System

Abstract

To provide a system according to an embodiment that responds quickly and appropriately to various inquiries from customers.SOLUTION: A system according to an embodiment comprises a reception unit, a response providing unit, a troubleshooting unit, a product information providing unit, an order information providing unit, and a connection unit. The reception unit receives input from a customer. The response providing unit, when the type of input from the customer is a question about a product, generates a response to the question and provides the generated response to the customer. The troubleshooting unit, when the type of input from the customer is a technical problem or malfunction of a product, proposes a solution to the technical problem or malfunction to the customer. The product information providing unit, when the type of input from the customer is information about a product, provides the information about the product to the customer. The order information providing unit, when the type of input from the customer is a product order, provides information on the order history and delivery status of the product to the customer. The connection unit connects the customer to a person in charge or a responsible department when the response providing unit is unable to provide a response.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to respond quickly and appropriately to various inquiries from customers, and there were challenges in improving customer satisfaction.

[0005] The system according to the embodiment aims to quickly and appropriately respond to various inquiries from customers. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an answer providing unit, a troubleshooting unit, a product information providing unit, an order information providing unit, and a connection unit. The reception unit receives input from a customer. If the type of the customer's input is a product question, the answer providing unit generates an answer to the question and provides the generated answer to the customer. If the type of the customer's input is a technical problem or malfunction of the product, the troubleshooting unit proposes a solution to the technical problem or malfunction to the customer. If the type of the customer's input is product information, the product information providing unit provides the customer with product information. If the type of the customer's input is a product order, the order information providing unit provides the customer with information on the product's order history and delivery status. If the type of the customer's input is a product order, the connection unit connects the customer to a person in charge or a department in charge. Effect of the Invention

[0007] The system according to the embodiment can quickly and appropriately respond to various inquiries from customers. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The AI ​​assistant system for a customer support center according to an embodiment of the present invention is a system that accepts input from customers, generates answers to questions using a generation AI, proposes solutions to technical problems and malfunctions, provides information on products and services, and provides information on order history and delivery status. This system can quickly and appropriately respond to various inputs from customers. For example, it has an FAQ answering function that quickly answers questions frequently asked by customers, a troubleshooting function that proposes solutions to technical problems and malfunctions, a product information providing function that provides detailed information on products and services, an order information providing function that checks order history and delivery status, a feedback collecting function that collects customer opinions and requests, an escalation support function that escalates to an appropriate person or department to deal with complex problems or specific requests, and a 24-hour support function. As a result, the AI ​​assistant system for a customer support center can quickly and appropriately respond to various needs of customers.

[0029] The AI ​​assistant system of the customer support center according to the embodiment includes a reception unit, an answer providing unit, a troubleshooting unit, a product information providing unit, an order information providing unit, and a connection unit. The reception unit receives input from a customer. The customer input includes, but is not limited to, for example, text input, voice input, and image input. The reception unit receives the customer input using a generation AI. The generation AI analyzes the customer input and performs appropriate processing using, for example, natural language generation, image generation, voice generation, and other technologies. The answer providing unit generates an answer to a question using the AI. The AI ​​generates an appropriate answer to a customer question using, for example, natural language processing, machine learning, deep learning, and other technologies. The troubleshooting unit uses the AI ​​to propose a solution to a technical problem or malfunction. The AI ​​uses, for example, natural language processing, machine learning, deep learning, and other technologies to propose an appropriate solution to a customer's technical problem or malfunction. The product information providing unit provides product information using the AI. The AI ​​provides appropriate product information to the customer using, for example, natural language processing, machine learning, deep learning, and other technologies. The order information providing unit manages information on order history and delivery status using blockchain technology. The blockchain technology uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage information on order history and delivery status. The connection unit connects the customer to a person in charge or department in charge when the answer providing unit cannot provide an answer. The connection unit uses AI to select an appropriate person in charge or department and connects the customer. This allows the customer support center's AI assistant system to quickly and appropriately respond to the diverse needs of customers.

[0030] The reception unit receives input from a customer. Examples of customer input include, but are not limited to, text input, voice input, and image input. The reception unit uses a generation AI to receive customer input. The generation AI analyzes the customer input using technologies such as natural language generation, image generation, and voice generation, and performs appropriate processing. Specifically, in the case of text input, the generation AI analyzes the input content using natural language processing technology and understands the customer's intention. For example, if a customer inputs "I would like to cancel my order," the generation AI accurately grasps the intention and performs appropriate processing to proceed to the next step. In the case of voice input, the generation AI converts voice data into text using voice recognition technology, and then analyzes it using natural language processing technology. For example, if a customer inputs by voice, "Please tell me the details of the product," the generation AI converts the voice into text and understands the intention. In the case of image input, the generation AI analyzes image data using image recognition technology and understands the customer's request. For example, if a customer sends a photo of a defective product, the generation AI analyzes the image and identifies the content of the defect. This allows the reception unit to handle a variety of input formats and accurately grasp the customer's request. Furthermore, the reception department can analyze the contents entered by the customer in real time and move on to the next process quickly, thereby minimizing the waiting time for the customer and providing smooth support.

[0031] The answer providing unit generates answers to questions using AI. For example, AI uses technologies such as natural language processing, machine learning, and deep learning to generate appropriate answers to customer questions. Specifically, it uses natural language processing technology to analyze the content of the customer's question and understand the intent. For example, if a customer asks "Please tell me how to return a product," AI analyzes the question and generates an appropriate answer. It uses machine learning technology to learn data on past questions and answers and provide optimal answers to similar questions. For example, if many customers have asked a similar question in the past, it generates optimal answers based on the answer data. It uses deep learning technology to make it possible to handle complex questions. For example, if a customer asks "Please tell me the features of this product and how it differs from other products," AI analyzes the question with a deep learning model and generates detailed answers. This allows the answer providing unit to quickly and accurately provide answers to various questions from customers. Furthermore, the answer providing unit can evaluate the quality of the generated answers and make corrections as necessary. For example, if the generated answer is inappropriate, the AI ​​reevaluates the answer and generates a more appropriate answer. The answer providing unit can also collect customer feedback and continuously improve the quality of the answers. This allows the answer providing section to consistently provide high quality answers and improve customer satisfaction.

[0032] The troubleshooting department uses AI to propose solutions to technical problems or malfunctions. AI proposes appropriate solutions to customers' technical problems or malfunctions using technologies such as natural language processing, machine learning, and deep learning. Specifically, natural language processing technology is used to analyze the content of the customer's problem and identify its cause. For example, if a customer reports that "Internet connection is unstable," AI analyzes the problem and identifies possible causes. Machine learning technology is used to learn past troubleshooting data and provide optimal solutions to similar problems. For example, if a similar problem has occurred in the past, the optimal solution is proposed based on the solution data. Deep learning technology is used to make it possible to handle complex problems. For example, if a customer reports that "an error occurred during software installation," AI analyzes the problem with a deep learning model and proposes a detailed solution. This allows the troubleshooting department to quickly and accurately provide solutions to various technical problems of customers. In addition, the troubleshooting department can evaluate the effectiveness of the proposed solution and make corrections as necessary. For example, if the proposed solution is not effective, AI reevaluates the solution and proposes a more appropriate solution. In addition, the troubleshooting department can collect customer feedback and continuously improve the quality of the solutions. This enables the troubleshooting department to consistently provide high quality solutions and improve customer satisfaction.

[0033] The product information providing unit uses AI to provide product information. For example, AI uses technologies such as natural language processing, machine learning, and deep learning to provide appropriate product information to customers. Specifically, natural language processing technology is used to analyze the content of the customer's question and understand the intention. For example, if a customer asks, "Please tell me the features of this product," AI analyzes the question and provides appropriate product information. Machine learning technology is used to learn data on past questions and answers, and provide optimal product information for similar questions. For example, if many customers have asked a similar question in the past, optimal product information is provided based on the answer data. Deep learning technology is used to enable response to complex questions. For example, if a customer asks, "Please tell me the features of this product and the difference between it and other products," AI analyzes the question with a deep learning model and provides detailed product information. This allows the product information providing unit to quickly and accurately provide product information in response to various questions from customers. Furthermore, the product information providing unit can evaluate the quality of the provided product information and make corrections as necessary. For example, if the provided product information is inappropriate, AI reevaluates the information and provides more appropriate product information. In addition, the product information providing department can collect customer feedback and continuously improve the quality of the product information, thereby enabling the product information providing department to always provide high-quality product information and increase customer satisfaction.

[0034] The order information providing unit uses blockchain technology to manage information on order history and delivery status. Blockchain technology, for example, uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage information on order history and delivery status. Specifically, a public blockchain is used to make all order histories public and ensure transparency. This allows customers to check their order history at any time. A private blockchain is used to manage information on order history and delivery status within a company and enhance security. This allows companies to safely manage customer order information. A consortium blockchain is used to share information on order history and delivery status among multiple companies and realize efficient logistics management. This allows customers to check in real time what stage their order is at. Furthermore, the order information providing unit uses blockchain technology to record information on order history and delivery status in a form that cannot be tampered with. This allows customers to confirm that their order information is accurate. In addition, the order information providing unit can collect customer feedback and continuously improve the method of managing order information. This allows the order information providing unit to always provide high-quality order information and improve customer satisfaction.

[0035] The connection unit connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. The connection unit uses AI to select an appropriate person in charge or department and connects the customer. Specifically, the AI ​​analyzes the content of the customer's question and the type of problem, and identifies the most suitable person in charge or department. For example, if a customer asks "I would like to know more about returning products," the AI ​​analyzes the question and connects the customer to the returns department. Also, if a customer reports that "a technical problem has occurred," the AI ​​analyzes the problem and connects the customer to a technical support person. This allows the connection unit to respond quickly and appropriately to the diverse needs of customers. Furthermore, the connection unit can check the availability of the person in charge or department in real time to minimize the customer's waiting time, and make the optimal connection. For example, if multiple people are available, the AI ​​selects the person in charge who can respond most quickly and connects the customer. The connection unit can also collect customer feedback and continuously improve the quality of the connection method. This allows the connection unit to always provide high-quality connection services and improve customer satisfaction.

[0036] The answer providing unit can generate answers to questions using AI. The answer providing unit generates answers to customer questions using, for example, natural language processing technology. For example, the answer providing unit analyzes customer questions and generates appropriate answers. The answer providing unit can also generate answers to customer questions using machine learning technology. For example, the answer providing unit learns data on past questions and answers and generates appropriate answers to new questions. The answer providing unit can also generate answers to customer questions using deep learning technology. For example, the answer providing unit learns a large amount of text data and generates appropriate answers to customer questions using an AI model with advanced natural language processing capabilities. As a result, answers to questions can be generated quickly and accurately by using AI.

