously purchased a specific product, they can offer information on new products or upgrades related to that product. If a customer has frequently purchased products in a specific category in the past, they can offer special offers or discounts related to that category. If a customer has a preference for a particular brand in the past, they can suggest new or limited-edition products from that brand. This allows for improved customer satisfaction by providing optimal suggestions based on the customer's past purchase history. Purchase history analysis can also be performed using generative AI; for example, an agent can input customer purchase history data into a generative AI, which can then generate optimal suggestions.

[0062] Interactive customer center agents can customize the content of their conversations based on the customer's current situation. For example, if a customer is traveling, they can provide information and services related to their destination. If a customer is attending a specific event, they can provide information and support related to that event. If a customer is working on a specific project, they can provide information and resources related to that project. By customizing the conversation based on the customer's current situation, more relevant information can be provided, improving customer satisfaction. Situational awareness may also be achieved using generative AI; for example, the agent can input data on the customer's current situation into the generative AI, which can then customize the optimal conversation content.

[0063] Interactive customer center agents can analyze a customer's past inquiry history and select the most appropriate response. For example, if a customer has asked the same question before, they can refer to that history to provide a quick answer. If a customer has shown interest in a particular topic in the past, they can prioritize providing information related to that topic. If a customer has asked multiple different questions in the past, the system analyzes the patterns to select the most appropriate response. This allows for faster and more appropriate responses by selecting the best response based on the customer's past inquiry history. The analysis of inquiry history may also be performed using generative AI; for example, an agent can input customer inquiry history data into a generative AI, which can then select the most appropriate response.

[0064] Interactive customer center agents can select the most appropriate response method by considering the customer's geographical location. For example, if a customer is in a specific region, they can prioritize providing information relevant to that region. If a customer is traveling, they can prioritize providing information relevant to their travel destination. If a customer is in a specific city, they can prioritize providing information relevant to that city. By selecting the most appropriate response method based on the customer's geographical location, more relevant information can be provided. Consideration of geographical location can also be performed using generative AI; for example, the agent can input the customer's geographical location data into the generative AI, which can then select the most appropriate response method.

[0065] Interactive customer center agents can analyze customers' social media activity and provide relevant information. For example, if a customer is discussing a specific topic on social media, they can prioritize providing information related to that topic. If a customer is mentioning a specific issue on social media, they can prioritize providing information related to that issue. If a customer is discussing a specific product on social media, they can prioritize providing information related to that product. By analyzing customers' social media activity and providing relevant information, it is possible to provide more appropriate information and improve customer satisfaction. Social media activity analysis can also be performed using generative AI; for example, an agent can input customer social media activity data into a generative AI, which can then provide relevant information.

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

[0067] Step 1: The understanding unit understands the customer's inquiry. The understanding unit uses, for example, natural language processing technology to gain a high level of understanding of the customer's inquiry. Specifically, it uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to accurately grasp the customer's inquiry. Step 2: The learning unit improves the quality of responses based on the inquiries understood by the understanding unit. For example, the learning unit improves the quality of responses based on past dialogue data. Specifically, it analyzes past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. Step 3: The dialogue unit interacts with multiple customers simultaneously, based on the improved quality of responses achieved by the learning unit. The dialogue unit interacts with multiple customers simultaneously, for example, using technologies such as chatbots and multithreading. Specifically, even if multiple customers make inquiries at the same time, it responds to each customer individually. Step 4: The escalation unit, based on the content of the conversation conducted by the dialogue unit, transfers the inquiry to a human operator as needed. The escalation unit achieves a seamless escalation process using technologies such as real-time data transfer and integrated systems. Specifically, it transfers the inquiry to an operator when there are technical issues or when special handling is required. Step 5: The support department will provide 24 / 7 support based on inquiries handed over by the escalation department. The support department will provide 24 / 7 support using technologies such as shift work and automated systems. Specifically, they will respond to customer inquiries even late at night and on holidays.

[0068] (Example of form 2) The interactive customer center agent according to an embodiment of the present invention is a system that utilizes advanced speech recognition technology of generative AI. This system has real-time response and high comprehension capabilities, enabling it to resolve customer inquiries immediately and reduce waiting times. Specifically, it uses natural language processing technology to understand the content of customer inquiries, has learning capabilities to improve the quality of its responses, and can converse with multiple customers simultaneously. It also has a seamless escalation process and is available 24 hours a day, 365 days a year. For example, the interactive customer center agent uses natural language processing technology based on generative AI to highly understand the content of customer inquiries. This allows it to accurately grasp what kind of questions the customer is asking and provide appropriate answers. For example, if a customer asks, "How do I return a product?", the agent will immediately explain the details of the return procedure. Next, the agent has learning capabilities and improves the quality of its responses based on past conversation data. This allows for more accurate and faster responses over time. For example, the agent will automatically provide the best answer to frequently asked questions. Furthermore, the agent can converse with multiple customers simultaneously. This allows for quick responses without causing waiting times when customers make inquiries. For example, even if multiple customers make inquiries simultaneously, the agent will handle each customer individually. Furthermore, the agent has a seamless escalation process and can transfer inquiries to human operators as needed. This allows for quick responses to complex issues that agents cannot handle. For instance, in cases of technical problems or those requiring special assistance, the agent will automatically transfer the inquiry to an operator. These agents are available 24 / 7, 365 days a year, ensuring constant customer support. This improves customer satisfaction and enhances the company's service quality. For example, if a customer makes an inquiry late at night or on a holiday, an agent can respond immediately. In the future, support will be expanded to other languages, enabling global support.This enables consistent support for customers worldwide. For example, agents can assist customers who speak languages ​​other than English. In this way, conversational customer center agents powered by generative AI are revolutionizing customer support, improving customer satisfaction and streamlining business operations. As a result, conversational customer center agents can efficiently understand customer inquiries, improve the quality of responses, interact with multiple customers simultaneously, escalate issues as needed, and provide 24 / 7 / 365 support.

