system

Abstract

The system according to this embodiment aims to automate and streamline the return process in e-commerce operations. [Solution] The system according to the embodiment comprises a reception unit, a discrimination unit, a determination unit, a decision unit, and an execution unit. The reception unit receives customer input. The discrimination unit determines the reason for return based on the content received by the reception unit. The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit determines whether a return and refund are possible based on the condition of the product determined by the determination unit. The execution unit performs a refund or exchange process based on the result determined by the decision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the return operation in EC operation is complicated and time-consuming and costly.

[0005] The system according to the embodiment aims to automate and improve the efficiency of the return operation in EC operation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a discrimination unit, a determination unit, a decision unit, and an execution unit. The reception unit receives customer input. The discrimination unit determines the reason for return based on the information received by the reception unit. The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit determines whether a return and refund are possible based on the condition of the product determined by the determination unit. The execution unit performs a refund or exchange process based on the result determined by the decision unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate and streamline the return process in e-commerce operations. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The automated return processing system according to an embodiment of the present invention is a system that automates return processing in e-commerce operations using AI multi-agent technology. When a customer wishes to return an item, this automated return processing system automatically determines the reason for the return from the customer's input. Next, it automatically determines the condition of the product using image recognition technology. Based on the reason for the return and the condition of the product, the AI ​​determines whether a return and refund are possible. Furthermore, based on the reason for the return, it automatically executes refund or exchange processing. For example, when a customer wishes to return an item, the automated return processing system automatically determines the reason for the return from the customer's input. For example, the automated return processing system automatically determines the condition of the product using image recognition technology. Based on the reason for the return and the condition of the product, the AI ​​determines whether a return and refund are possible. For example, the automated return processing system automatically executes refund or exchange processing based on the reason for the return. This improves the efficiency of return processing and reduces time and costs. In addition, the automated return processing system analyzes data such as the reason for the return and customer attributes to consider measures to reduce the return rate. For example, the automated return processing system identifies problems such as "extra items not ordered were included" or "the product was damaged," which are among the top reasons for returns, and develops measures to resolve these issues. Furthermore, the automated return processing system also develops and implements measures to improve customer satisfaction. For instance, the automated return processing system conducts customer satisfaction surveys, collects customer feedback, and uses it to improve services. This system consists of an AI multi-agent system comprising a return acceptance agent, a refund agent, and a shipping agent. The return acceptance agent automatically determines the reason for return from the customer's input and automatically assesses the condition of the product using image recognition technology. The refund agent determines whether a return and refund are possible based on the reason for return and the condition of the product, and automatically executes the refund or exchange process. The shipping agent automatically communicates with the shipping company and executes the shipment of the product. This system streamlines the return process in e-commerce operations, enabling reductions in time and costs. It is also expected to contribute to improved customer satisfaction and a reduction in the return rate.As a result, the automated return processing system can automatically determine the reason for return from the customer's input, automatically assess the condition of the product, decide whether a return and refund are possible, and automatically execute the refund or exchange process.

[0029] The automated return processing system according to this embodiment comprises a reception unit, a discrimination unit, a determination unit, a judgment unit, and an execution unit. The reception unit receives customer input. Customer input includes, but is not limited to, text input, multiple-choice input, and voice input. The reception unit can, for example, receive text input. The reception unit can also receive multiple-choice input. Furthermore, the reception unit can also receive voice input. For example, the reception unit receives text data entered by the customer. The reception unit can also, for example, receive data in which the customer has selected options. The reception unit can also, for example, receive data entered by the customer via voice. The discrimination unit determines the reason for return based on the content received by the reception unit. Reasons for return include, but are not limited to, product defects, order errors, and customer convenience. For example, the discrimination unit determines that product defects are the reason for return. The discrimination unit can also determine that order errors are the reason for return. Furthermore, the discrimination unit can also determine that customer convenience is the reason for return. For example, the discrimination unit detects a defect in the product and identifies it as a reason for return. The discrimination unit can also detect, for example, an ordering error and identify it as a reason for return. The discrimination unit can also detect, for example, customer convenience and identify it as a reason for return. The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes, but is not limited to, external damage, malfunction, and signs of use. For example, the determination unit determines external damage to the product. The determination unit can also determine malfunction of the product. Furthermore, the determination unit can also determine signs of use on the product. For example, the determination unit determines whether there is external damage to the product. The determination unit can also determine, for example, whether there is a malfunction in the product's operation. The determination unit can also determine, for example, whether there are signs of use on the product. The judgment unit determines whether a return and refund are possible based on the condition of the product determined by the determination unit. Whether a return and refund are possible includes, but is not limited to, the return policy, the condition of the product, and the number of days elapsed since the date of purchase. For example, the decision-making unit determines whether a return and refund are possible based on the return policy.The decision unit can also determine whether a return and refund are possible based on the condition of the product. Furthermore, the decision unit can also determine whether a return and refund are possible based on the number of days elapsed since the date of purchase. For example, the decision unit determines whether a return and refund are possible according to the return policy. The decision unit can also determine whether a return and refund are possible by considering, for example, the condition of the product. The decision unit can also determine whether a return and refund are possible by considering, for example, the number of days elapsed since the date of purchase. The execution unit performs the refund or exchange process based on the result determined by the decision unit. The refund or exchange process includes, but is not limited to, the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund process according to the refund method. Furthermore, the execution unit can also perform the exchange process according to the shipping procedure for the replacement product. Furthermore, the execution unit can also perform the process by combining the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund process according to the refund method. The execution unit can also perform the exchange process according to the shipping procedure for the replacement product. Furthermore, the execution unit can also perform the process by combining the refund method and the shipping procedure for the replacement product. As a result, the automated return processing system according to this embodiment can automatically determine the reason for return from the customer's input, automatically assess the condition of the product, determine whether a return and refund are possible, and automatically execute refund or exchange processing.