[0037] The troubleshooting unit can use AI to propose solutions to technical problems or malfunctions. The troubleshooting unit can use, for example, natural language processing technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit analyzes the customer's problem and proposes an appropriate solution. The troubleshooting unit can also use machine learning technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit learns data on past problems and solutions and proposes an appropriate solution to a new problem. The troubleshooting unit can also use deep learning technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit learns large amounts of text data and uses an AI model with advanced natural language processing capabilities to propose an appropriate solution to the customer's problem. As a result, solutions to technical problems and malfunctions are quickly and accurately proposed by using AI.

[0038] The order information providing unit can manage the information on the order history and the delivery status using blockchain technology. The order information providing unit can manage the information on the order history and the delivery status using, for example, public blockchain technology. For example, the order information providing unit records the data on the order history and the delivery status on the blockchain and manages it safely and accurately. The order information providing unit can also manage the information on the order history and the delivery status using private blockchain technology. For example, the order information providing unit builds a private blockchain used within a company and manages the data on the order history and the delivery status. The order information providing unit can also manage the information on the order history and the delivery status using consortium blockchain technology. For example, the order information providing unit builds a consortium blockchain in which multiple companies participate, shares the data on the order history and the delivery status, and manages it safely and accurately. As a result, the order history and the delivery status information are managed safely and accurately by using blockchain technology.

[0039] The reception unit can accept the customer's input using the generation AI. The reception unit accepts the customer's input using, for example, natural language generation technology. For example, the reception unit analyzes the customer's text input and performs appropriate processing. The reception unit can also accept the customer's input using image generation technology. For example, the reception unit analyzes the customer's image input and performs appropriate processing. The reception unit can also accept the customer's input using voice generation technology. For example, the reception unit analyzes the customer's voice input and performs appropriate processing. In this way, by using the generation AI, the customer's input can be accepted quickly and accurately.

[0040] The related information providing unit includes a related information providing unit, which can search and provide at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. The related information providing unit, for example, searches and provides social media posts. For example, the related information providing unit searches social media posts such as X (formerly Twitter (registered trademark)), Facebook (registered trademark), and Instagram (registered trademark), and provides information related to the customer's input. The related information providing unit can also search and provide scientific papers. For example, the related information providing unit searches scientific papers such as physics, chemistry, and biology, and provides information related to the customer's input. The related information providing unit can also search and provide technical specifications. For example, the related information providing unit searches technical specifications such as technical specifications, blueprints, and manuals of products, and provides information related to the customer's input. The related information providing unit can also search and provide patent documents. For example, the related information providing unit searches patent documents such as patent numbers, details of inventions, and claims, and provides information related to the customer's input. This allows the customer's questions and problems to be solved more effectively by providing a wide range of information related to the customer's input.

[0041] The reception unit can determine the type of input from the customer based on the attributes of the customer. The reception unit determines the type of input from the customer based on attribute information such as the customer's age, sex, occupation, and purchase history. By determining the type of input based on the attributes of the customer, more appropriate handling is possible.

[0042] The product information providing unit can visually provide product information to the customer by using augmented reality technology. The product information providing unit can visually provide product information to the customer by using, for example, AR glasses. For example, the product information providing unit displays detailed product information through the AR glasses. The product information providing unit can also visually provide product information to the customer by using a smartphone app. For example, the product information providing unit displays detailed product information through a smartphone app. The product information providing unit can also visually provide product information to the customer by using projection mapping technology. For example, the product information providing unit displays detailed product information using projection mapping. In this way, by using augmented reality technology, it is possible to provide product information that is visually easy to understand for the customer.

[0043] The system includes a prediction unit that can analyze a customer's input and predict future inputs using an AI model. The prediction unit can analyze a customer's input and predict future inputs using, for example, a neural network. The prediction unit can also analyze a customer's input and predict future inputs using a support vector machine. For example, the prediction unit predicts future inputs based on the customer's past input data. In this way, by predicting future inputs, countermeasures can be prepared in advance and a quick response can be made.

[0044] The system includes an adjustment unit, which can adjust the allocation of resources to the answer providing unit, the troubleshooting unit, the product information providing unit, the order information providing unit, and the connection unit based on the prediction result by the prediction unit. The adjustment unit adjusts CPU resources, for example. The adjustment unit can also adjust memory resources. For example, the adjustment unit allocates appropriate memory resources to each unit based on the prediction result by the prediction unit. The adjustment unit can also adjust personnel resources. For example, the adjustment unit allocates appropriate personnel resources to each unit based on the prediction result by the prediction unit. This adjusts the resource allocation, thereby improving the efficiency of the entire system.

[0045] The reception unit can analyze the customer's past inquiry history and select the optimal reception method. For example, the reception unit preferentially suggests an inquiry method that the customer has frequently used in the past. For example, the reception unit analyzes the customer's past inquiry history and selects the optimal reception method. The reception unit can also select the most efficient reception method from the customer's past inquiry history. For example, the reception unit selects the optimal reception method based on the customer's past inquiry data. The reception unit can also analyze the customer's past inquiry history and automatically select the optimal reception method. For example, the reception unit learns the customer's past inquiry data and suggests the optimal reception method. In this way, the optimal reception method can be provided to the customer by analyzing the past inquiry history.

[0046] The reception unit can filter inputs based on the customer's current situation and areas of interest. The reception unit, for example, preferentially receives inputs that are highly relevant based on the customer's current situation. For example, the reception unit filters relevant inputs based on the customer's current location and activity status. The reception unit can also filter relevant inputs based on the customer's areas of interest. For example, the reception unit filters relevant inputs based on the customer's hobbies and products and services in which the customer is interested. The reception unit can also filter optimal inputs based on the customer's current situation and areas of interest. For example, the reception unit analyzes the customer's current situation and areas of interest and selects optimal inputs. This makes it possible to provide more relevant responses by filtering inputs based on the customer's current situation and areas of interest.

[0047] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the customer. The reception unit preferentially receives highly relevant inputs, for example, based on the current location of the customer. For example, the reception unit filters relevant inputs based on the GPS data of the customer. The reception unit can also filter relevant inputs based on the IP address of the customer. The reception unit can also filter relevant inputs based on a location information service of the customer. For example, the reception unit analyzes the location information of the customer and selects the most appropriate input. This makes it possible to provide a more relevant response by considering the geographical location information of the customer.

[0048] The reception unit can analyze the social media activity of the customer and receive related input. For example, the reception unit analyzes the social media activity of the customer on X (formerly Twitter), Facebook, Instagram, etc., and filters the related input. The reception unit can also filter optimal input based on the social media activity of the customer. For example, the reception unit analyzes the social media activity of the customer and selects the optimal input. In this way, by analyzing the social media activity of the customer, it becomes possible to provide a more relevant response.

[0049] The answer providing unit can adjust the level of detail of the answer based on the importance of the question. The answer providing unit provides a detailed answer, for example, to an important question. For example, the answer providing unit generates a detailed answer based on the urgency and scope of impact of the question. The answer providing unit can also provide a concise answer to a general question. For example, the answer providing unit evaluates the importance of the question and generates a concise answer. The answer providing unit can also adjust the level of detail of the answer based on the importance of the question. For example, the answer providing unit analyzes the importance of the question and determines an optimal level of detail of the answer. In this way, a more appropriate answer can be provided by adjusting the level of detail of the answer based on the importance of the question.

[0050] The answer providing unit can apply different answer algorithms depending on the category of the question. For example, the answer providing unit applies a specialized answer algorithm to a technical question. For example, the answer providing unit analyzes a technical question and generates a specialized answer. The answer providing unit can also apply a concise answer algorithm to a general question. For example, the answer providing unit analyzes a general question and generates a concise answer. The answer providing unit can also apply an optimal answer algorithm depending on the category of the question. For example, the answer providing unit analyzes the category of the question and selects an optimal answer algorithm. In this way, a more appropriate answer can be provided by applying the optimal answer algorithm depending on the category of the question.

[0051] The answer providing unit can determine the priority of answers based on the time when the question was submitted. For example, the answer providing unit determines the priority of answers based on the date and time when the question was submitted. The answer providing unit can also determine the priority of answers based on the time that has elapsed since the question was submitted. For example, the answer providing unit analyzes the time that has elapsed since the question was submitted and determines the optimal priority of answers. In this way, by determining the priority of answers based on the time when the question was submitted, a quick and appropriate response can be made.

[0052] The answer providing unit can adjust the order of answers based on the relevance of the question. For example, the answer providing unit evaluates the relevance of the question and provides the answers in an optimal order. The answer providing unit can also provide an optimal answer based on the relevance of the question. For example, the answer providing unit analyzes the relevance of the question and generates an optimal answer. The answer providing unit can also determine the order of answers based on the relevance of the question. For example, the answer providing unit evaluates the relevance of the question and provides the answers in an optimal order. In this way, by adjusting the order of answers based on the relevance of the question, a more appropriate answer is provided.

[0053] The troubleshooting unit can improve the accuracy of troubleshooting by taking into account the interrelationships between technical problems. For example, the troubleshooting unit analyzes the cause-effect relationship of a technical problem and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the interrelationships between a plurality of technical problems. For example, the troubleshooting unit analyzes the interrelationships between a plurality of problems and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the interrelationships between technical problems. For example, the troubleshooting unit analyzes the interrelationships between technical problems and proposes an optimal solution. In this way, the accuracy of troubleshooting is improved by taking into account the interrelationships between technical problems.

[0054] The troubleshooting unit can perform troubleshooting by taking into consideration attribute information of the person who submitted the problem. The troubleshooting unit provides optimal troubleshooting by taking into consideration attribute information such as the age, sex, occupation, and purchase history of the person who submitted the problem. For example, the troubleshooting unit proposes an optimal solution based on the age of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the sex of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the occupation of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the purchase history of the person who submitted the problem. In this way, more appropriate troubleshooting is provided by taking into consideration attribute information of the person who submitted the problem.

[0055] The troubleshooting unit can perform troubleshooting taking into account the geographical distribution of technical problems. For example, the troubleshooting unit analyzes the region where the technical problem occurs and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the frequency of problems in each region. For example, the troubleshooting unit analyzes the frequency of problems in each region and proposes an optimal solution. The troubleshooting unit can also perform troubleshooting taking into account the geographical distribution of technical problems. For example, the troubleshooting unit analyzes the geographical distribution of technical problems and proposes an optimal solution. In this way, more appropriate troubleshooting is provided by taking into account the geographical distribution of technical problems.

[0056] The troubleshooting unit can improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, the troubleshooting unit can refer to related literature such as technical papers, patent documents, and technical manuals, and propose an optimal solution. The troubleshooting unit can also analyze related literature of the technical problem to improve the accuracy of troubleshooting. For example, the troubleshooting unit can analyze related literature and propose an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, the troubleshooting unit can analyze related literature and propose an optimal solution. As a result, the accuracy of troubleshooting is improved by referring to related literature of the technical problem.