[0069] The interactive customer center agent according to this embodiment comprises an understanding unit, a learning unit, a dialogue unit, an escalation unit, and a response unit. The understanding unit understands the content of customer inquiries. The understanding unit uses, for example, natural language processing technology to gain a high level of understanding of customer inquiries. For example, the understanding unit uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to accurately grasp the content of customer inquiries. The learning unit improves the quality of responses based on the content of inquiries understood by the understanding unit. The learning unit improves the quality of responses based on, for example, past dialogue data. For example, the learning unit analyzes past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. The dialogue unit interacts with multiple customers simultaneously based on the improved quality of responses by the learning unit. The dialogue unit interacts with multiple customers simultaneously using technologies such as chatbots and multithreading. For example, even if multiple customers make inquiries at the same time, the dialogue unit responds to each customer individually. The escalation unit transfers inquiries to human operators as needed based on the content of the dialogue conducted by the dialogue unit. The escalation department, for example, uses technologies such as real-time data transfer and collaborative systems to realize a seamless escalation process. For example, the escalation department transfers inquiries to operators when there are technical problems or when special attention is required. The response department provides 24 / 7 support based on inquiries transferred by the escalation department. The response department provides 24 / 7 support using technologies such as shift systems and automated systems. For example, the response department responds to customer inquiries even late at night or on holidays. As a result, the interactive customer center agent according to this embodiment can efficiently understand customer inquiries, improve the quality of support, interact with multiple customers simultaneously, escalate as needed, and provide 24 / 7 support.

[0070] The understanding unit understands the content of customer inquiries. For example, the understanding unit uses natural language processing technology to understand customer inquiries at a high level. Specifically, the understanding unit uses morphological analysis to break down the customer's inquiry sentence into individual words, grasps the sentence structure through grammatical analysis, and understands the meaning of the entire sentence through semantic analysis. This allows the understanding unit to accurately grasp the intent even if the customer's inquiry is ambiguous or contains complex expressions. Furthermore, the understanding unit achieves a higher level of accuracy by referring to the customer's past inquiry history and past response data for similar inquiries. For example, if a customer inquires, "I want to cancel my order," the understanding unit extracts the keywords "order" and "cancel," and refers to data on past cancellation procedures to understand the specific procedure. In addition, the understanding unit can analyze the customer's emotions and tone to determine how urgent the customer feels and what kind of response they expect. This makes it possible to quickly provide an appropriate response that meets the customer's needs.

[0071] The learning unit improves the quality of responses based on the inquiries understood by the understanding unit. For example, the learning unit improves the quality of responses based on past dialogue data. Specifically, the learning unit uses machine learning algorithms to analyze past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. For example, in response to a customer inquiry such as "How do I return a product?", the learning unit generates the most effective answer based on past dialogue data. The learning unit also collects customer feedback and continuously improves the accuracy of answers and the quality of responses. For example, if a customer rates a provided answer as "helpful," the learning unit prioritizes learning that answer pattern and incorporates it into future responses. Furthermore, the learning unit can automatically learn information about new products and services and provide responses based on the latest information. As a result, the learning unit can always provide high-quality responses based on the latest information and improve customer satisfaction.

[0072] The dialogue unit interacts with multiple customers simultaneously, based on the improved quality of responses provided by the learning unit. The dialogue unit uses technologies such as chatbots and multi-threading to interact with multiple customers simultaneously. Specifically, the dialogue unit receives customer inquiries in real time and quickly provides the optimal answer learned by the learning unit. For example, if multiple customers simultaneously inquire about product availability, the dialogue unit provides individual inventory information to each customer. Furthermore, the dialogue unit can automatically select the appropriate response based on the customer's inquiry, providing a quick and accurate answer. In addition, if a customer's inquiry is complex or requires special handling, the dialogue unit can transfer the inquiry to the escalation unit. This allows the dialogue unit to efficiently and effectively handle multiple customers, improving customer satisfaction.

[0073] The escalation department, based on the content of the conversation conducted by the dialogue department, transfers inquiries to human operators as needed. The escalation department achieves a seamless escalation process using technologies such as real-time data transfer and integrated systems. Specifically, the escalation department transfers inquiries to operators when there are technical problems that the dialogue department cannot handle or when special handling is required. For example, if a customer inquires, "I would like a detailed explanation about a product defect," the escalation department will transfer the customer's inquiry content and past conversation history collected by the dialogue department to the operator in real time, enabling the operator to respond quickly. The escalation department also provides operators with necessary information in real time during the response, improving the quality of service. As a result, the escalation department can respond to customer inquiries quickly and appropriately, improving customer satisfaction.

[0074] The customer support department provides 24 / 7 support based on inquiries handed over by the escalation department. The department utilizes technologies such as shift systems and automated systems to maintain 24 / 7 support. Specifically, the department maintains a shift system to ensure operators are always on standby to handle customer inquiries, even late at night and on holidays. Furthermore, the department reduces the burden on operators and achieves efficient service by implementing automated systems. For example, the department implements a system that automatically categorizes customer inquiries and assigns them to the appropriate operator. This allows the department to respond to customer inquiries quickly and accurately, improving customer satisfaction. Additionally, the department centrally manages customer inquiry content and response history, enabling it to provide optimal support based on past response data. This allows the department to provide high-quality support tailored to customer needs, further improving customer satisfaction.