[0030] The reception desk receives customer input. Customer input includes, but is not limited to, text input, multiple-choice input, and voice input. For example, the reception desk can accept text input. The reception desk can also accept multiple-choice input. Furthermore, the reception desk can also accept voice input. For example, the reception desk can receive text data entered by the customer. The reception desk can also receive data selected by the customer from multiple-choice options. The reception desk can also receive data entered by the customer via voice. When a customer wishes to return an item, the reception desk can enhance customer convenience by offering various input methods. For example, with text input, the customer can describe the reason for the return and the condition of the item in detail. With multiple-choice input, the customer can easily complete the input by simply selecting the appropriate item from a set of options. With voice input, the content spoken by the customer can be converted into text data using speech recognition technology and accepted as input. This allows the reception desk to meet diverse customer needs and support a smooth return process. Furthermore, the reception desk also has a function to automatically classify the input content and distribute it to the appropriate department or person in charge. For example, it can analyze the text input using natural language processing technology and distribute it to the appropriate processing flow according to the reason for return and the condition of the product. In the case of multiple-choice input, processing proceeds automatically based on the selected option. In the case of voice input, it can also convert it into text data using speech recognition technology, analyze it in the same way, and distribute it to the appropriate processing flow. As a result, the reception desk can efficiently process customer input and provide a quick response.

[0031] The discrimination unit determines the reason for return based on the information received by the reception unit. Reasons for return include, but are not limited to, product defects, ordering errors, and customer convenience. For example, the discrimination unit may determine a product defect as the reason for return. It can also determine an ordering error as the reason for return. Furthermore, it can determine customer convenience as the reason for return. For example, the discrimination unit may detect a product defect and determine it as the reason for return. It can also detect an ordering error and determine it as the reason for return. It can also detect customer convenience and determine it as the reason for return. The discrimination unit uses AI to analyze customer input and automatically determine the reason for return. For example, it can use natural language processing technology to analyze text input and identify reasons for return such as product defects, ordering errors, and customer convenience. In the case of voice input, it can use speech recognition technology to convert it into text data and then similarly analyze it to determine the reason for return. In the case of multiple-choice input, it can automatically determine the reason for return based on the selected option. This allows the discrimination unit to quickly and accurately analyze customer input and identify the appropriate reason for return. Furthermore, the discrimination unit can utilize historical data and statistical information to analyze trends and patterns in return reasons. For example, based on past return data, it can understand trends in return reasons for specific products or periods, and formulate future countermeasures. It can also use anomaly detection algorithms to detect unusual patterns or abnormal data and issue warnings early. As a result, the discrimination unit can not only determine return reasons in real time but also handle long-term trend analysis and anomaly detection, improving the reliability and efficiency of the entire system.

[0032] The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes, but is not limited to, external damage, malfunction, and signs of use. For example, the determination unit can determine external damage to the product. The determination unit can also determine malfunctions in the product. Furthermore, the determination unit can also determine signs of use. For example, the determination unit can determine whether there is external damage to the product. The determination unit can also determine, for example, whether there are malfunctions in the product's operation. The determination unit can also determine, for example, whether there are signs of use. The determination unit automatically determines the condition of the product using AI. For example, it can analyze the appearance of the product using image recognition technology to determine the presence and extent of damage. In the case of malfunctions, it can inspect the product's operation using sensors and test equipment to identify the faulty part. Regarding signs of use, it can analyze the surface and internal condition of the product to determine traces of use. This allows the determination unit to quickly and accurately determine the condition of the product and provide information for appropriate processing. Furthermore, the determination unit can improve the accuracy of product condition determination by utilizing past data and statistical information. For example, based on past judgment data, it is possible to understand the damage patterns and malfunction trends of specific products and optimize the judgment algorithm. Furthermore, anomaly detection algorithms can be used to detect unusual patterns or abnormal conditions and issue early warnings. This allows the judgment unit to handle not only real-time condition judgment but also long-term trend analysis and anomaly detection, improving the overall reliability and efficiency of the system.