[0057] When providing product information, the product information providing unit can provide optimal information by referring to past data. The product information providing unit, for example, refers to the customer's past purchase history to provide optimal product information. For example, the product information providing unit provides optimal product information based on the customer's past purchase data. The product information providing unit can also provide related product information by referring to the customer's past search history. For example, the product information providing unit provides optimal product information based on the customer's past search data. The product information providing unit can also provide optimal product information by referring to the customer's past feedback. For example, the product information providing unit provides optimal product information based on the customer's past feedback data. In this way, optimal product information can be provided to the customer by referring to past data.

[0058] The product information providing unit can apply different information providing methods for each product category. For example, the product information providing unit provides detailed technical specifications for electronic products. For example, the product information providing unit explains the technical specifications of electronic products in detail. The product information providing unit can also provide detailed information on size and material for clothing items. For example, the product information providing unit explains in detail the size and material information of clothing items. The product information providing unit can also provide detailed information on ingredients and nutrition for food items. For example, the product information providing unit explains in detail the ingredients and nutrition information of food items. In this way, more appropriate product information can be provided to customers by applying the optimal information providing method for each product category.

[0059] When providing product information, the product information providing unit can determine the priority of information based on the submission time of the product. The product information providing unit, for example, provides information on new products preferentially. For example, the product information providing unit determines the priority of information based on the submission date and time of the new product. The product information providing unit can also provide information on seasonal products or limited-time products preferentially. For example, the product information providing unit determines the priority of information based on the submission date and time of the seasonal products or limited-time products. The product information providing unit can also provide information on products in which the customer has shown interest in the past preferentially. For example, the product information providing unit determines the priority of information based on past interest data of the customer. In this way, more appropriate product information can be provided by determining the priority of information based on the submission time of the product.

[0060] When providing product information, the product information providing unit can provide information by referring to related market data. The product information providing unit, for example, refers to market trend data to provide related product information. For example, the product information providing unit provides optimal product information based on market trend data. The product information providing unit can also refer to information on competing products to emphasize points of differentiation. For example, the product information providing unit emphasizes points of differentiation based on data on competing products. The product information providing unit can also refer to market demand data to provide optimal product information. For example, the product information providing unit provides optimal product information based on market demand data. In this way, more appropriate product information can be provided to customers by referring to the related market data.

[0061] When providing order information, the order information providing unit can provide optimal information by referring to past order history. The order information providing unit, for example, refers to the customer's past order history to provide relevant order information. For example, the order information providing unit provides optimal order information based on the customer's past order data. The order information providing unit can also analyze the customer's past order history to provide optimal order information. For example, the order information providing unit analyzes the customer's past order data to provide optimal order information. The order information providing unit can also refer to the customer's past order history to provide optimal order information. For example, the order information providing unit provides optimal order information based on the customer's past order data. In this way, optimal order information can be provided to the customer by referring to the past order history.

[0062] When providing order information, the order information providing unit can provide optimal information by taking into consideration the geographical location information of the customer. The order information providing unit provides optimal order information by taking into consideration, for example, the geographical location information of the customer. For example, the order information providing unit provides optimal order information based on the GPS data of the customer. The order information providing unit can also provide optimal order information based on the IP address of the customer. The order information providing unit can also provide optimal order information based on a location information service for the customer. For example, the order information providing unit analyzes the location information of the customer and provides optimal order information. In this way, more appropriate order information is provided by taking into consideration the geographical location information of the customer.

[0063] At the time of connection, the connection unit can select the most suitable representative by referring to past connection history. For example, the connection unit selects the most suitable representative based on the customer's past connection data. The connection unit can also analyze the customer's past connection history and select the most suitable representative. For example, the connection unit analyzes the customer's past connection data and selects the most suitable representative. The connection unit can also select the most suitable representative by referring to the customer's past connection history. For example, the connection unit selects the most suitable representative based on the customer's past connection data. In this way, the most suitable representative for the customer can be selected by referring to the past connection history.

[0064] At the time of connection, the connection unit can select the most suitable representative by taking into consideration the geographic location information of the customer. For example, the connection unit selects the most suitable representative based on the customer's GPS data. The connection unit can also select the most suitable representative based on the customer's IP address. The connection unit can also select the most suitable representative based on the customer's location information service. For example, the connection unit analyzes the customer's location information and selects the most suitable representative. In this way, a more suitable representative can be selected by taking into consideration the customer's geographic location information.

[0065] When providing related information, the related information providing unit can provide optimal information by referring to past data. For example, the related information providing unit provides optimal related information based on the customer's past search data. The related information providing unit can also provide optimal related information by referring to the customer's past feedback. For example, the related information providing unit provides optimal related information based on the customer's past feedback data. The related information providing unit can also provide optimal related information by referring to the customer's past data. For example, the related information providing unit provides optimal related information based on the customer's past data. This makes it possible to provide optimal related information to the customer by referring to past data.

[0066] When providing related information, the related information providing unit can provide optimal information taking into consideration the geographical location information of the customer. The related information providing unit provides optimal related information, for example, taking into consideration the geographical location information of the customer. For example, the related information providing unit provides optimal related information based on the GPS data of the customer. The related information providing unit can also provide optimal related information based on the IP address of the customer. The related information providing unit can also provide optimal related information based on a location information service for the customer. For example, the related information providing unit analyzes the location information of the customer and provides optimal related information. In this way, more appropriate related information is provided by taking into consideration the geographical location information of the customer.

[0067] The prediction unit can apply an optimal prediction algorithm by referring to past data when making a prediction. The prediction unit can also apply an optimal prediction algorithm by referring to past feedback of the customer. For example, the prediction unit selects an optimal prediction algorithm based on past feedback data of the customer. The prediction unit can also apply an optimal prediction algorithm by referring to past data of the customer. For example, the prediction unit selects an optimal prediction algorithm based on past data of the customer. This enables more accurate prediction by referring to past data.

[0068] When making a prediction, the prediction unit can make an optimal prediction by taking into account the geographic location information of the customer. For example, the prediction unit provides an optimal prediction based on the GPS data of the customer. The prediction unit can also provide an optimal prediction based on the IP address of the customer. The prediction unit can also provide an optimal prediction based on a location information service of the customer. For example, the prediction unit analyzes the location information of the customer and provides an optimal prediction. This allows for more accurate predictions by taking into account the geographic location information of the customer.

[0069] During adjustment, the adjustment unit can perform optimal resource allocation by referring to past data. For example, the adjustment unit determines optimal resource allocation based on past data. The adjustment unit can also perform optimal resource allocation by referring to past feedback. For example, the adjustment unit determines optimal resource allocation based on past feedback data. The adjustment unit can also perform optimal resource allocation by referring to past data. For example, the adjustment unit determines optimal resource allocation based on past data. This enables more appropriate resource allocation by referring to past data.

[0070] During adjustment, the adjustment unit can perform optimal resource allocation by taking into account the geographical location information of the customer. For example, the adjustment unit determines optimal resource allocation based on the GPS data of the customer. The adjustment unit can also perform optimal resource allocation based on the IP address of the customer. The adjustment unit can also perform optimal resource allocation based on a location information service of the customer. For example, the adjustment unit analyzes the location information of the customer and determines optimal resource allocation. In this way, more appropriate resource allocation is possible by taking into account the geographical location information of the customer.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The AI ​​assistant system at the customer support center can further analyze the customer's past inquiry history and select the optimal reception method. For example, it can prioritize and suggest inquiry methods that the customer has frequently used in the past. It can also select the most efficient reception method from the customer's past inquiry history. It can also analyze the customer's past inquiry history and automatically select the optimal reception method. In this way, it is possible to provide the optimal reception method to the customer by analyzing past inquiry history.

[0073] The AI ​​assistant system in the customer support center can further filter inputs based on the customer's current situation and areas of interest. For example, it can filter relevant inputs based on the customer's current location and activity status. It can also filter relevant inputs based on the customer's hobbies and products and services that interest them. It can also analyze the customer's current situation and areas of interest and select the most suitable input. This allows for more relevant responses by filtering inputs based on the customer's current situation and areas of interest.

[0074] The AI ​​assistant system of the customer support center can further take into account the geographic location information of the customer and prioritize relevant input. For example, it can prioritize relevant input based on the customer's current location. It can also filter relevant input based on the customer's GPS data. It can also filter relevant input based on the customer's IP address. This allows for more relevant responses by taking into account the customer's geographic location information.

[0075] The AI ​​assistant system of the customer support center can further analyze the customer's social media activity and accept relevant input. For example, it can analyze the customer's social media activity on X (formerly Twitter), Facebook, Instagram, etc., and prioritize accepting related input. It can also filter the most suitable input based on the customer's social media activity. It can also analyze the customer's social media activity and select the most suitable input. This allows for more relevant responses by analyzing the customer's social media activity.

[0076] The AI ​​assistant system of the customer support center can further take into account the geographic distribution of technical problems when troubleshooting. For example, it can analyze the region where the technical problem occurs and suggest the optimal solution. It can also improve the accuracy of troubleshooting by taking into account the frequency of problems in each region. It can further analyze the geographic distribution of technical problems and suggest the optimal solution. This provides more appropriate troubleshooting by taking into account the geographic distribution of technical problems.

[0077] The AI ​​assistant system of the customer support center can further improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, it can refer to related literature such as technical papers, patent documents, and technical manuals to propose an optimal solution. It can also analyze related literature of the technical problem to improve the accuracy of troubleshooting. It can also analyze related literature and propose an optimal solution. As a result, the accuracy of troubleshooting is improved by referring to related literature of the technical problem.

[0078] The process flow of the first embodiment will be briefly described below.

[0079] Step 1: The reception unit receives input from a customer. Examples of customer input include, but are not limited to, text input, voice input, and image input. The reception unit receives the customer input using a generation AI. The generation AI analyzes the customer input using technologies such as natural language generation, image generation, and voice generation, and performs appropriate processing. Step 2: The answer providing unit generates answers to questions using AI. The AI ​​uses technologies such as natural language processing, machine learning, and deep learning to generate appropriate answers to customer questions. Step 3: The troubleshooting department uses AI to suggest solutions to technical problems or malfunctions. AI uses technologies such as natural language processing, machine learning, and deep learning to suggest appropriate solutions to the customer's technical problems or malfunctions. Step 4: The product information provision unit uses AI to provide product information. The AI ​​uses technologies such as natural language processing, machine learning, and deep learning to provide appropriate product information to customers. Step 5: The order information provider uses blockchain technology to manage order history and delivery status information. The blockchain technology uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage order history and delivery status information. Step 6: If the answer provider is unable to provide an answer, the connection unit connects the customer to a person in charge or department. The connection unit uses AI to select the appropriate person in charge or department and connects the customer.

[0080] (Example 2) The AI ​​assistant system for a customer support center according to an embodiment of the present invention is a system that accepts input from customers, generates answers to questions using a generation AI, proposes solutions to technical problems and malfunctions, provides information on products and services, and provides information on order history and delivery status. This system can quickly and appropriately respond to various inputs from customers. For example, it has an FAQ answering function that quickly answers questions frequently asked by customers, a troubleshooting function that proposes solutions to technical problems and malfunctions, a product information providing function that provides detailed information on products and services, an order information providing function that checks order history and delivery status, a feedback collecting function that collects customer opinions and requests, an escalation support function that escalates to an appropriate person or department to deal with complex problems or specific requests, and a 24-hour support function. As a result, the AI ​​assistant system for a customer support center can quickly and appropriately respond to various needs of customers.