[0075] The understanding unit can highly understand customer inquiries using natural language processing technology. For example, the understanding unit accurately grasps customer inquiries using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For instance, the understanding unit uses morphological analysis to break down customer inquiries into individual words, grammatical analysis to analyze sentence structure, and semantic analysis to understand sentence meaning. This allows for a high level of understanding of customer inquiries through the use of natural language processing technology. Some or all of the above-described processes in the understanding unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the understanding unit can input customer inquiries into a generative AI, which can then analyze and understand the inquiries.

[0076] The learning unit can improve the quality of its responses based on past dialogue data. For example, the learning unit analyzes past dialogue data and prioritizes learning data that provides optimal answers to frequently asked questions. For example, the learning unit collects past dialogue data as text data or audio data and optimizes its learning algorithm based on it. By improving the quality of responses based on past dialogue data, it becomes possible to provide more accurate and faster responses over time. Some or all of the above processing in the learning unit may be performed using generative AI, or it may be performed without generative AI. For example, the learning unit can input past dialogue data into a generative AI, which can then analyze the data and optimize its learning algorithm.

[0077] The dialogue unit can interact with multiple customers simultaneously. The dialogue unit interacts with multiple customers simultaneously using technologies such as chatbots and multithreading. For example, even if multiple customers make inquiries at the same time, the dialogue unit will respond to each customer individually. This allows for quick responses without any waiting time when customers make inquiries by interacting with multiple customers simultaneously. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the content of inquiries from multiple customers into a generative AI, and the generative AI can respond to each inquiry individually.

[0078] The escalation unit can have a seamless process for transferring inquiries to human operators as needed. The escalation unit can achieve a seamless escalation process using technologies such as real-time data transfer and collaborative systems. For example, the escalation unit will transfer inquiries to operators when there are technical problems or when special handling is required. This allows for a seamless process of transferring inquiries to human operators as needed, enabling a rapid response even to complex problems that agents cannot handle. Some or all of the above-described processes in the escalation unit may be performed using generative AI, or not. For example, the escalation unit can input the inquiry content into a generative AI, which can then determine whether or not to transfer the inquiry to an operator.

[0079] The support department is available 24 hours a day, 365 days a year. The support department operates 24 hours a day, 365 days a year, using technologies such as shift systems and automated systems. For example, the support department responds to customer inquiries even late at night or on holidays. This ensures that customer inquiries are always addressed, as the support department is available 24 hours a day, 365 days a year. Some or all of the above-described processes in the support department may be performed using a generation AI, or they may be performed without a generation AI. For example, the support department can input the inquiry content into a generation AI, which can then propose the optimal method for 24 / 7 support.

[0080] The understanding unit can estimate the customer's emotions and adjust its understanding of the inquiry based on the estimated emotions. For example, if the customer is angry, the understanding unit prioritizes a concise answer to respond quickly. For example, if the customer is confused, the understanding unit gathers additional information to provide a more detailed explanation. For example, if the customer is relaxed, the understanding unit applies the normal understanding process and provides a standard answer. This allows for a more appropriate response by adjusting the understanding of the inquiry based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using or without a generative AI. For example, the understanding unit can input customer emotion data into a generative AI, which can estimate the emotion and adjust its understanding.

[0081] The understanding unit can analyze a customer's past inquiry history and select the optimal understanding method. For example, if a customer has asked the same question in the past, the understanding unit can refer to that history and provide a quick answer. For example, if a customer has shown interest in a particular topic in the past, the understanding unit will prioritize understanding information related to that topic. For example, if a customer has asked multiple different questions in the past, the understanding unit can analyze the patterns and select the optimal understanding method. This allows the understanding unit to select the optimal understanding method and provide a quick answer by analyzing the customer's past inquiry history. Some or all of the above processing in the understanding unit may be performed using or without a generative AI. For example, the understanding unit can input the customer's past inquiry history into a generative AI, which can then select the optimal understanding method.

[0082] The understanding unit can filter the content of inquiries based on the customer's current situation and areas of interest. For example, if the customer describes their current situation, the understanding unit prioritizes understanding information related to that situation. For example, if the customer asks a question about a specific area of ​​interest, the understanding unit filters and provides information related to that area. For example, if the customer asks multiple questions, the understanding unit prioritizes understanding the most relevant question based on the customer's current situation and areas of interest. This allows the understanding unit to provide more relevant information by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the understanding unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the understanding unit can input data on the customer's current situation and areas of interest into a generative AI, which can then perform the filtering.

[0083] The understanding unit can estimate the customer's emotions and determine the priority of inquiries to be understood based on the estimated emotions. For example, if the customer is angry, the understanding unit will process that inquiry with the highest priority. For example, if the customer is confused, the understanding unit will process that inquiry quickly. For example, if the customer is relaxed, the understanding unit will process the inquiry with the normal priority. This allows inquiries to be processed in a more appropriate order by determining the priority of inquiries to be understood based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the understanding unit may be performed using or without a generative AI. For example, the understanding unit can input customer emotion data into a generative AI, which can estimate emotions and determine priorities.