[0033] The decision unit determines whether a return and refund is possible based on the condition of the product determined by the judgment unit. The decision regarding return and refund eligibility includes, but is not limited to, the return policy, the condition of the product, and the number of days elapsed since the purchase date. For example, the decision unit may determine whether a return and refund is possible based on the return policy. The decision unit may also determine whether a return and refund is possible based on the condition of the product. Furthermore, the decision unit may also determine whether a return and refund is possible based on the number of days elapsed since the purchase date. For example, the decision unit may determine whether a return and refund is possible according to the return policy. The decision unit may also determine whether a return and refund is possible considering, for example, the condition of the product. The decision unit may also determine whether a return and refund is possible considering, for example, the number of days elapsed since the purchase date. The decision unit uses AI to automatically determine whether a return and refund is possible. For example, it can use a rule-based algorithm based on the return policy to determine whether a return and refund is possible, taking into account the condition of the product and the number of days elapsed since the purchase date. Regarding the condition of the product, the system evaluates the presence of external damage, malfunctions, and signs of use based on information provided by the judgment unit, and determines whether a return and refund are possible. For the number of days elapsed since the purchase date, the system retrieves the purchase date from its database and makes an appropriate decision according to the return policy. This allows the judgment unit to quickly and accurately determine whether a return and refund are possible and provide appropriate support to the customer. Furthermore, the judgment unit can improve the accuracy of its judgment algorithm by utilizing historical data and statistical information. For example, it can analyze return trends and refund rates for specific products based on past return and refund data to optimize the judgment criteria. It can also use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the judgment unit to handle not only real-time decisions but also long-term trend analysis and anomaly detection, improving the overall reliability and efficiency of the system.

[0034] The execution unit performs refund or exchange processing based on the results determined by the decision unit. Refund and exchange processing includes, but is not limited to, the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund processing according to the refund method. The execution unit can also perform the exchange processing according to the shipping procedure for the replacement product. Furthermore, the execution unit can combine the refund method and the shipping procedure for the replacement product to perform the processing. For example, the execution unit performs the refund processing according to the refund method. The execution unit can also perform the exchange processing according to, for example, the shipping procedure for the replacement product. The execution unit can also combine the refund method and the shipping procedure for the replacement product to perform the processing. Based on the information provided by the decision unit, the execution unit performs the refund or exchange processing quickly and accurately. For example, in the case of a refund, the refund is made according to the customer's payment method. In the case of a credit card payment, the refund procedure is requested from the credit card company, and in the case of a bank transfer, the refund is made to the customer's bank account. In the case of an exchange, the inventory status of the replacement product is checked and the replacement product is shipped to the customer according to the appropriate shipping procedure. This allows the execution unit to provide customers with a quick and appropriate response and improve customer satisfaction. Furthermore, the execution unit can monitor the progress of refund and exchange processing in real time and adjust responses as needed. For example, if a refund is delayed, it can identify the cause and take prompt action. Similarly, if the shipment of a replacement product is delayed, it can check the inventory status and take appropriate action. This allows the execution unit to improve the efficiency and reliability of refund and exchange processing. In addition, the execution unit can collect customer feedback and continuously improve the accuracy and effectiveness of the processing. For example, it can improve processing flows and systems based on customer opinions and requests regarding refund and exchange processing. This allows the execution unit to provide better service to customers and improve the reliability and efficiency of the overall system.

[0035] The analysis department can analyze data on return reasons and customer attributes. For example, the analysis department can analyze the details of return reasons. For example, the analysis department can analyze the details of return reasons and consider measures to reduce the return rate. The analysis department can also analyze the age of customers. For example, the analysis department can analyze the age of customers and develop measures for specific age groups. Furthermore, the analysis department can also analyze the gender of customers. For example, the analysis department can analyze the gender of customers and develop measures for specific genders. The analysis department can also analyze the purchase history of customers. For example, the analysis department can analyze the purchase history of customers and develop measures based on specific purchase histories. This allows the analysis department to consider measures to reduce the return rate by analyzing data on return reasons and customer attributes. Some or all of the above processing in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input detailed data on return reasons into a generating AI and have the generating AI develop measures to reduce the return rate.

[0036] The research department can conduct customer satisfaction surveys. For example, the research department can conduct questionnaire surveys. For example, the research department can conduct questionnaires with customers to investigate customer satisfaction. The research department can also conduct interviews. For example, the research department can conduct interviews with customers to investigate customer satisfaction. Furthermore, the research department can collect evaluation scores. For example, the research department can collect evaluation scores from customers to investigate customer satisfaction. By conducting customer satisfaction surveys, measures to improve customer satisfaction can be formulated. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input customer satisfaction survey data into a generating AI and have the generating AI formulate measures to improve customer satisfaction.

[0037] The delivery department can communicate with delivery companies. The delivery department can, for example, perform API integration. For example, the delivery department can use the delivery company's API to automatically process product shipments. The delivery department can also send email notifications. For example, the delivery department can send email notifications to delivery companies to process product shipments. Furthermore, the delivery department can also make telephone contacts. For example, the delivery department can contact delivery companies by telephone to process product shipments. In this way, product shipments can be automatically executed by communicating with delivery companies. Some or all of the above processes in the delivery department may be performed using AI, for example, or not using AI. For example, the delivery department can input communication data with delivery companies into a generating AI and have the generating AI execute product shipment procedures.