[0081] The AI ​​assistant system of the customer support center according to the embodiment includes a reception unit, an answer providing unit, a troubleshooting unit, a product information providing unit, an order information providing unit, and a connection unit. The reception unit receives input from a customer. The customer input includes, but is not limited to, for example, text input, voice input, and image input. The reception unit receives the customer input using a generation AI. The generation AI analyzes the customer input and performs appropriate processing using, for example, natural language generation, image generation, voice generation, and other technologies. The answer providing unit generates an answer to a question using the AI. The AI ​​generates an appropriate answer to a customer question using, for example, natural language processing, machine learning, deep learning, and other technologies. The troubleshooting unit uses the AI ​​to propose a solution to a technical problem or malfunction. The AI ​​uses, for example, natural language processing, machine learning, deep learning, and other technologies to propose an appropriate solution to a customer's technical problem or malfunction. The product information providing unit provides product information using the AI. The AI ​​provides appropriate product information to the customer using, for example, natural language processing, machine learning, deep learning, and other technologies. The order information providing unit manages information on order history and delivery status using blockchain technology. The blockchain technology uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage information on order history and delivery status. The connection unit connects the customer to a person in charge or department in charge when the answer providing unit cannot provide an answer. The connection unit uses AI to select an appropriate person in charge or department and connects the customer. This allows the customer support center's AI assistant system to quickly and appropriately respond to the diverse needs of customers.

[0082] The reception unit receives input from a customer. Examples of customer input include, but are not limited to, text input, voice input, and image input. The reception unit uses a generation AI to receive customer input. The generation AI analyzes the customer input using technologies such as natural language generation, image generation, and voice generation, and performs appropriate processing. Specifically, in the case of text input, the generation AI analyzes the input content using natural language processing technology and understands the customer's intention. For example, if a customer inputs "I would like to cancel my order," the generation AI accurately grasps the intention and performs appropriate processing to proceed to the next step. In the case of voice input, the generation AI converts voice data into text using voice recognition technology, and then analyzes it using natural language processing technology. For example, if a customer inputs by voice, "Please tell me the details of the product," the generation AI converts the voice into text and understands the intention. In the case of image input, the generation AI analyzes image data using image recognition technology and understands the customer's request. For example, if a customer sends a photo of a defective product, the generation AI analyzes the image and identifies the content of the defect. This allows the reception unit to handle a variety of input formats and accurately grasp the customer's request. Furthermore, the reception department can analyze the contents entered by the customer in real time and move on to the next process quickly, thereby minimizing the waiting time for the customer and providing smooth support.

[0083] The answer providing unit generates answers to questions using AI. For example, AI uses technologies such as natural language processing, machine learning, and deep learning to generate appropriate answers to customer questions. Specifically, it uses natural language processing technology to analyze the content of the customer's question and understand the intent. For example, if a customer asks "Please tell me how to return a product," AI analyzes the question and generates an appropriate answer. It uses machine learning technology to learn data on past questions and answers and provide optimal answers to similar questions. For example, if many customers have asked a similar question in the past, it generates optimal answers based on the answer data. It uses deep learning technology to make it possible to handle complex questions. For example, if a customer asks "Please tell me the features of this product and how it differs from other products," AI analyzes the question with a deep learning model and generates detailed answers. This allows the answer providing unit to quickly and accurately provide answers to various questions from customers. Furthermore, the answer providing unit can evaluate the quality of the generated answers and make corrections as necessary. For example, if the generated answer is inappropriate, the AI ​​reevaluates the answer and generates a more appropriate answer. The answer providing unit can also collect customer feedback and continuously improve the quality of the answers. This allows the answer providing section to consistently provide high quality answers and improve customer satisfaction.

[0084] The troubleshooting department uses AI to propose solutions to technical problems or malfunctions. AI proposes appropriate solutions to customers' technical problems or malfunctions using technologies such as natural language processing, machine learning, and deep learning. Specifically, natural language processing technology is used to analyze the content of the customer's problem and identify its cause. For example, if a customer reports that "Internet connection is unstable," AI analyzes the problem and identifies possible causes. Machine learning technology is used to learn past troubleshooting data and provide optimal solutions to similar problems. For example, if a similar problem has occurred in the past, the optimal solution is proposed based on the solution data. Deep learning technology is used to make it possible to handle complex problems. For example, if a customer reports that "an error occurred during software installation," AI analyzes the problem with a deep learning model and proposes a detailed solution. This allows the troubleshooting department to quickly and accurately provide solutions to various technical problems of customers. In addition, the troubleshooting department can evaluate the effectiveness of the proposed solution and make corrections as necessary. For example, if the proposed solution is not effective, AI reevaluates the solution and proposes a more appropriate solution. In addition, the troubleshooting department can collect customer feedback and continuously improve the quality of the solutions. This enables the troubleshooting department to consistently provide high quality solutions and improve customer satisfaction.

[0085] The product information providing unit uses AI to provide product information. For example, AI uses technologies such as natural language processing, machine learning, and deep learning to provide appropriate product information to customers. Specifically, natural language processing technology is used to analyze the content of the customer's question and understand the intention. For example, if a customer asks, "Please tell me the features of this product," AI analyzes the question and provides appropriate product information. Machine learning technology is used to learn data on past questions and answers, and provide optimal product information for similar questions. For example, if many customers have asked a similar question in the past, optimal product information is provided based on the answer data. Deep learning technology is used to enable response to complex questions. For example, if a customer asks, "Please tell me the features of this product and the difference between it and other products," AI analyzes the question with a deep learning model and provides detailed product information. This allows the product information providing unit to quickly and accurately provide product information in response to various questions from customers. Furthermore, the product information providing unit can evaluate the quality of the provided product information and make corrections as necessary. For example, if the provided product information is inappropriate, AI reevaluates the information and provides more appropriate product information. In addition, the product information providing department can collect customer feedback and continuously improve the quality of the product information, thereby enabling the product information providing department to always provide high-quality product information and increase customer satisfaction.

[0086] The order information providing unit uses blockchain technology to manage information on order history and delivery status. Blockchain technology, for example, uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage information on order history and delivery status. Specifically, a public blockchain is used to make all order histories public and ensure transparency. This allows customers to check their order history at any time. A private blockchain is used to manage information on order history and delivery status within a company and enhance security. This allows companies to safely manage customer order information. A consortium blockchain is used to share information on order history and delivery status among multiple companies and realize efficient logistics management. This allows customers to check in real time what stage their order is at. Furthermore, the order information providing unit uses blockchain technology to record information on order history and delivery status in a form that cannot be tampered with. This allows customers to confirm that their order information is accurate. In addition, the order information providing unit can collect customer feedback and continuously improve the method of managing order information. This allows the order information providing unit to always provide high-quality order information and improve customer satisfaction.

[0087] The connection unit connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. The connection unit uses AI to select an appropriate person in charge or department and connects the customer. Specifically, the AI ​​analyzes the content of the customer's question and the type of problem, and identifies the most suitable person in charge or department. For example, if a customer asks "I would like to know more about returning products," the AI ​​analyzes the question and connects the customer to the returns department. Also, if a customer reports that "a technical problem has occurred," the AI ​​analyzes the problem and connects the customer to a technical support person. This allows the connection unit to respond quickly and appropriately to the diverse needs of customers. Furthermore, the connection unit can check the availability of the person in charge or department in real time to minimize the customer's waiting time, and make the optimal connection. For example, if multiple people are available, the AI ​​selects the person in charge who can respond most quickly and connects the customer. The connection unit can also collect customer feedback and continuously improve the quality of the connection method. This allows the connection unit to always provide high-quality connection services and improve customer satisfaction.

[0088] The answer providing unit can generate answers to questions using AI. The answer providing unit generates answers to customer questions using, for example, natural language processing technology. For example, the answer providing unit analyzes customer questions and generates appropriate answers. The answer providing unit can also generate answers to customer questions using machine learning technology. For example, the answer providing unit learns data on past questions and answers and generates appropriate answers to new questions. The answer providing unit can also generate answers to customer questions using deep learning technology. For example, the answer providing unit learns a large amount of text data and generates appropriate answers to customer questions using an AI model with advanced natural language processing capabilities. As a result, answers to questions can be generated quickly and accurately by using AI.

[0089] The troubleshooting unit can use AI to propose solutions to technical problems or malfunctions. The troubleshooting unit can use, for example, natural language processing technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit analyzes the customer's problem and proposes an appropriate solution. The troubleshooting unit can also use machine learning technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit learns data on past problems and solutions and proposes an appropriate solution to a new problem. The troubleshooting unit can also use deep learning technology to propose solutions to technical problems or malfunctions of customers. For example, the troubleshooting unit learns large amounts of text data and uses an AI model with advanced natural language processing capabilities to propose an appropriate solution to the customer's problem. As a result, solutions to technical problems and malfunctions are quickly and accurately proposed by using AI.

[0090] The order information providing unit can manage the information on the order history and the delivery status using blockchain technology. The order information providing unit can manage the information on the order history and the delivery status using, for example, public blockchain technology. For example, the order information providing unit records the data on the order history and the delivery status on the blockchain and manages it safely and accurately. The order information providing unit can also manage the information on the order history and the delivery status using private blockchain technology. For example, the order information providing unit builds a private blockchain used within a company and manages the data on the order history and the delivery status. The order information providing unit can also manage the information on the order history and the delivery status using consortium blockchain technology. For example, the order information providing unit builds a consortium blockchain in which multiple companies participate, shares the data on the order history and the delivery status, and manages it safely and accurately. As a result, the order history and the delivery status information are managed safely and accurately by using blockchain technology.

[0091] The reception unit can accept the customer's input using the generation AI. The reception unit accepts the customer's input using, for example, natural language generation technology. For example, the reception unit analyzes the customer's text input and performs appropriate processing. The reception unit can also accept the customer's input using image generation technology. For example, the reception unit analyzes the customer's image input and performs appropriate processing. The reception unit can also accept the customer's input using voice generation technology. For example, the reception unit analyzes the customer's voice input and performs appropriate processing. In this way, by using the generation AI, the customer's input can be accepted quickly and accurately.

[0092] The system includes a related information providing unit, which can search and provide at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. The related information providing unit, for example, searches and provides social media posts. For example, the related information providing unit searches social media posts such as X (formerly Twitter), Facebook, and Instagram, and provides information related to the customer's input. The related information providing unit can also search and provide scientific papers. For example, the related information providing unit searches scientific papers such as physics, chemistry, and biology, and provides information related to the customer's input. The related information providing unit can also search and provide technical specifications. For example, the related information providing unit searches technical specifications such as technical specifications, blueprints, and manuals of products, and provides information related to the customer's input. The related information providing unit can also search and provide patent documents. For example, the related information providing unit searches patent documents such as patent numbers, details of inventions, and claims, and provides information related to the customer's input. This allows the customer's questions and problems to be solved more effectively by providing a wide range of information related to the customer's input.