[0084] The understanding unit can prioritize understanding highly relevant content by considering the customer's geographical location when understanding the content of an inquiry. For example, if the customer is in a specific region, the understanding unit will prioritize understanding information related to that region. For example, if the customer is traveling, the understanding unit will prioritize understanding information related to their travel destination. For example, if the customer is in a specific city, the understanding unit will prioritize understanding information related to that city. By prioritizing the understanding of highly relevant content while considering the customer's geographical location, the understanding unit can provide more appropriate information. Some or all of the above processing in the understanding unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the understanding unit can input the customer's geographical location information into a generative AI, which can then prioritize understanding highly relevant content.

[0085] The understanding unit can analyze the customer's social media activity and understand relevant content when understanding an inquiry. For example, if the customer is talking about a specific topic on social media, the understanding unit will prioritize understanding information related to that topic. For example, if the customer is mentioning a specific issue on social media, the understanding unit will prioritize understanding information related to that issue. For example, if the customer is talking about a specific product on social media, the understanding unit will prioritize understanding information related to that product. This allows the understanding unit to provide more relevant information by analyzing the customer's social media activity. Some or all of the above processing in the understanding unit may be performed using generative AI, or not. For example, the understanding unit can input data on the customer's social media activity into a generative AI, which can then understand the relevant content.

[0086] The learning unit can estimate the customer's emotions and select training data based on the estimated emotions. For example, if the customer is angry, the learning unit will prioritize learning data related to that emotion. For example, if the customer is confused, the learning unit will prioritize learning data related to that emotion. For example, if the customer is relaxed, the learning unit will select normal training data. This allows for the learning of more appropriate data by selecting training data based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using or without a generative AI. For example, the learning unit can input customer emotion data into a generative AI, which can then estimate the emotion and select training data.

[0087] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal algorithm. For example, the learning unit can adjust the algorithm parameters based on past learning data. For example, the learning unit can optimize the learning process by referring to past learning data. This improves the accuracy of learning by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the learning unit can input past learning data into a generative AI, and the generative AI can optimize the algorithm.

[0088] The learning unit can prioritize learning data that provides optimal answers to frequently asked questions during the learning process. For example, the learning unit can analyze frequently asked questions and prioritize learning the answer data. For example, the learning unit can prioritize learning relevant data to provide optimal answers to frequently asked questions. For example, the learning unit can prioritize learning relevant data to improve the quality of answers to frequently asked questions. This improves the quality of responses by prioritizing the learning of data that provides optimal answers to frequently asked questions. Some or all of the above processing in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input data on frequently asked questions into a generative AI, which can then learn data to provide optimal answers.

[0089] The learning unit can estimate the customer's emotions and adjust the learning frequency based on the estimated emotions. For example, if the customer is angry, the learning unit will frequently learn data related to that emotion. For example, if the customer is confused, the learning unit will frequently learn data related to that emotion. For example, if the customer is relaxed, the learning unit will learn data at a normal learning frequency. By adjusting the learning frequency based on the customer's emotions, learning can be performed at a more appropriate frequency. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using or without a generative AI. For example, the learning unit can input customer emotion data into a generative AI, which can estimate the emotion and adjust the learning frequency.

[0090] The learning unit can weight the training data based on the submission date of inquiries during training. For example, the learning unit can weight the training data based on recent inquiries. For example, the learning unit can weight the training data based on past inquiries. For example, the learning unit can weight the training data based on inquiries received during a specific period. By weighting the training data based on the submission date of inquiries, more appropriate data can be learned. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input data on the submission date of inquiries into a generative AI, and the generative AI can weight the training data.

[0091] The learning unit can select training data while considering customer attribute information during training. For example, the learning unit may select training data based on the customer's age. For example, the learning unit may select training data based on the customer's gender. For example, the learning unit may select training data based on the customer's region. By selecting training data while considering customer attribute information, more appropriate data can be learned. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input customer attribute information into a generative AI, and the generative AI can select training data.

[0092] The dialogue unit can estimate the customer's emotions and adjust the way the dialogue is expressed based on the estimated emotions. For example, if the customer is angry, the dialogue unit will use a calm and composed expression. For example, if the customer is confused, the dialogue unit will use a detailed and easy-to-understand expression. For example, if the customer is relaxed, the dialogue unit will use a normal expression. This allows for more appropriate dialogue by adjusting the way the dialogue is expressed based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input customer emotion data into a generative AI, which can estimate the emotion and adjust the way the dialogue is expressed.

[0093] The dialogue unit can adjust the level of detail in the conversation based on the customer's importance. For example, the dialogue unit provides detailed information to important customers, standard information to general customers, and concise information to low-priority customers. By adjusting the level of detail in the conversation based on the customer's importance, more appropriate information can be provided. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input customer importance data into a generative AI, which can then adjust the level of detail in the conversation.

[0094] The dialogue unit can apply different dialogue algorithms depending on the customer's category during a conversation. For example, the dialogue unit might apply an algorithm that provides basic information to new customers, an algorithm that provides detailed information to repeat customers, and an algorithm that provides special information to VIP customers. By applying different dialogue algorithms depending on the customer's category, more appropriate conversations become possible. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input customer category data into a generative AI, and the generative AI can apply different dialogue algorithms.

[0095] The dialogue unit can estimate the customer's emotions and adjust the length of the dialogue based on the estimated emotions. For example, if the customer is angry, the dialogue unit will quickly end the dialogue. For example, if the customer is confused, the dialogue unit will extend the dialogue to provide a more detailed explanation. For example, if the customer is relaxed, the dialogue unit will maintain a normal dialogue length. This allows for more appropriate dialogue by adjusting the length of the dialogue based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input customer emotion data into a generative AI, which can then estimate the emotion and adjust the length of the dialogue.