[0038] The discrimination unit can determine the condition of a product using image recognition technology. The discrimination unit can analyze the appearance of a product using, for example, object detection technology. For example, the discrimination unit can determine whether there is any damage to the appearance of a product using object detection technology. The discrimination unit can also classify the condition of a product using image classification technology. For example, the discrimination unit can classify the condition of a product into "new," "used," "damaged," etc., using image classification technology. Furthermore, the discrimination unit can analyze the detailed condition of a product using segmentation technology. For example, the discrimination unit can detect scratches and stains on the surface of a product using segmentation technology. As a result, the condition of a product can be automatically determined using image recognition technology. Some or all of the above-described processes in the discrimination unit may be performed using, for example, AI, or without AI. For example, the discrimination unit can input image data of a product into a generating AI and have the generating AI perform the determination of the condition of the product.

[0039] The execution unit can perform refund or exchange processing based on the reason for return. For example, the execution unit can perform refund processing according to the processing procedure for each reason for return. For example, if the reason for return is a product defect, the execution unit will prioritize the refund process. The execution unit can also perform exchange processing based on the priority of each reason for return. For example, if the reason for return is an order error, the execution unit will prioritize the exchange process. Furthermore, the execution unit can combine processing procedures and priorities for each reason for return. For example, if the reason for return is due to customer reasons, the execution unit can perform both refund and exchange processing. This allows for the automatic execution of refund and exchange processing based on the reason for return. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input return reason data into a generating AI and have the generating AI perform the refund or exchange processing.

[0040] The reception department can analyze a user's past return history and select the optimal return method. For example, if a user has made frequent returns in the past, the reception department can provide a simplified return method. The reception department can also provide detailed guidance to support the return process if the user has never made a return before. Furthermore, the reception department can suggest the optimal return method for a specific reason based on the user's past return history. This allows the reception department to select the optimal return method by analyzing the user's past return history. Some or all of the above processing in the reception department may be performed using AI, or not. For example, the reception department can input the user's past return history data into a generating AI and have the generating AI select the optimal return method.

[0041] The reception unit can filter the user's current purchase history and areas of interest at the time of reception. For example, the reception unit can automatically filter items eligible for return from the user's purchase history. The reception unit can also prioritize the acceptance of returns of items related to the user's areas of interest. Furthermore, the reception unit can combine the user's purchase history and areas of interest to suggest the optimal return acceptance method. This allows for priority acceptance of returns of related items by filtering based on the user's current purchase history and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the user's purchase history data and areas of interest data into a generating AI and have the generating AI perform the filtering.

[0042] The reception desk can prioritize the acceptance of highly relevant returns by considering the user's geographical location information at the time of acceptance. For example, if the user lives nearby, the reception desk will prioritize the acceptance of that user's return. The reception desk can also accept returns with normal priority if the user lives far away. For example, if the reception desk lives far away, the reception desk will prioritize the acceptance of that user's return. Furthermore, the reception desk can also suggest the optimal return acceptance method based on the user's geographical location information. For example, the reception desk will suggest the optimal return acceptance method based on the user's geographical location information. This allows for the priority acceptance of highly relevant returns by considering the user's geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location information data into a generating AI and have the generating AI perform the priority acceptance of highly relevant returns.

[0043] The reception department can analyze the user's social media activity at the time of reception and accept related returns. For example, the reception department can collect information related to the reason for return from the user's social media activity and accept the return. The reception department can also analyze the user's social media activity and propose the optimal method for accepting returns. Furthermore, the reception department can prioritize accepting returns of related products based on the user's social media activity. For example, the reception department prioritizes accepting returns of related products based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to accept related returns. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the user's social media activity data into a generating AI and have the generating AI execute the acceptance of related returns.

[0044] The discrimination unit can adjust the level of detail in its discrimination process based on the importance of the reason for return. For example, the discrimination unit can perform a detailed discrimination if the reason for return is important. The discrimination unit can also perform a normal discrimination if the reason for return is common. Furthermore, the discrimination unit can perform a simplified discrimination if the reason for return is minor. By adjusting the level of detail in the discrimination process based on the importance of the reason for return, a more appropriate discrimination can be achieved. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the return reason data into a generating AI and have the generating AI perform the adjustment of the level of detail in the discrimination process.

[0045] The discrimination unit can apply different discrimination algorithms depending on the category of the reason for return during discrimination. For example, if the reason for return is related to product damage, the discrimination unit can apply an image recognition algorithm. For example, if the reason for return is related to product damage, the discrimination unit can apply an algorithm that discriminates based on the delivery history. For example, if the reason for return is related to product misdelivery, the discrimination unit can apply an algorithm that discriminates based on the delivery history. Furthermore, if the reason for return is related to product quality, the discrimination unit can apply a quality inspection algorithm. For example, if the reason for return is related to product quality, the discrimination unit can apply a quality inspection algorithm. By applying different discrimination algorithms depending on the category of the reason for return, more accurate discrimination can be achieved. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the return reason data into a generating AI and have the generating AI execute the application of different discrimination algorithms.