[0093] The reception unit can determine the type of input from the customer based on the attributes of the customer. The reception unit determines the type of input from the customer based on attribute information such as the customer's age, sex, occupation, and purchase history. By determining the type of input based on the attributes of the customer, more appropriate handling is possible.

[0094] The product information providing unit can visually provide product information to the customer by using augmented reality technology. The product information providing unit can visually provide product information to the customer by using, for example, AR glasses. For example, the product information providing unit displays detailed product information through the AR glasses. The product information providing unit can also visually provide product information to the customer by using a smartphone app. For example, the product information providing unit displays detailed product information through a smartphone app. The product information providing unit can also visually provide product information to the customer by using projection mapping technology. For example, the product information providing unit displays detailed product information using projection mapping. In this way, by using augmented reality technology, it is possible to provide product information that is visually easy to understand for the customer.

[0095] The system includes a prediction unit that can analyze a customer's input and predict future inputs using an AI model. The prediction unit can analyze a customer's input and predict future inputs using, for example, a neural network. The prediction unit can also analyze a customer's input and predict future inputs using a support vector machine. For example, the prediction unit predicts future inputs based on the customer's past input data. In this way, by predicting future inputs, countermeasures can be prepared in advance and a quick response can be made.

[0096] The system includes an adjustment unit, which can adjust the allocation of resources to the answer providing unit, the troubleshooting unit, the product information providing unit, the order information providing unit, and the connection unit based on the prediction result by the prediction unit. The adjustment unit adjusts CPU resources, for example. The adjustment unit can also adjust memory resources. For example, the adjustment unit allocates appropriate memory resources to each unit based on the prediction result by the prediction unit. The adjustment unit can also adjust personnel resources. For example, the adjustment unit allocates appropriate personnel resources to each unit based on the prediction result by the prediction unit. This adjusts the resource allocation, thereby improving the efficiency of the entire system.

[0097] The reception unit can estimate the customer's emotions and adjust the timing of input reception based on the estimated customer's emotions. For example, when the customer is feeling stressed, the reception unit allows the generation AI to delay the timing of input reception so that the customer can relax. For example, the reception unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Also, when the customer is in a hurry, the reception unit can allow the generation AI to advance the timing of input reception and respond quickly. For example, the reception unit records the customer's voice and estimates the emotion using a voice analysis technology. Also, when the customer is feeling anxious, the reception unit can allow the generation AI to adjust the timing of input reception so as to give the customer a sense of security. For example, the reception unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. As a result, customer satisfaction is improved by adjusting the timing of input reception according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0098] The reception unit can analyze the customer's past inquiry history and select the optimal reception method. For example, the reception unit preferentially suggests an inquiry method that the customer has frequently used in the past. For example, the reception unit analyzes the customer's past inquiry history and selects the optimal reception method. The reception unit can also select the most efficient reception method from the customer's past inquiry history. For example, the reception unit selects the optimal reception method based on the customer's past inquiry data. The reception unit can also analyze the customer's past inquiry history and automatically select the optimal reception method. For example, the reception unit learns the customer's past inquiry data and suggests the optimal reception method. In this way, the optimal reception method can be provided to the customer by analyzing the past inquiry history.

[0099] The reception unit can filter inputs based on the customer's current situation and areas of interest. The reception unit, for example, preferentially receives inputs that are highly relevant based on the customer's current situation. For example, the reception unit filters relevant inputs based on the customer's current location and activity status. The reception unit can also filter relevant inputs based on the customer's areas of interest. For example, the reception unit filters relevant inputs based on the customer's hobbies and products and services in which the customer is interested. The reception unit can also filter optimal inputs based on the customer's current situation and areas of interest. For example, the reception unit analyzes the customer's current situation and areas of interest and selects optimal inputs. This makes it possible to provide more relevant responses by filtering inputs based on the customer's current situation and areas of interest.

[0100] The reception unit can estimate the customer's emotions and determine the priority of inputs to be received based on the estimated customer's emotions. For example, when the customer is feeling stressed, the reception unit has the generation AI set the priority of the input high and respond quickly. For example, the reception unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Also, when the customer is relaxed, the reception unit can have the generation AI set the priority of the input low and prioritize other important inputs. For example, the reception unit records the customer's voice and estimates the emotion using voice analysis technology. Also, when the customer is feeling anxious, the reception unit can have the generation AI adjust the priority of the inputs to give a sense of security. For example, the reception unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of the inputs according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0101] The reception unit can preferentially receive highly relevant inputs in consideration of the geographical location information of the customer. The reception unit preferentially receives highly relevant inputs, for example, based on the current location of the customer. For example, the reception unit filters relevant inputs based on the GPS data of the customer. The reception unit can also filter relevant inputs based on the IP address of the customer. The reception unit can also filter relevant inputs based on a location information service of the customer. For example, the reception unit analyzes the location information of the customer and selects the most appropriate input. This makes it possible to provide a more relevant response by considering the geographical location information of the customer.

[0102] The reception unit can analyze the social media activity of the customer and receive related input. For example, the reception unit analyzes the social media activity of the customer on X (formerly Twitter), Facebook, Instagram, etc., and filters the related input. The reception unit can also filter optimal input based on the social media activity of the customer. For example, the reception unit analyzes the social media activity of the customer and selects the optimal input. In this way, by analyzing the social media activity of the customer, it becomes possible to provide a more relevant response.

[0103] The answer providing unit can estimate the customer's emotion and adjust the way of expressing the answer based on the estimated emotion of the customer. For example, when the customer is stressed, the answer providing unit provides a concise and easy-to-understand answer. For example, the answer providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, when the customer is relaxed, the answer providing unit can also provide an answer including detailed information. For example, the answer providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the answer providing unit can also provide an answer in an expression method that gives a sense of security. For example, the answer providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. As a result, the way of expressing the answer is adjusted according to the customer's emotion, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0104] The answer providing unit can adjust the level of detail of the answer based on the importance of the question. The answer providing unit provides a detailed answer, for example, to an important question. For example, the answer providing unit generates a detailed answer based on the urgency and scope of impact of the question. The answer providing unit can also provide a concise answer to a general question. For example, the answer providing unit evaluates the importance of the question and generates a concise answer. The answer providing unit can also adjust the level of detail of the answer based on the importance of the question. For example, the answer providing unit analyzes the importance of the question and determines an optimal level of detail of the answer. In this way, a more appropriate answer can be provided by adjusting the level of detail of the answer based on the importance of the question.

[0105] The answer providing unit can apply different answer algorithms depending on the category of the question. For example, the answer providing unit applies a specialized answer algorithm to a technical question. For example, the answer providing unit analyzes a technical question and generates a specialized answer. The answer providing unit can also apply a concise answer algorithm to a general question. For example, the answer providing unit analyzes a general question and generates a concise answer. The answer providing unit can also apply an optimal answer algorithm depending on the category of the question. For example, the answer providing unit analyzes the category of the question and selects an optimal answer algorithm. In this way, a more appropriate answer can be provided by applying the optimal answer algorithm depending on the category of the question.

[0106] The answer providing unit can estimate the customer's emotion and adjust the length of the answer based on the estimated emotion of the customer. For example, when the customer is stressed, the answer providing unit provides a concise answer. For example, the answer providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the answer providing unit can also provide a detailed answer when the customer is relaxed. For example, the answer providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the answer providing unit can also provide an answer of a length that gives a sense of security. For example, the answer providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. Thereby, the length of the answer is adjusted according to the customer's emotion, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0107] The answer providing unit can determine the priority of answers based on the time when the question was submitted. For example, the answer providing unit determines the priority of answers based on the date and time when the question was submitted. The answer providing unit can also determine the priority of answers based on the time that has elapsed since the question was submitted. For example, the answer providing unit analyzes the time that has elapsed since the question was submitted and determines the optimal priority of answers. In this way, by determining the priority of answers based on the time when the question was submitted, a quick and appropriate response can be made.

[0108] The answer providing unit can adjust the order of answers based on the relevance of the question. For example, the answer providing unit evaluates the relevance of the question and provides the answers in an optimal order. The answer providing unit can also provide an optimal answer based on the relevance of the question. For example, the answer providing unit analyzes the relevance of the question and generates an optimal answer. The answer providing unit can also determine the order of answers based on the relevance of the question. For example, the answer providing unit evaluates the relevance of the question and provides the answers in an optimal order. In this way, by adjusting the order of answers based on the relevance of the question, a more appropriate answer is provided.

[0109] The troubleshooting unit can estimate the customer's emotions and adjust the troubleshooting criteria based on the estimated customer's emotions. For example, when the customer is stressed, the troubleshooting unit provides concise and easy-to-understand troubleshooting. For example, the troubleshooting unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Also, when the customer is relaxed, the troubleshooting unit can provide detailed troubleshooting. For example, the troubleshooting unit records the customer's voice and estimates the emotion using a voice analysis technology. Also, when the customer is anxious, the troubleshooting unit can provide troubleshooting that gives a sense of security. For example, the troubleshooting unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. Thereby, customer satisfaction is improved by adjusting the troubleshooting criteria according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0110] The troubleshooting unit can improve the accuracy of troubleshooting by taking into account the interrelationships between technical problems. For example, the troubleshooting unit analyzes the cause-effect relationship of a technical problem and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the interrelationships between a plurality of technical problems. For example, the troubleshooting unit analyzes the interrelationships between a plurality of problems and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the interrelationships between technical problems. For example, the troubleshooting unit analyzes the interrelationships between technical problems and proposes an optimal solution. In this way, the accuracy of troubleshooting is improved by taking into account the interrelationships between technical problems.

[0111] The troubleshooting unit can perform troubleshooting by taking into consideration attribute information of the person who submitted the problem. The troubleshooting unit provides optimal troubleshooting by taking into consideration attribute information such as the age, sex, occupation, and purchase history of the person who submitted the problem. For example, the troubleshooting unit proposes an optimal solution based on the age of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the sex of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the occupation of the person who submitted the problem. The troubleshooting unit can also propose an optimal solution based on the purchase history of the person who submitted the problem. In this way, more appropriate troubleshooting is provided by taking into consideration attribute information of the person who submitted the problem.