[0096] The dialogue unit can determine the priority of a conversation based on the customer's inquiry. For example, it will prioritize urgent inquiries. For example, it will prioritize general inquiries. For example, it will postpone inquiries. By determining the priority of conversations based on the customer's inquiry, it is possible to conduct conversations in a more appropriate order. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input customer inquiry data into a generative AI, and the generative AI can determine the priority of the conversation.

[0097] The dialogue unit can adjust the order of conversations based on customer relevance during a conversation. For example, the dialogue unit will respond to important customers first. For example, the dialogue unit will respond to general customers in the normal order. For example, the dialogue unit will respond to lower-priority customers later. By adjusting the order of conversations based on customer relevance, conversations can be conducted in a more appropriate order. Some or all of the above processing in the dialogue unit may be performed using generative AI, or it may be performed without generative AI. For example, the dialogue unit can input customer relevance data into the generative AI, and the generative AI can adjust the order of conversations.

[0098] The escalation unit can estimate the customer's emotions and adjust the escalation criteria based on the estimated emotions. For example, if the customer is angry, the escalation unit will escalate quickly. For example, if the customer is confused, the escalation unit will escalate to provide more detailed information. For example, if the customer is relaxed, the escalation unit will escalate using normal criteria. This allows for more appropriate escalation by adjusting the escalation criteria based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the escalation unit may be performed using or without generative AI. For example, the escalation unit can input customer emotion data into a generative AI, which can estimate the emotion and adjust the escalation criteria.

[0099] The escalation unit can improve the accuracy of escalation by considering the relationships between customers during the escalation process. For example, if a customer is related to other customers, the escalation unit will consider those relationships when escalating. For example, if a customer belongs to a specific group, the escalation unit will consider the information of that group when escalating. For example, if a customer is involved in a specific project, the escalation unit will consider the information of that project when escalating. By improving the accuracy of escalation by considering the relationships between customers, more appropriate escalation becomes possible. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the relationships between customers into a generative AI, which can then improve the accuracy of escalation.

[0100] The escalation unit can perform escalations while considering customer attribute information. For example, the escalation unit may perform escalations based on the customer's age. For example, the escalation unit may perform escalations based on the customer's gender. For example, the escalation unit may perform escalations based on the customer's region. By performing escalations while considering customer attribute information, more appropriate escalations become possible. Some or all of the above processing in the escalation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the escalation unit can input customer attribute information into a generation AI, and the generation AI can perform the escalation.

[0101] The escalation unit can estimate the customer's emotions and adjust the order in which the escalation results are displayed based on the estimated emotions. For example, if the customer is angry, the escalation unit will display the results quickly. For example, if the customer is confused, the escalation unit will display the results in detail. For example, if the customer is relaxed, the escalation unit will display the results in the normal order. This allows for the display of results in a more appropriate order by adjusting the order in which the escalation results are displayed based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the escalation unit may be performed using or without a generative AI. For example, the escalation unit can input customer emotion data into a generative AI, which can then estimate the emotions and adjust the order in which the results are displayed.

[0102] The escalation unit can perform escalations while considering the geographical distribution of customers. For example, if a customer is in a specific region, the escalation unit will perform escalations while considering information related to that region. For example, if a customer is traveling, the escalation unit will perform escalations while considering information related to the travel destination. For example, if a customer is in a specific city, the escalation unit will perform escalations while considering information related to that city. This makes it possible to perform more appropriate escalations by considering the geographical distribution of customers. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the geographical distribution of customers into a generative AI, and the generative AI can perform escalations.

[0103] The escalation unit can improve the accuracy of escalations by referring to the customer's relevant literature during the escalation process. For example, if the customer refers to a specific document, the escalation unit will take that document into consideration when escalating. For example, if the customer is conducting a specific research project, the escalation unit will take that research into consideration when escalating. For example, if the customer is involved in a specific project, the escalation unit will take that project's literature into consideration when escalating. By improving the accuracy of escalations by referring to the customer's relevant literature, more appropriate escalations become possible. Some or all of the above processing in the escalation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the escalation unit can input data on the customer's relevant literature into a generative AI, which can then improve the accuracy of the escalation.

[0104] The response unit can estimate the customer's emotions and adjust its response based on those emotions. For example, if the customer is angry, the response unit prioritizes a concise response to ensure a quick response. If the customer is confused, for example, the response unit gathers additional information to provide a more detailed explanation. If the customer is relaxed, for example, the response unit applies its normal response method. This allows for a more appropriate response by adjusting the response method based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using or without generative AI. For example, the response unit can input customer emotion data into a generative AI, which can then estimate the emotion and adjust its response method.

[0105] The response unit can select the optimal response method by referring to the customer's past inquiry history when responding to an inquiry. For example, if the customer has asked the same question in the past, the response unit can refer to that history and provide a quick answer. For example, if the customer has shown interest in a particular topic in the past, the response unit can prioritize providing information related to that topic. For example, if the customer has asked multiple different questions in the past, the response unit can analyze the pattern and select the optimal response method. This enables faster and more appropriate responses by referring to the customer's past inquiry history and selecting the optimal response method. Some or all of the above processing in the response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the response unit can input data from the customer's past inquiry history into a generative AI, which can then select the optimal response method.