[0046] The discrimination unit can determine the priority of discrimination based on the submission timing of the return reason. For example, if the return reason is submitted early, the discrimination unit will prioritize its discrimination. The discrimination unit can also determine the return reason with the normal priority if it is submitted at the normal submission time. Furthermore, the discrimination unit can postpone the discrimination of a return reason if it is submitted late. By determining the priority of discrimination based on the submission timing of the return reason, discrimination can be performed in a more appropriate order. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the submission timing data of the return reason into a generating AI and have the generating AI determine the priority of discrimination.

[0047] The discrimination unit can adjust the order of discrimination based on the relevance of the return reasons during discrimination. For example, the discrimination unit can prioritize discrimination when the return reason is related to the quality of the product. The discrimination unit can also perform discrimination in the normal order when the return reason is related to delivery. Furthermore, the discrimination unit can postpone discrimination when the return reason is related to a minor issue. In this way, discrimination can be performed in a more appropriate order by adjusting the order of discrimination based on the relevance of the return reasons. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input data on the relevance of the return reasons into a generating AI and have the generating AI perform the adjustment of the discrimination order.

[0048] The judgment unit can improve the accuracy of its judgment by considering the interrelationships between products during the judgment process. For example, the judgment unit can make a judgment by considering the interrelationships between products in the same category. The judgment unit can also make a judgment based on the interrelationships between similar products. For example, the judgment unit can make a judgment based on the interrelationships between similar products. Furthermore, the judgment unit can analyze the interrelationships between products and make the optimal judgment. For example, the judgment unit can analyze the interrelationships between products and make the optimal judgment. In this way, the accuracy of the judgment can be improved by considering the interrelationships between products. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input product interrelationship data into a generating AI and have the generating AI perform the task of improving the accuracy of the judgment.

[0049] The judgment unit can make a judgment by considering the attribute information of the product submitter. For example, the judgment unit can make a judgment by considering the submitter's age and gender. The judgment unit can also make a judgment based on the submitter's past purchase history. Furthermore, the judgment unit can also make a judgment based on the submitter's regional information. By considering the attribute information of the product submitter, a more appropriate judgment can be made. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the judgment.

[0050] The judgment unit can make a judgment while considering the geographical distribution of the product. For example, the judgment unit can make the optimal judgment based on the geographical distribution of the product. The judgment unit can also determine the quality of the product based on its geographical distribution. For example, the judgment unit can determine the quality of the product based on its geographical distribution. Furthermore, the judgment unit can also determine whether a return is possible while considering the geographical distribution. For example, the judgment unit can determine whether a return is possible while considering the geographical distribution. This allows for a more appropriate judgment by considering the geographical distribution of the product. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input geographical distribution data of the product into a generating AI and have the generating AI perform the judgment.

[0051] The judgment unit can improve the accuracy of its judgment by referring to relevant literature on the product during the judgment process. For example, the judgment unit can determine the quality based on relevant literature on the product. The judgment unit can also determine the condition of the product by referring to relevant literature. Furthermore, the judgment unit can determine whether a product is eligible for return based on relevant literature. In this way, the accuracy of the judgment can be improved by referring to relevant literature on the product. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input relevant literature data on the product into a generating AI and have the generating AI perform the task of improving the accuracy of the judgment.

[0052] The decision-making unit can predict the current decision by referring to past decision data when making a decision. For example, the decision-making unit predicts the current decision based on past decision data. The decision-making unit can also analyze past decision patterns to make the optimal decision. For example, the decision-making unit analyzes past decision patterns to make the optimal decision. Furthermore, the decision-making unit can improve the accuracy of the current decision by referring to past decision data. For example, the decision-making unit improves the accuracy of the current decision by referring to past decision data. In this way, the accuracy of the current decision can be improved by referring to past decision data. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input past decision data into a generating AI and have the generating AI perform a prediction of the current decision.

[0053] The decision-making unit can apply different decision-making analysis methods to each product category when making a decision. For example, the decision-making unit can apply different decision-making analysis methods depending on the product category. For example, the decision-making unit can apply different decision-making analysis methods depending on the product category. The decision-making unit can also make the optimal decision by considering the characteristics of each category. For example, the decision-making unit can make the optimal decision by considering the characteristics of each category. Furthermore, the decision-making unit can make a decision by applying different algorithms based on the product category. For example, the decision-making unit can make a decision by applying different algorithms based on the product category. This allows for more appropriate decisions to be made by applying different decision-making analysis methods to each product category. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input product category data into a generating AI and have the generating AI execute the application of decision-making analysis methods.

[0054] The decision unit can analyze changes in judgment based on the product submission timing when making a decision. For example, the decision unit can analyze changes in judgment based on the product submission timing. The decision unit can also analyze decision patterns for each submission timing to make the optimal decision. For example, the decision unit can analyze decision patterns for each submission timing to make the optimal decision. Furthermore, the decision unit can predict changes in judgment depending on the submission timing. For example, the decision unit can predict changes in judgment depending on the submission timing. This allows for more appropriate decisions to be made by analyzing changes in judgment based on the product submission timing. Some or all of the above processing in the decision unit may be performed using AI, for example, or without AI. For example, the decision unit can input product submission timing data into a generating AI and have the generating AI perform the analysis of changes in judgment.