[0112] The troubleshooting unit can estimate the customer's emotions and adjust the order of displaying troubleshooting results based on the estimated customer's emotions. For example, when the customer is stressed, the troubleshooting unit preferentially displays concise and easy-to-understand results. For example, the troubleshooting unit captures the customer's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. In addition, the troubleshooting unit can also preferentially display detailed results when the customer is relaxed. For example, the troubleshooting unit records the customer's voice and estimates the emotions using a voice analysis technology. In addition, when the customer is anxious, the troubleshooting unit can also preferentially display results that give a sense of security. For example, the troubleshooting unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotions using an emotion estimation algorithm. As a result, the order of displaying troubleshooting results according to the customer's emotions is adjusted, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0113] The troubleshooting unit can perform troubleshooting taking into account the geographical distribution of technical problems. For example, the troubleshooting unit analyzes the region where the technical problem occurs and proposes an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by taking into account the frequency of problems in each region. For example, the troubleshooting unit analyzes the frequency of problems in each region and proposes an optimal solution. The troubleshooting unit can also perform troubleshooting taking into account the geographical distribution of technical problems. For example, the troubleshooting unit analyzes the geographical distribution of technical problems and proposes an optimal solution. In this way, more appropriate troubleshooting is provided by taking into account the geographical distribution of technical problems.

[0114] The troubleshooting unit can improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, the troubleshooting unit can refer to related literature such as technical papers, patent documents, and technical manuals, and propose an optimal solution. The troubleshooting unit can also analyze related literature of the technical problem to improve the accuracy of troubleshooting. For example, the troubleshooting unit can analyze related literature and propose an optimal solution. The troubleshooting unit can also improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, the troubleshooting unit can analyze related literature and propose an optimal solution. As a result, the accuracy of troubleshooting is improved by referring to related literature of the technical problem.

[0115] The product information providing unit can estimate the customer's emotion and adjust the display method of the product information based on the estimated customer's emotion. For example, when the customer is stressed, the product information providing unit provides concise and easy-to-understand product information. For example, the product information providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, when the customer is relaxed, the product information providing unit can also provide detailed product information. For example, the product information providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the product information providing unit can also provide product information that gives a sense of security. For example, the product information providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. As a result, the display method of the product information is adjusted according to the customer's emotion, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0116] When providing product information, the product information providing unit can provide optimal information by referring to past data. The product information providing unit, for example, refers to the customer's past purchase history to provide optimal product information. For example, the product information providing unit provides optimal product information based on the customer's past purchase data. The product information providing unit can also provide related product information by referring to the customer's past search history. For example, the product information providing unit provides optimal product information based on the customer's past search data. The product information providing unit can also provide optimal product information by referring to the customer's past feedback. For example, the product information providing unit provides optimal product information based on the customer's past feedback data. In this way, optimal product information can be provided to the customer by referring to past data.

[0117] The product information providing unit can apply different information providing methods for each product category. For example, the product information providing unit provides detailed technical specifications for electronic products. For example, the product information providing unit explains the technical specifications of electronic products in detail. The product information providing unit can also provide detailed information on size and material for clothing items. For example, the product information providing unit explains in detail the size and material information of clothing items. The product information providing unit can also provide detailed information on ingredients and nutrition for food items. For example, the product information providing unit explains in detail the ingredients and nutrition information of food items. In this way, more appropriate product information can be provided to customers by applying the optimal information providing method for each product category.

[0118] The product information providing unit can estimate the customer's emotion and adjust the importance of the product information based on the estimated customer's emotion. For example, when the customer is stressed, the product information providing unit provides important product information preferentially. For example, the product information providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the product information providing unit can provide detailed product information when the customer is relaxed. For example, the product information providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the product information providing unit can provide product information that gives a sense of security. For example, the product information providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. As a result, the importance of the product information is adjusted according to the customer's emotion, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0119] When providing product information, the product information providing unit can determine the priority of information based on the submission time of the product. The product information providing unit, for example, provides information on new products preferentially. For example, the product information providing unit determines the priority of information based on the submission date and time of the new product. The product information providing unit can also provide information on seasonal products or limited-time products preferentially. For example, the product information providing unit determines the priority of information based on the submission date and time of the seasonal products or limited-time products. The product information providing unit can also provide information on products in which the customer has shown interest in the past preferentially. For example, the product information providing unit determines the priority of information based on past interest data of the customer. In this way, more appropriate product information can be provided by determining the priority of information based on the submission time of the product.

[0120] When providing product information, the product information providing unit can provide information by referring to related market data. The product information providing unit, for example, refers to market trend data to provide related product information. For example, the product information providing unit provides optimal product information based on market trend data. The product information providing unit can also refer to information on competing products to emphasize points of differentiation. For example, the product information providing unit emphasizes points of differentiation based on data on competing products. The product information providing unit can also refer to market demand data to provide optimal product information. For example, the product information providing unit provides optimal product information based on market demand data. In this way, more appropriate product information can be provided to customers by referring to the related market data.

[0121] The order information providing unit can estimate the customer's emotion and adjust the display method of the order information based on the estimated emotion of the customer. For example, when the customer is stressed, the order information providing unit provides concise and easy-to-understand order information. For example, the order information providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the order information providing unit can provide detailed order information when the customer is relaxed. For example, the order information providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the order information providing unit can provide order information that gives a sense of security. For example, the order information providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This improves customer satisfaction by adjusting the display method of the order information according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0122] When providing order information, the order information providing unit can provide optimal information by referring to past order history. The order information providing unit, for example, refers to the customer's past order history to provide relevant order information. For example, the order information providing unit provides optimal order information based on the customer's past order data. The order information providing unit can also analyze the customer's past order history to provide optimal order information. For example, the order information providing unit analyzes the customer's past order data to provide optimal order information. The order information providing unit can also refer to the customer's past order history to provide optimal order information. For example, the order information providing unit provides optimal order information based on the customer's past order data. In this way, optimal order information can be provided to the customer by referring to the past order history.

[0123] The order information providing unit can estimate the customer's emotions and determine the priority of the order information based on the estimated customer's emotions. For example, when the customer is stressed, the order information providing unit provides important order information with priority. For example, the order information providing unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the order information providing unit can provide detailed order information when the customer is relaxed. For example, the order information providing unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, the order information providing unit can provide order information that gives a sense of security when the customer is anxious. For example, the order information providing unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of the order information according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0124] When providing order information, the order information providing unit can provide optimal information by taking into consideration the geographical location information of the customer. The order information providing unit provides optimal order information by taking into consideration, for example, the geographical location information of the customer. For example, the order information providing unit provides optimal order information based on the GPS data of the customer. The order information providing unit can also provide optimal order information based on the IP address of the customer. The order information providing unit can also provide optimal order information based on a location information service for the customer. For example, the order information providing unit analyzes the location information of the customer and provides optimal order information. In this way, more appropriate order information is provided by taking into consideration the geographical location information of the customer.

[0125] The connection unit can estimate the emotion of the customer and adjust the timing of the connection based on the estimated emotion of the customer. For example, when the customer is stressed, the connection unit quickly establishes the connection. For example, the connection unit captures the facial expression of the customer with a camera and estimates the emotion using an emotion estimation algorithm. In addition, when the customer is relaxed, the connection unit can also establish the connection at an appropriate timing. For example, the connection unit records the voice of the customer and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the connection unit can also establish the connection at a timing that gives the customer a sense of security. For example, the connection unit collects the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. Thereby, the timing of the connection is adjusted according to the emotion of the customer, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0126] At the time of connection, the connection unit can select the most suitable representative by referring to past connection history. For example, the connection unit selects the most suitable representative based on the customer's past connection data. The connection unit can also analyze the customer's past connection history and select the most suitable representative. For example, the connection unit analyzes the customer's past connection data and selects the most suitable representative. The connection unit can also select the most suitable representative by referring to the customer's past connection history. For example, the connection unit selects the most suitable representative based on the customer's past connection data. In this way, the most suitable representative for the customer can be selected by referring to the past connection history.

[0127] The connection unit can estimate the emotion of the customer and determine the priority of the connection based on the estimated emotion of the customer. For example, when the customer is stressed, the connection unit prioritizes the connection. For example, the connection unit captures the facial expression of the customer with a camera and estimates the emotion using an emotion estimation algorithm. In addition, when the customer is relaxed, the connection unit can also perform the connection with an appropriate priority. For example, the connection unit records the voice of the customer and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the connection unit can perform the connection with a priority that gives a sense of security. For example, the connection unit collects the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of the connection according to the emotion of the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0128] At the time of connection, the connection unit can select the most suitable representative by taking into consideration the geographic location information of the customer. For example, the connection unit selects the most suitable representative based on the customer's GPS data. The connection unit can also select the most suitable representative based on the customer's IP address. The connection unit can also select the most suitable representative based on the customer's location information service. For example, the connection unit analyzes the customer's location information and selects the most suitable representative. In this way, a more suitable representative can be selected by taking into consideration the customer's geographic location information.

[0129] The related information providing unit can estimate the emotion of the customer and adjust the display method of the related information based on the estimated emotion of the customer. For example, when the customer is stressed, the related information providing unit provides concise and easy-to-understand related information. For example, the related information providing unit captures the facial expression of the customer with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the related information providing unit can provide detailed related information when the customer is relaxed. For example, the related information providing unit records the voice of the customer and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the related information providing unit can provide related information that gives a sense of security. For example, the related information providing unit collects the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. As a result, the display method of the related information is adjusted according to the emotion of the customer, thereby improving customer satisfaction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0130] When providing related information, the related information providing unit can provide optimal information by referring to past data. For example, the related information providing unit provides optimal related information based on the customer's past search data. The related information providing unit can also provide optimal related information by referring to the customer's past feedback. For example, the related information providing unit provides optimal related information based on the customer's past feedback data. The related information providing unit can also provide optimal related information by referring to the customer's past data. For example, the related information providing unit provides optimal related information based on the customer's past data. This makes it possible to provide optimal related information to the customer by referring to past data.

[0131] The related information providing unit can estimate the emotion of the customer and determine the priority of related information based on the estimated emotion of the customer. For example, when the customer is stressed, the related information providing unit provides important related information with priority. For example, the related information providing unit captures the facial expression of the customer with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the related information providing unit can provide detailed related information when the customer is relaxed. For example, the related information providing unit records the voice of the customer and estimates the emotion using a voice analysis technology. In addition, the related information providing unit can provide related information that gives a sense of security when the customer is anxious. For example, the related information providing unit collects the biometric data of the customer (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of related information according to the emotion of the customer. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0132] When providing related information, the related information providing unit can provide optimal information taking into consideration the geographical location information of the customer. The related information providing unit provides optimal related information, for example, taking into consideration the geographical location information of the customer. For example, the related information providing unit provides optimal related information based on the GPS data of the customer. The related information providing unit can also provide optimal related information based on the IP address of the customer. The related information providing unit can also provide optimal related information based on a location information service for the customer. For example, the related information providing unit analyzes the location information of the customer and provides optimal related information. In this way, more appropriate related information is provided by taking into consideration the geographical location information of the customer.