[0106] The response unit can customize its response methods based on the customer's current situation when responding. For example, if the customer describes their current situation, the response unit will prioritize providing information relevant to that situation. For example, if the customer asks about a specific area of ​​interest, the response unit will provide information relevant to that area. For example, if the customer asks multiple questions, the response unit will prioritize responding to the most relevant question based on the customer's current situation. This allows for a more appropriate response by customizing the response methods based on the customer's current situation. Some or all of the above processing in the response unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the response unit can input data on the customer's current situation into a generative AI, which can then customize the response methods.

[0107] The response unit can estimate the customer's emotions and determine the priority of responses based on the estimated emotions. For example, if the customer is angry, the response unit will process the inquiry with the highest priority. If the customer is confused, the response unit will process the inquiry quickly. If the customer is relaxed, the response unit will process the inquiry with the normal priority. This allows for responses to be delivered in a more appropriate order by determining the priority of responses based on the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the response unit may be performed using generative AI or not. For example, the response unit can input customer emotion data into a generative AI, which can estimate the emotions and determine the priority of responses.

[0108] The response unit can select the optimal response method when responding to a customer, taking into account the customer's geographical location information. For example, if the customer is in a specific region, the response unit will prioritize providing information related to that region. For example, if the customer is traveling, the response unit will prioritize providing information related to their travel destination. For example, if the customer is in a specific city, the response unit will prioritize providing information related to that city. By selecting the optimal response method considering the customer's geographical location information, more appropriate information can be provided. Some or all of the above processing in the response unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the response unit can input the customer's geographical location data into a generation AI, which can then select the optimal response method.

[0109] The response unit can analyze the customer's social media activity and propose a course of action when responding. For example, if the customer is talking about a specific topic on social media, the response unit will prioritize providing information related to that topic. For example, if the customer is mentioning a specific issue on social media, the response unit will prioritize providing information related to that issue. For example, if the customer is talking about a specific product on social media, the response unit will prioritize providing information related to that product. This allows the response unit to provide more appropriate information by analyzing the customer's social media activity and proposing a course of action. Some or all of the above processing in the response unit may be performed using or without a generative AI. For example, the response unit can input data on the customer's social media activity into a generative AI, which can then propose a course of action.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] Interactive customer center agents can estimate a customer's emotions and adjust the tone of the conversation based on that estimation. For example, if a customer is angry, the agent will use a calm and composed tone to alleviate the customer's frustration. If a customer is confused, the agent will use a kind and polite tone to explain things in a way that is easy for the customer to understand. If a customer is relaxed, the agent will use a friendly and casual tone to facilitate the conversation. This allows for improved customer satisfaction by using an appropriate tone of voice based on the customer's emotions. Emotion estimation is achieved using emotion engines or generative AI. For example, the agent can input customer emotion data into a generative AI, which can then estimate the emotion and adjust the tone of the conversation accordingly.

[0112] Interactive customer center agents can analyze a customer's past purchase history and provide optimal suggestions. For example, if a customer has previously purchased a specific product, they can offer information on new products or upgrades related to that product. If a customer has frequently purchased products in a specific category in the past, they can offer special offers or discounts related to that category. If a customer has a preference for a particular brand in the past, they can suggest new or limited-edition products from that brand. This allows for improved customer satisfaction by providing optimal suggestions based on the customer's past purchase history. Purchase history analysis can also be performed using generative AI; for example, an agent can input customer purchase history data into a generative AI, which can then generate optimal suggestions.

[0113] Interactive customer center agents can estimate customer emotions and adjust the timing of escalation based on those estimates. For example, if a customer is angry, the agent will escalate quickly to resolve the issue promptly. If a customer is confused, the agent will provide a detailed explanation and escalate as needed. If a customer is relaxed, the agent will apply the standard escalation process and escalate at the appropriate time. This improves customer satisfaction by escalating at the right time according to the customer's emotions. Emotion estimation is achieved using emotion engines or generative AI. For example, the agent can input customer emotion data into generative AI, which can estimate emotions and adjust the timing of escalation.

[0114] Interactive customer center agents can customize the content of their conversations based on the customer's current situation. For example, if a customer is traveling, they can provide information and services related to their destination. If a customer is attending a specific event, they can provide information and support related to that event. If a customer is working on a specific project, they can provide information and resources related to that project. By customizing the conversation based on the customer's current situation, more relevant information can be provided, improving customer satisfaction. Situational awareness may also be achieved using generative AI; for example, the agent can input data on the customer's current situation into the generative AI, which can then customize the optimal conversation content.

[0115] Interactive customer center agents can estimate a customer's emotions and adjust the pace of the conversation based on that estimation. For example, if a customer is angry, the agent will proceed quickly and strive to resolve the problem as soon as possible. If a customer is confused, the agent will explain slowly and carefully, adjusting the pace of the conversation to ensure the customer understands. If a customer is relaxed, the agent will proceed at a normal pace, ensuring a smooth conversation. This allows for improved customer satisfaction by conducting conversations at an appropriate pace according to the customer's emotions. Emotion estimation is achieved using emotion engines or generative AI. For example, the agent can input customer emotion data into a generative AI, which can then estimate the emotion and adjust the pace of the conversation accordingly.

[0116] Interactive customer center agents can analyze a customer's past inquiry history and select the most appropriate response. For example, if a customer has asked the same question before, they can refer to that history to provide a quick answer. If a customer has shown interest in a particular topic in the past, they can prioritize providing information related to that topic. If a customer has asked multiple different questions in the past, the system analyzes the patterns to select the most appropriate response. This allows for faster and more appropriate responses by selecting the best response based on the customer's past inquiry history. The analysis of inquiry history may also be performed using generative AI; for example, an agent can input customer inquiry history data into a generative AI, which can then select the most appropriate response.