[0055] The decision-making unit can analyze its decision by referring to relevant market data for the product. For example, the decision-making unit can analyze its decision based on relevant market data for the product. The decision-making unit can also determine the quality of the product by referring to market data. For example, the decision-making unit can determine the quality of the product by referring to market data. Furthermore, the decision-making unit can determine whether a return is possible based on market data. For example, the decision-making unit can determine whether a return is possible based on market data. This allows for more appropriate decisions to be made by referring to relevant market data for the product. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input relevant market data for the product into a generating AI and have the generating AI perform the analysis of the decision.

[0056] The execution unit can improve the accuracy of execution by considering the interrelationships between products during execution. For example, the execution unit can perform execution by considering the interrelationships between products in the same category. The execution unit can also perform execution based on the interrelationships between similar products. Furthermore, the execution unit can analyze the interrelationships between products and perform the optimal execution. In this way, the accuracy of execution can be improved by considering the interrelationships between products. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input product interrelationship data into a generating AI and have the generating AI perform the execution accuracy improvement.

[0057] The execution unit can perform actions while considering the attribute information of the product submitter. For example, the execution unit can perform actions while considering the submitter's age and gender. The execution unit can also perform actions based on the submitter's past purchase history. Furthermore, the execution unit can also perform actions while considering the submitter's regional information. This allows for more appropriate execution by considering the attribute information of the product submitter. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the execution.

[0058] The execution unit can perform actions while considering the geographical distribution of the products. For example, the execution unit can perform optimal actions based on the geographical distribution of the products. The execution unit can also perform actions on product quality based on geographical distribution. Furthermore, the execution unit can also determine whether or not a product is eligible for return, taking geographical distribution into consideration. This allows for more appropriate actions by considering the geographical distribution of the products. Some or all of the above-described processes in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input geographical distribution data of the products into a generating AI and have the generating AI perform the actions.

[0059] The execution unit can improve the accuracy of its execution by referring to relevant literature on the product during execution. For example, the execution unit can perform quality checks based on relevant literature on the product. The execution unit can also perform condition checks based on relevant literature. Furthermore, the execution unit can determine whether a product is eligible for return based on relevant literature. In this way, the accuracy of the execution can be improved by referring to relevant literature on the product. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input relevant literature data on the product into a generating AI and have the generating AI perform the improvement of execution accuracy.

[0060] The analysis unit can optimize its analysis algorithm by referring to past analysis data during the analysis process. For example, the analysis unit can optimize the current analysis algorithm based on past analysis data. The analysis unit can also analyze past analysis patterns and apply the most suitable algorithm. Furthermore, the analysis unit can improve the accuracy of the current analysis by referring to past analysis data. For example, the analysis unit can improve the accuracy of the current analysis by referring to past analysis data. This allows the accuracy of the current analysis to be improved by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0061] The analysis department can weight the analysis data based on when the return reasons were submitted. For example, if the return reasons were submitted early, the analysis department can assign a higher weight to that data for analysis. The analysis department can also perform the analysis with normal weights if the return reasons were submitted at the normal submission time. Furthermore, the analysis department can assign a lower weight to the data if the return reasons were submitted late. This allows for a more appropriate analysis by weighting the analysis data based on when the return reasons were submitted. Some or all of the above processing in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can input the return reason submission time data into a generating AI and have the generating AI perform the weighting of the analysis data.

[0062] The research department can provide optimal advice by referring to the user's past research history when advising on research. For example, the research department can provide optimal advice based on the user's past research history. The research department can also provide optimal advice by analyzing past research patterns. For example, the research department can provide optimal advice by analyzing past research patterns. Furthermore, the research department can improve the accuracy of the current research by referring to past research history. For example, the research department can improve the accuracy of the current research by referring to past research history. This allows the research department to provide more appropriate advice by referring to the user's past research history. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input the user's past research history data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0063] The research department can provide optimal advice by considering the user's device information when providing research advice. For example, if the user is using a smartphone, the research department can provide advice tailored to the screen size. For example, if the user is using a tablet, the research department can provide advice optimized for a larger screen. For example, if the user is using a tablet, the research department can provide advice optimized for a larger screen. Furthermore, if the user is using a smartwatch, the research department can provide concise and easy-to-read advice. For example, if the user is using a smartwatch, the research department can provide concise and easy-to-read advice. This allows for the provision of more appropriate advice by considering the user's device information. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can input user device information data into a generating AI and have the generating AI provide optimal advice.

[0064] The delivery department can select the optimal delivery method by referring to the user's past delivery history during delivery. For example, the delivery department can select the optimal delivery method based on the user's past delivery history. The delivery department can also analyze past delivery patterns and propose the optimal delivery method. Furthermore, the delivery department can improve the accuracy of current deliveries by referring to past delivery history. For example, the delivery department can improve the accuracy of current deliveries by referring to past delivery history. This allows for the selection of a more appropriate delivery method by referring to the user's past delivery history. Some or all of the above processes in the delivery department may be performed using AI, for example, or without AI. For example, the delivery department can input the user's past delivery history data into a generating AI and have the generating AI select the optimal delivery method.