[0133] The prediction unit can estimate the customer's emotion and adjust the accuracy of the prediction based on the estimated emotion of the customer. For example, when the customer is stressed, the prediction unit provides a highly accurate prediction. For example, the prediction unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the prediction unit can also provide a detailed prediction when the customer is relaxed. For example, the prediction unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the prediction unit can provide a prediction that gives a sense of security. For example, the prediction unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This allows for more accurate prediction by adjusting the accuracy of the prediction according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0134] The prediction unit can apply an optimal prediction algorithm by referring to past data when making a prediction. The prediction unit can also apply an optimal prediction algorithm by referring to past feedback of the customer. For example, the prediction unit selects an optimal prediction algorithm based on past feedback data of the customer. The prediction unit can also apply an optimal prediction algorithm by referring to past data of the customer. For example, the prediction unit selects an optimal prediction algorithm based on past data of the customer. This enables more accurate prediction by referring to past data.

[0135] The prediction unit can estimate the customer's emotions and determine the priority of predictions based on the estimated customer's emotions. For example, when the customer is stressed, the prediction unit provides important predictions with priority. For example, the prediction unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The prediction unit can also provide detailed predictions when the customer is relaxed. For example, the prediction unit records the customer's voice and estimates the emotion using a voice analysis technology. The prediction unit can also provide predictions that give a sense of security when the customer is anxious. For example, the prediction unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of predictions according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0136] When making a prediction, the prediction unit can make an optimal prediction by taking into account the geographic location information of the customer. For example, the prediction unit provides an optimal prediction based on the GPS data of the customer. The prediction unit can also provide an optimal prediction based on the IP address of the customer. The prediction unit can also provide an optimal prediction based on a location information service of the customer. For example, the prediction unit analyzes the location information of the customer and provides an optimal prediction. This allows for more accurate predictions by taking into account the geographic location information of the customer.

[0137] The adjustment unit can estimate the customer's emotion and adjust resource allocation based on the estimated customer's emotion. For example, when the customer is stressed, the adjustment unit preferentially allocates resources to quickly respond. For example, the adjustment unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the adjustment unit can also allocate appropriate resources when the customer is relaxed. For example, the adjustment unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is anxious, the adjustment unit can adjust resources to give a sense of security. For example, the adjustment unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. Thereby, customer satisfaction is improved by adjusting the resource allocation according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0138] During adjustment, the adjustment unit can perform optimal resource allocation by referring to past data. For example, the adjustment unit determines optimal resource allocation based on past data. The adjustment unit can also perform optimal resource allocation by referring to past feedback. For example, the adjustment unit determines optimal resource allocation based on past feedback data. The adjustment unit can also perform optimal resource allocation by referring to past data. For example, the adjustment unit determines optimal resource allocation based on past data. This enables more appropriate resource allocation by referring to past data.

[0139] The adjustment unit can estimate the customer's emotion and determine the priority of resources based on the estimated emotion of the customer. For example, when the customer is feeling stressed, the adjustment unit preferentially allocates important resources. For example, the adjustment unit captures the customer's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. In addition, the adjustment unit can also allocate appropriate resources when the customer is relaxed. For example, the adjustment unit records the customer's voice and estimates the emotion using a voice analysis technology. In addition, when the customer is feeling anxious, the adjustment unit can adjust resources to give a sense of security. For example, the adjustment unit collects the customer's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This enables a quick and appropriate response by determining the priority of resources according to the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0140] During adjustment, the adjustment unit can perform optimal resource allocation by taking into account the geographical location information of the customer. For example, the adjustment unit determines optimal resource allocation based on the GPS data of the customer. The adjustment unit can also perform optimal resource allocation based on the IP address of the customer. The adjustment unit can also perform optimal resource allocation based on a location information service of the customer. For example, the adjustment unit analyzes the location information of the customer and determines optimal resource allocation. In this way, more appropriate resource allocation is possible by taking into account the geographical location information of the customer.

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

[0142] The AI ​​assistant system at the customer support center can further estimate the customer's emotions and adjust the way the answer is expressed based on the estimated emotions. For example, if the customer is stressed, it can provide a concise and easy-to-understand answer. If the customer is relaxed, it can provide an answer with detailed information. Furthermore, if the customer is anxious, it can provide an answer in a way that gives a sense of security. This improves customer satisfaction by adjusting the way the answer is expressed depending on the customer's emotions.

[0143] The AI ​​assistant system at the customer support center can further analyze the customer's past inquiry history and select the optimal reception method. For example, it can prioritize and suggest inquiry methods that the customer has frequently used in the past. It can also select the most efficient reception method from the customer's past inquiry history. It can also analyze the customer's past inquiry history and automatically select the optimal reception method. In this way, it is possible to provide the optimal reception method to the customer by analyzing past inquiry history.

[0144] The AI ​​assistant system in the customer support center can further filter inputs based on the customer's current situation and areas of interest. For example, it can filter relevant inputs based on the customer's current location and activity status. It can also filter relevant inputs based on the customer's hobbies and products and services that interest them. It can also analyze the customer's current situation and areas of interest and select the most suitable input. This allows for more relevant responses by filtering inputs based on the customer's current situation and areas of interest.

[0145] The AI ​​assistant system at the customer support center can further estimate the customer's emotions and prioritize the inputs to be received based on the estimated emotions. For example, if the customer is feeling stressed, the priority of the input can be set high to respond quickly. Also, if the customer is relaxed, the priority of the input can be set low to prioritize other important inputs. Furthermore, if the customer is feeling anxious, the priority of the input can be adjusted to give the customer a sense of security. In this way, by prioritizing the inputs according to the customer's emotions, it is possible to respond quickly and appropriately.

[0146] The AI ​​assistant system of the customer support center can further take into account the geographic location information of the customer and prioritize relevant input. For example, it can prioritize relevant input based on the customer's current location. It can also filter relevant input based on the customer's GPS data. It can also filter relevant input based on the customer's IP address. This allows for more relevant responses by taking into account the customer's geographic location information.

[0147] The AI ​​assistant system of the customer support center can further analyze the customer's social media activity and accept relevant input. For example, it can analyze the customer's social media activity on X (formerly Twitter), Facebook, Instagram, etc., and prioritize accepting related input. It can also filter the most suitable input based on the customer's social media activity. It can also analyze the customer's social media activity and select the most suitable input. This allows for more relevant responses by analyzing the customer's social media activity.

[0148] The AI ​​assistant system in the customer support center can further estimate the customer's emotions and adjust the troubleshooting criteria based on the estimated emotions. For example, if the customer is stressed, it can provide concise and easy-to-understand troubleshooting. If the customer is relaxed, it can provide detailed troubleshooting. Furthermore, if the customer is anxious, it can provide reassuring troubleshooting. This improves customer satisfaction by adjusting the troubleshooting criteria according to the customer's emotions.

[0149] The AI ​​assistant system of the customer support center can further take into account the geographic distribution of technical problems when troubleshooting. For example, it can analyze the region where the technical problem occurs and suggest the optimal solution. It can also improve the accuracy of troubleshooting by taking into account the frequency of problems in each region. It can further analyze the geographic distribution of technical problems and suggest the optimal solution. This provides more appropriate troubleshooting by taking into account the geographic distribution of technical problems.

[0150] The AI ​​assistant system of the customer support center can further improve the accuracy of troubleshooting by referring to related literature of the technical problem. For example, it can refer to related literature such as technical papers, patent documents, and technical manuals to propose an optimal solution. It can also analyze related literature of the technical problem to improve the accuracy of troubleshooting. It can also analyze related literature and propose an optimal solution. As a result, the accuracy of troubleshooting is improved by referring to related literature of the technical problem.

[0151] The AI ​​assistant system at the customer support center can further estimate the customer's emotions and adjust the way product information is displayed based on the estimated emotions. For example, if a customer is feeling stressed, concise and easy-to-understand product information can be provided. If the customer is feeling relaxed, detailed product information can be provided. Furthermore, if the customer is feeling anxious, product information that gives a sense of security can be provided. In this way, customer satisfaction can be improved by adjusting the way product information is displayed according to the customer's emotions.

[0152] The process flow of the second embodiment will be briefly described below.

[0153] Step 1: The reception unit receives input from a customer. Examples of customer input include, but are not limited to, text input, voice input, and image input. The reception unit receives the customer input using a generation AI. The generation AI analyzes the customer input using technologies such as natural language generation, image generation, and voice generation, and performs appropriate processing. Step 2: The answer providing unit generates answers to questions using AI. The AI ​​uses technologies such as natural language processing, machine learning, and deep learning to generate appropriate answers to customer questions. Step 3: The troubleshooting department uses AI to suggest solutions to technical problems or malfunctions. AI uses technologies such as natural language processing, machine learning, and deep learning to suggest appropriate solutions to the customer's technical problems or malfunctions. Step 4: The product information provision unit uses AI to provide product information. The AI ​​uses technologies such as natural language processing, machine learning, and deep learning to provide appropriate product information to customers. Step 5: The order information provider uses blockchain technology to manage order history and delivery status information. The blockchain technology uses technologies such as public blockchain, private blockchain, and consortium blockchain to safely and accurately manage order history and delivery status information. Step 6: If the answer provider is unable to provide an answer, the connection unit connects the customer to a person in charge or department. The connection unit uses AI to select the appropriate person in charge or department and connects the customer.

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

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

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

[0157] For example, the reception unit receives input from a customer using the reception device 38 of the smart device 14 or the communication I / F 26 of the data processing device 12. For example, the answer providing unit is realized by the specific processing unit 290 of the data processing device 12 and generates answers to questions using AI. For example, the troubleshooting unit is realized by the specific processing unit 290 of the data processing device 12 and proposes solutions to technical problems and malfunctions. For example, the product information providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides product information. For example, the order information providing unit is realized by the specific processing unit 290 of the data processing device 12 and manages information on order history and delivery status using blockchain technology. For example, the connection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. For example, the related information providing unit is realized by the specific processing unit 290 of the data processing device 12 and searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. For example, the prediction unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the customer's input, and predicts future input using an AI model. For example, the adjustment unit is realized by the specific processing unit 290 of the data processing device 12, and adjusts the allocation of resources of the answer providing unit, troubleshooting unit, product information providing unit, order information providing unit, and connection unit based on the prediction result by the prediction unit. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

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

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

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

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

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

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

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

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

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

[0168] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

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

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0173] For example, the reception unit accepts input from a customer using the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. For example, the answer providing unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer to a question using AI. For example, the troubleshooting unit is realized by the specific processing unit 290 of the data processing device 12 and proposes solutions to technical problems and malfunctions. For example, the product information providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides product information. For example, the order information providing unit is realized by the specific processing unit 290 of the data processing device 12 and manages order history and delivery status information using blockchain technology. For example, the connection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. For example, the related information providing unit is realized by the specific processing unit 290 of the data processing device 12 and searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. For example, the prediction unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the customer's input, and predicts future input using an AI model. For example, the adjustment unit is realized by the specific processing unit 290 of the data processing device 12, and adjusts the allocation of resources of the answer providing unit, troubleshooting unit, product information providing unit, order information providing unit, and connection unit based on the prediction result by the prediction unit. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