[0117] Interactive customer service agents can estimate a customer's emotions and adjust the length of the conversation based on that estimation. For example, if a customer is angry, the agent will end the conversation quickly and try to resolve the problem as soon as possible. If a customer is confused, the agent will extend the conversation to provide a more detailed explanation. If a customer is relaxed, the agent will maintain a normal conversation length to ensure a smooth interaction. This improves customer satisfaction by conducting conversations of an appropriate length according to the customer's emotions. Emotion estimation is achieved using emotion engines or generative AI. For example, the agent can input customer emotion data into a generative AI, which can then estimate the emotion and adjust the conversation length accordingly.

[0118] Interactive customer center agents can select the most appropriate response method by considering the customer's geographical location. For example, if a customer is in a specific region, they can prioritize providing information relevant to that region. If a customer is traveling, they can prioritize providing information relevant to their travel destination. If a customer is in a specific city, they can prioritize providing information relevant to that city. By selecting the most appropriate response method based on the customer's geographical location, more relevant information can be provided. Consideration of geographical location can also be performed using generative AI; for example, the agent can input the customer's geographical location data into the generative AI, which can then select the most appropriate response method.

[0119] Interactive customer center agents can estimate customer emotions and prioritize responses based on those estimates. For example, if a customer is angry, the inquiry will be handled with the highest priority. If a customer is confused, the inquiry will be handled quickly. If a customer is relaxed, the inquiry will be handled with the normal priority. This allows for more appropriate responses by prioritizing responses based on customer emotions. Emotion estimation is achieved using emotion engines or generative AI. For example, an agent can input customer emotion data into a generative AI, which can then estimate the emotion and determine the priority of responses.