[0065] The delivery unit can select the optimal delivery method by considering the user's geographical location information during delivery. For example, the delivery unit can select the optimal delivery method based on the user's geographical location information. The delivery unit can also provide the fastest delivery method based on geographical location information. Furthermore, the delivery unit can propose the optimal delivery route by considering geographical location information. For example, the delivery unit proposes the optimal delivery route by considering geographical location information. This allows for the selection of a more appropriate delivery method by considering the user's geographical location information. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input the user's geographical location data into a generating AI and have the generating AI select the optimal delivery method.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The reception desk can improve the accuracy of user input by referring to the user's past purchase history. For example, the reception desk can suggest input options based on information about products the user has purchased in the past. It can also prioritize displaying information about frequently returned items based on the user's past purchase history. Furthermore, the reception desk can analyze the user's past purchase history and provide an auto-completion function for input. This improves the accuracy of user input and streamlines the reception process.

[0068] The judgment unit can refer to quality assurance data provided by the product manufacturer when determining the condition of a product. For example, the judgment unit can determine the condition of a product in detail based on the quality assurance data provided by the product manufacturer. Furthermore, the judgment unit can also make a determination that takes into account the product's usage and storage conditions, based on the quality assurance data. In addition, the judgment unit can refer to the quality assurance data to provide additional information about the product's condition. This allows for a more accurate determination of the product's condition.

[0069] The execution unit can select the optimal processing method by referring to the user's past return history when performing refund or exchange processing. For example, the execution unit can propose the most suitable refund method based on information about products the user has returned in the past. Furthermore, the execution unit can prioritize the execution of exchange methods for frequently returned items based on past return history. In addition, the execution unit can analyze the user's past return history and automate refund and exchange processing. This improves the efficiency of refund and exchange processing.

[0070] The discrimination unit can analyze user input using natural language processing technology when determining the reason for a return. For example, the discrimination unit can analyze text data entered by the user using natural language processing technology and automatically extract the reason for the return. Furthermore, the discrimination unit can use natural language processing technology to understand the context of the user's input and determine a more accurate reason for the return. In addition, the discrimination unit can use natural language processing technology to fill in ambiguous parts of the user's input. This improves the accuracy of determining the reason for a return.

[0071] The execution unit can select the optimal processing method when performing refund or exchange processing, taking into account the user's geographical location. For example, if the user lives nearby, the execution unit will prioritize processing their return. If the user lives far away, it can process the return with the normal priority. Furthermore, the execution unit can suggest the most suitable refund or exchange method based on the user's geographical location. This allows for the selection of a more appropriate processing method by considering the user's geographical location.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The reception desk receives customer input. Customer input includes text input, selection from multiple-choice options, and voice input. For example, the reception desk can receive text data entered by the customer, data selected from multiple-choice options, and data entered by voice. Step 2: The discrimination unit determines the reason for return based on the information received by the reception unit. Reasons for return include product defects, ordering mistakes, and customer convenience. For example, the discrimination unit can determine product defects, ordering mistakes, and customer convenience as reasons for return. Step 3: The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes external damage, malfunction, and signs of use. For example, the determination unit can determine external damage, malfunction, and signs of use. Step 4: The judgment unit determines whether a return and refund are possible based on the condition of the product determined by the assessment unit. Factors in determining whether a return and refund are possible include the return policy, the condition of the product, and the number of days elapsed since the purchase date. For example, the judgment unit can determine whether a return and refund are possible based on the return policy, the condition of the product, and the number of days elapsed since the purchase date. Step 5: The execution unit performs the refund or exchange process based on the result determined by the decision unit. The refund or exchange process includes the refund method and the procedure for shipping the replacement product. For example, the execution unit can perform the refund process according to the refund method and the exchange process according to the procedure for shipping the replacement product.

[0074] (Example of form 2) The automated return processing system according to an embodiment of the present invention is a system that automates return processing in e-commerce operations using AI multi-agent technology. When a customer wishes to return an item, this automated return processing system automatically determines the reason for the return from the customer's input. Next, it automatically determines the condition of the product using image recognition technology. Based on the reason for the return and the condition of the product, the AI ​​determines whether a return and refund are possible. Furthermore, based on the reason for the return, it automatically executes refund or exchange processing. For example, when a customer wishes to return an item, the automated return processing system automatically determines the reason for the return from the customer's input. For example, the automated return processing system automatically determines the condition of the product using image recognition technology. Based on the reason for the return and the condition of the product, the AI ​​determines whether a return and refund are possible. For example, the automated return processing system automatically executes refund or exchange processing based on the reason for the return. This improves the efficiency of return processing and reduces time and costs. In addition, the automated return processing system analyzes data such as the reason for the return and customer attributes to consider measures to reduce the return rate. For example, the automated return processing system identifies problems such as "extra items not ordered were included" or "the product was damaged," which are among the top reasons for returns, and develops measures to resolve these issues. Furthermore, the automated return processing system also develops and implements measures to improve customer satisfaction. For instance, the automated return processing system conducts customer satisfaction surveys, collects customer feedback, and uses it to improve services. This system consists of an AI multi-agent system comprising a return acceptance agent, a refund agent, and a shipping agent. The return acceptance agent automatically determines the reason for return from the customer's input and automatically assesses the condition of the product using image recognition technology. The refund agent determines whether a return and refund are possible based on the reason for return and the condition of the product, and automatically executes the refund or exchange process. The shipping agent automatically communicates with the shipping company and executes the shipment of the product. This system streamlines the return process in e-commerce operations, enabling reductions in time and costs. It is also expected to contribute to improved customer satisfaction and a reduction in the return rate.As a result, the automated return processing system can automatically determine the reason for return from the customer's input, automatically assess the condition of the product, decide whether a return and refund are possible, and automatically execute the refund or exchange process.