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

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

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

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

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

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

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

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

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

[0184] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

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

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0189] For example, the reception unit receives input from a customer using the microphone 238 of the headset terminal 314 or the communication I / F 26 of the data processing device 12. For example, the answer providing unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer to a question using AI. For example, the troubleshooting unit is realized by the specific processing unit 290 of the data processing device 12 and proposes solutions to technical problems and malfunctions. For example, the product information providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides product information. For example, the order information providing unit is realized by the specific processing unit 290 of the data processing device 12 and manages information on order history and delivery status using blockchain technology. For example, the connection unit is realized by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. For example, the related information providing unit is realized by the specific processing unit 290 of the data processing device 12, and searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. For example, the prediction unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the customer's input and predicts future inputs using an AI model. For example, the adjustment unit is realized by the specific processing unit 290 of the data processing device 12, and adjusts the allocation of resources of the answer providing unit, troubleshooting unit, product information providing unit, order information providing unit, and connection unit based on the prediction result by the prediction unit. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0191] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

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

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

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

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

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

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

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

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

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

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

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

[0204] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

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

[0206] For example, the reception unit accepts input from a customer using the microphone 238 of the robot 414 or the communication I / F 26 of the data processing device 12. For example, the answer providing unit is realized by the specific processing unit 290 of the data processing device 12, and generates an answer to a question using AI. For example, the troubleshooting unit is realized by the specific processing unit 290 of the data processing device 12, and proposes solutions to technical problems and malfunctions. For example, the product information providing unit is realized by the specific processing unit 290 of the data processing device 12, and provides product information. For example, the order information providing unit is realized by the specific processing unit 290 of the data processing device 12, and manages information on order history and delivery status using blockchain technology. For example, the connection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. For example, the related information providing unit is realized by the specific processing unit 290 of the data processing device 12, and searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input. For example, the prediction unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the customer's input, and predicts future input using an AI model. For example, the adjustment unit is realized by the specific processing unit 290 of the data processing device 12, and adjusts the allocation of resources of the answer providing unit, troubleshooting unit, product information providing unit, order information providing unit, and connection unit based on the prediction result by the prediction unit. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

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

[0208] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

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

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

[0211] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0212] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

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

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

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

[0216] In addition, 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 upon request from the data processing device 12.

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

[0218] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

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

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

[0221] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

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

[0223] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

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

[0225] (Appendix 1) A reception unit that receives input from a customer; an answer providing unit that, when the type of the input from the customer is a question about a product, generates an answer to the question and provides the generated answer to the customer; a troubleshooting unit that, when the type of the customer's input is a technical problem or defect of a product, proposes a solution to the technical problem or defect to the customer; a product information providing unit that provides product information to the customer when the type of the input from the customer is product information; an order information providing unit that provides information on the order history and delivery status of the product to the customer when the type of the customer's input is a product order; A connection unit that connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. A system characterized by: (Appendix 2) The answer providing unit is Generate the answers to the questions using AI 2. The system of claim 1, (Appendix 3) The troubleshooting unit includes: Using AI to propose solutions to the technical problems or malfunctions 2. The system of claim 1, (Appendix 4) The order information providing unit: Manage order history and delivery status information using blockchain technology 2. The system of claim 1, (Appendix 5) The reception unit is Accepting the customer's input using a generation AI 2. The system of claim 1, (Appendix 6) Equipped with a related information provision department, The related information providing unit searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer input. 2. The system of claim 1, (Appendix 7) The reception unit is Determining a type of input for the customer based on attributes of the customer 2. The system of claim 1, (Appendix 8) The product information providing unit includes: Using augmented reality technology to provide visual product information to the customer 2. The system of claim 1, (Appendix 9) A prediction unit is provided, The prediction unit analyzes the customer's input and predicts future inputs using an AI model. 2. The system of claim 1, (Appendix 10) Equipped with an adjustment unit, The adjustment unit adjusts allocation of resources to each of the answer providing unit, the troubleshooting unit, the product information providing unit, the order information providing unit, and the connection unit based on a result of the prediction by the prediction unit. 2. The system of claim 1, (Appendix 11) The reception unit is Estimate customer sentiment and adjust input acceptance timing based on the estimated customer sentiment 2. The system of claim 1, (Appendix 12) The reception unit is Analyze the customer's past inquiry history and select the optimal reception method 2. The system of claim 1, (Appendix 13) The reception unit is Filter input based on the customer's current situation or interests 2. The system of claim 1, (Appendix 14) The reception unit is Infer customer sentiment and prioritize incoming inputs based on the inferred sentiment 2. The system of claim 1, (Appendix 15) The reception unit is Prioritize relevant input by taking into account the customer's geographic location 2. The system of claim 1, (Appendix 16) The reception unit is Analyze your customers' social media activity and receive relevant input 2. The system of claim 1, (Appendix 17) The answer providing unit is Infer customer sentiment and adjust the wording of your answers based on the inferred customer sentiment 2. The system of claim 1, (Appendix 18) The answer providing unit is Adjust the detail of your answer based on the importance of the question 2. The system of claim 1, (Appendix 19) The answer providing unit is Apply different answering algorithms depending on the question category 2. The system of claim 1, (Appendix 20) The answer providing unit is Estimate customer sentiment and adjust the length of answers based on the estimated customer sentiment 2. The system of claim 1, (Appendix 21) The answer providing unit is Prioritize answers based on when a question was submitted 2. The system of claim 1, (Appendix 22) The answer providing unit is Adjust the order of answers based on the relevance of the question 2. The system of claim 1, (Appendix 23) The troubleshooting unit includes: Estimate customer sentiment and adjust troubleshooting measures based on estimated customer sentiment 2. The system of claim 1, (Appendix 24) The troubleshooting unit includes: Improve troubleshooting by considering the correlation of technical issues 2. The system of claim 1, (Appendix 25) The troubleshooting unit includes: Troubleshoot issues by considering the submitter's profile information 2. The system of claim 1, (Appendix 26) The troubleshooting unit includes: Infer customer sentiment and adjust the order in which troubleshooting results are displayed based on the inferred customer sentiment 2. The system of claim 1, (Appendix 27) The troubleshooting unit includes: Troubleshoot technical issues geographically 2. The system of claim 1, (Appendix 28) The troubleshooting unit includes: Improve troubleshooting by referencing relevant literature for technical issues 2. The system of claim 1, (Appendix 29) The product information providing unit includes: Infer customer sentiment and adjust how product information is displayed based on the inferred customer sentiment 2. The system of claim 1, (Appendix 30) The product information providing unit includes: When providing product information, provide optimal information by referring to past data 2. The system of claim 1, (Appendix 31) The product information providing unit includes: Apply different information presentation methods to different product categories 2. The system of claim 1, (Appendix 32) The product information providing unit includes: Estimate customer sentiment and adjust the importance of product information based on the estimated customer sentiment 2. The system of claim 1, (Appendix 33) The product information providing unit includes: When providing product information, we will prioritize the information based on when the product was submitted 2. The system of claim 1, (Appendix 34) The product information providing unit includes: When providing product information, provide information by referring to relevant market data 2. The system of claim 1, (Appendix 35) The order information providing unit: Infer customer sentiment and adjust how order information is displayed based on the inferred customer sentiment 2. The system of claim 1, (Appendix 36) The order information providing unit: When providing order information, provide optimal information by referring to past order history 2. The system of claim 1, (Appendix 37) The order information providing unit: Estimate customer sentiment and prioritize order information based on estimated customer sentiment 2. The system of claim 1, (Appendix 38) The order information providing unit: When providing order information, provide optimal information by considering the customer's geographic location 2. The system of claim 1, (Appendix 39) The connection portion is Estimate customer sentiment and time connections based on estimated customer sentiment 2. The system of claim 1, (Appendix 40) The connection portion is When connecting, refer to past connection history to select the most suitable person 2. The system of claim 1, (Appendix 41) The connection portion is Estimate customer sentiment and prioritize connections based on the estimated customer sentiment 2. The system of claim 1, (Appendix 42) The connection portion is When connecting, the most suitable agent is selected based on the customer's geographic location 2. The system of claim 1, (Appendix 43) The related information providing unit is Infer customer sentiment and tailor how relevant information is presented based on the inferred customer sentiment 2. The system of claim 1, (Appendix 44) The related information providing unit is When providing related information, provide optimal information by referencing past data 2. The system of claim 1, (Appendix 45) The related information providing unit is Estimate customer sentiment and prioritize relevant information based on the estimated customer sentiment 2. The system of claim 1, (Appendix 46) The related information providing unit is When providing relevant information, provide optimal information by considering the customer's geographic location 2. The system of claim 1, (Appendix 47) The prediction unit is Estimate customer sentiment and adjust prediction accuracy based on estimated customer sentiment 2. The system of claim 1, (Appendix 48) The prediction unit is When making predictions, look at past data to apply the best predictive algorithm 2. The system of claim 1, (Appendix 49) The prediction unit is Estimate customer sentiment and prioritize predictions based on estimated customer sentiment 2. The system of claim 1, (Appendix 50) The prediction unit is During forecasting, the geographic location of the customer is taken into account to make optimal predictions 2. The system of claim 1, (Appendix 51) The adjustment unit is Infer customer sentiment and adjust resource allocation based on inferred customer sentiment 2. The system of claim 1, (Appendix 52) The adjustment unit is When making adjustments, refer to past data to optimize resource allocation 2. The system of claim 1, (Appendix 53) The adjustment unit is Estimate customer sentiment and prioritize resources based on estimated customer sentiment 2. The system of claim 1, (Appendix 54) The adjustment unit is During coordination, consider the geographic location of the customer to optimize resource allocation 2. The system of claim 1, [Explanation of symbols]

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

Claims

1. A reception unit that receives input from a customer; an answer providing unit that, when the type of the input from the customer is a question about a product, generates an answer to the question and provides the generated answer to the customer; a troubleshooting unit that, when the type of the customer's input is a technical problem or defect of a product, suggests a solution to the technical problem or defect to the customer; a product information providing unit that provides product information to the customer when the type of the input from the customer is product information; an order information providing unit that provides information on the order history and delivery status of the product to the customer when the type of the customer's input is a product order; A connection unit that connects the customer to a person in charge or a department in charge when the answer providing unit cannot provide an answer. A system characterized by:

2. The answer providing unit is Using AI to generate the answer to the question 2. The system of claim 1 .

3. The troubleshooting unit includes: Using AI to propose solutions to the technical problems or defects 2. The system of claim 1 .

4. The order information providing unit: Manage order history and delivery status information using blockchain technology 2. The system of claim 1 .

5. The reception unit is Accepting the customer's input using a generating AI 2. The system of claim 1 .

6. Equipped with a related information provision department, The related information providing unit searches for and provides at least one of social media posts, scientific papers, technical specifications, and patent documents related to the customer's input.

2. The system of claim 1 .

7. The reception unit is Determining a type of input for the customer based on attributes of the customer 2. The system of claim 1 .

8. The product information providing unit includes: Using augmented reality technology to provide visual product information to the customer 2. The system of claim 1 .

Images