[0120] Interactive customer center agents can analyze customers' social media activity and provide relevant information. For example, if a customer is discussing a specific topic on social media, they can prioritize providing information related to that topic. If a customer is mentioning a specific issue on social media, they can prioritize providing information related to that issue. If a customer is discussing a specific product on social media, they can prioritize providing information related to that product. By analyzing customers' social media activity and providing relevant information, it is possible to provide more appropriate information and improve customer satisfaction. Social media activity analysis can also be performed using generative AI; for example, an agent can input customer social media activity data into a generative AI, which can then provide relevant information.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The understanding unit understands the customer's inquiry. The understanding unit uses, for example, natural language processing technology to gain a high level of understanding of the customer's inquiry. Specifically, it uses technologies such as morphological analysis, grammatical analysis, and semantic analysis to accurately grasp the customer's inquiry. Step 2: The learning unit improves the quality of responses based on the inquiries understood by the understanding unit. For example, the learning unit improves the quality of responses based on past dialogue data. Specifically, it analyzes past dialogue data and prioritizes learning data to provide optimal answers to frequently asked questions. Step 3: The dialogue unit interacts with multiple customers simultaneously, based on the improved quality of responses achieved by the learning unit. The dialogue unit interacts with multiple customers simultaneously, for example, using technologies such as chatbots and multithreading. Specifically, even if multiple customers make inquiries at the same time, it responds to each customer individually. Step 4: The escalation unit, based on the content of the conversation conducted by the dialogue unit, transfers the inquiry to a human operator as needed. The escalation unit achieves a seamless escalation process using technologies such as real-time data transfer and integrated systems. Specifically, it transfers the inquiry to an operator when there are technical issues or when special handling is required. Step 5: The support department will provide 24 / 7 support based on inquiries handed over by the escalation department. The support department will provide 24 / 7 support using technologies such as shift work and automated systems. Specifically, they will respond to customer inquiries even late at night and on holidays.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the understanding unit, learning unit, dialogue unit, escalation unit, and response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the understanding unit is implemented by the control unit 46A of the smart device 14 and uses natural language processing technology to highly understand the content of customer inquiries. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the quality of responses based on past dialogue data. The dialogue unit is implemented by the control unit 46A of the smart device 14 and interacts with multiple customers simultaneously. The escalation unit is implemented by the specific processing unit 290 of the data processing unit 12 and, if necessary, hands over the inquiry to a human operator. The response unit is implemented by the control unit 46A of the smart device 14 and provides 24 / 7 support. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the understanding unit, learning unit, dialogue unit, escalation unit, and response unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the understanding unit is implemented by the control unit 46A of the smart glasses 214 and uses natural language processing technology to highly understand the content of customer inquiries. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the quality of responses based on past dialogue data. The dialogue unit is implemented by the control unit 46A of the smart glasses 214 and interacts with multiple customers simultaneously. The escalation unit is implemented by the specific processing unit 290 of the data processing unit 12 and, if necessary, hands over the inquiry to a human operator. The response unit is implemented by the control unit 46A of the smart glasses 214 and provides 24 / 7 support. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the understanding unit, learning unit, dialogue unit, escalation unit, and response unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the understanding unit is implemented by the control unit 46A of the headset terminal 314 and uses natural language processing technology to highly understand the content of customer inquiries. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the quality of responses based on past dialogue data. The dialogue unit is implemented by the control unit 46A of the headset terminal 314 and interacts with multiple customers simultaneously. The escalation unit is implemented by the specific processing unit 290 of the data processing unit 12 and, if necessary, hands over the inquiry to a human operator. The response unit is implemented by the control unit 46A of the headset terminal 314 and provides 24 / 7 support. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the understanding unit, learning unit, dialogue unit, escalation unit, and response unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the understanding unit is implemented by the control unit 46A of the robot 414 and uses natural language processing technology to highly understand the content of customer inquiries. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves the quality of responses based on past dialogue data. The dialogue unit is implemented by the control unit 46A of the robot 414 and interacts with multiple customers simultaneously. The escalation unit is implemented by the specific processing unit 290 of the data processing unit 12 and, if necessary, hands over the inquiry to a human operator. The response unit is implemented by the control unit 46A of the robot 414 and provides 24 / 7 support. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) A comprehension unit that understands customer inquiries, A learning unit that improves the quality of responses based on the content of inquiries understood by the aforementioned understanding unit, Based on the improved quality of response achieved by the aforementioned learning unit, the dialogue unit engages in conversations with multiple customers simultaneously. An escalation unit that, based on the content of the conversation conducted by the aforementioned dialogue unit, transfers the inquiry to a human operator as needed. The system includes a response unit that provides 24 / 7 support based on inquiries taken over by the escalation unit. A system characterized by the following features. (Note 2) The aforementioned understanding unit is, Using natural language processing technology to gain a high level of understanding of customer inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, Improve the quality of service based on past conversation data. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned dialogue unit, Interacting with multiple customers simultaneously The system described in Appendix 1, characterized by the features described herein. (Note 5) The escalation unit is, We have a seamless process to transfer inquiries to human operators as needed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The corresponding part is, Available 24 hours a day, 365 days a year The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned understanding unit is, It estimates the customer's emotions and adjusts the level of understanding of the inquiry based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned understanding unit is, Analyze the customer's past inquiry history and select the most appropriate method of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned understanding unit is, When understanding inquiries, filtering is performed based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned understanding unit is, Estimate customer emotions and prioritize inquiries that require understanding based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned understanding unit is, When understanding customer inquiries, we prioritize understanding the most relevant information by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned understanding unit is, When understanding customer inquiries, we analyze their social media activity to identify relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, The system estimates customer emotions and selects training data based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, During training, the system prioritizes learning data that provides the best answers to frequently asked questions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, It estimates customer emotions and adjusts the learning frequency based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, During training, the training data is weighted based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During training, select training data while considering customer attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned dialogue unit, It estimates the customer's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned dialogue unit, During conversations, adjust the level of detail based on the customer's importance. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned dialogue unit, During the interaction, different dialogue algorithms are applied depending on the customer's category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned dialogue unit, It estimates the customer's emotions and adjusts the length of the conversation based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned dialogue unit, During the conversation, prioritize the conversation based on the customer's inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned dialogue unit, During conversations, adjust the order of the conversation based on the customer's relevance. The system described in Appendix 1, characterized by the features described herein. (Note 25) The escalation unit is, Estimate customer sentiment and adjust escalation criteria based on estimated customer sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The escalation unit is, When escalating a case, consider the relationships between customers to improve the accuracy of the escalation process. The system described in Appendix 1, characterized by the features described herein. (Note 27) The escalation unit is, When escalating a case, consider the customer's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The escalation unit is, It estimates customer sentiment and adjusts the order in which escalation results are displayed based on the estimated customer sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The escalation unit is, When escalating a case, consider the geographical distribution of the customers. The system described in Appendix 1, characterized by the features described herein. (Note 30) The escalation unit is, During escalation, refer to relevant customer literature to improve the accuracy of the escalation. The system described in Appendix 1, characterized by the features described herein. (Note 31) The corresponding part is, We estimate the customer's emotions and adjust our response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The corresponding part is, When responding to a customer inquiry, the system will refer to the customer's past inquiry history to select the most appropriate course of action. The system described in Appendix 1, characterized by the features described herein. (Note 33) The corresponding part is, When responding, customize the response method based on the customer's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The corresponding part is, Estimate the customer's emotions and determine the priority of responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The corresponding part is, When responding to a customer, the most appropriate response method will be selected, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The corresponding part is, When responding to a customer, we analyze their social media activity and propose appropriate responses. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 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. A comprehension unit that understands customer inquiries, A learning unit that improves the quality of responses based on the content of inquiries understood by the aforementioned understanding unit, Based on the improved quality of response achieved by the aforementioned learning unit, the dialogue unit engages in conversations with multiple customers simultaneously. An escalation unit that, based on the content of the conversation conducted by the aforementioned dialogue unit, transfers the inquiry to a human operator as needed. The system includes a response unit that provides 24 / 7 support based on inquiries taken over by the escalation unit. A system characterized by the following features.

2. The aforementioned understanding unit is, Using natural language processing technology to gain a high level of understanding of customer inquiries. The system according to feature 1.

3. The aforementioned learning unit, Improve the quality of service based on past conversation data. The system according to feature 1.

4. The aforementioned dialogue unit, Interacting with multiple customers simultaneously The system according to feature 1.

5. The escalation unit is, We have a seamless process to transfer inquiries to human operators as needed. The system according to feature 1.

6. The corresponding part is, Available 24 hours a day, 365 days a year The system according to feature 1.

7. The aforementioned understanding unit is, It estimates the customer's emotions and adjusts the level of understanding of the inquiry based on those estimated emotions. The system according to feature 1.

8. The aforementioned understanding unit is, Analyze the customer's past inquiry history and select the most appropriate method of understanding. The system according to feature 1.

Images