[0075] The automated return processing system according to this embodiment comprises a reception unit, a discrimination unit, a determination unit, a judgment unit, and an execution unit. The reception unit receives customer input. Customer input includes, but is not limited to, text input, multiple-choice input, and voice input. The reception unit can, for example, receive text input. The reception unit can also receive multiple-choice input. Furthermore, the reception unit can also receive voice input. For example, the reception unit receives text data entered by the customer. The reception unit can also, for example, receive data in which the customer has selected options. The reception unit can also, for example, receive data entered by the customer via voice. The discrimination unit determines the reason for return based on the content received by the reception unit. Reasons for return include, but are not limited to, product defects, order errors, and customer convenience. For example, the discrimination unit determines that product defects are the reason for return. The discrimination unit can also determine that order errors are the reason for return. Furthermore, the discrimination unit can also determine that customer convenience is the reason for return. For example, the discrimination unit detects a defect in the product and identifies it as a reason for return. The discrimination unit can also detect, for example, an ordering error and identify it as a reason for return. The discrimination unit can also detect, for example, customer convenience and identify it as a reason for return. The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes, but is not limited to, external damage, malfunction, and signs of use. For example, the determination unit determines external damage to the product. The determination unit can also determine malfunction of the product. Furthermore, the determination unit can also determine signs of use on the product. For example, the determination unit determines whether there is external damage to the product. The determination unit can also determine, for example, whether there is a malfunction in the product's operation. The determination unit can also determine, for example, whether there are signs of use on the product. The judgment unit determines whether a return and refund are possible based on the condition of the product determined by the determination unit. Whether a return and refund are possible includes, but is not limited to, the return policy, the condition of the product, and the number of days elapsed since the date of purchase. For example, the decision-making unit determines whether a return and refund are possible based on the return policy.The decision unit can also determine whether a return and refund are possible based on the condition of the product. Furthermore, the decision unit can also determine whether a return and refund are possible based on the number of days elapsed since the date of purchase. For example, the decision unit determines whether a return and refund are possible according to the return policy. The decision unit can also determine whether a return and refund are possible by considering, for example, the condition of the product. The decision unit can also determine whether a return and refund are possible by considering, for example, the number of days elapsed since the date of purchase. The execution unit performs the refund or exchange process based on the result determined by the decision unit. The refund or exchange process includes, but is not limited to, the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund process according to the refund method. Furthermore, the execution unit can also perform the exchange process according to the shipping procedure for the replacement product. Furthermore, the execution unit can also perform the process by combining the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund process according to the refund method. The execution unit can also perform the exchange process according to the shipping procedure for the replacement product. Furthermore, the execution unit can also perform the process by combining the refund method and the shipping procedure for the replacement product. As a result, the automated return processing system according to this embodiment can automatically determine the reason for return from the customer's input, automatically assess the condition of the product, determine whether a return and refund are possible, and automatically execute refund or exchange processing.

[0076] The reception desk receives customer input. Customer input includes, but is not limited to, text input, multiple-choice input, and voice input. For example, the reception desk can accept text input. The reception desk can also accept multiple-choice input. Furthermore, the reception desk can also accept voice input. For example, the reception desk can receive text data entered by the customer. The reception desk can also receive data selected by the customer from multiple-choice options. The reception desk can also receive data entered by the customer via voice. When a customer wishes to return an item, the reception desk can enhance customer convenience by offering various input methods. For example, with text input, the customer can describe the reason for the return and the condition of the item in detail. With multiple-choice input, the customer can easily complete the input by simply selecting the appropriate item from a set of options. With voice input, the content spoken by the customer can be converted into text data using speech recognition technology and accepted as input. This allows the reception desk to meet diverse customer needs and support a smooth return process. Furthermore, the reception desk also has a function to automatically classify the input content and distribute it to the appropriate department or person in charge. For example, it can analyze the text input using natural language processing technology and distribute it to the appropriate processing flow according to the reason for return and the condition of the product. In the case of multiple-choice input, processing proceeds automatically based on the selected option. In the case of voice input, it can also convert it into text data using speech recognition technology, analyze it in the same way, and distribute it to the appropriate processing flow. As a result, the reception desk can efficiently process customer input and provide a quick response.

[0077] The discrimination unit determines the reason for return based on the information received by the reception unit. Reasons for return include, but are not limited to, product defects, ordering errors, and customer convenience. For example, the discrimination unit may determine a product defect as the reason for return. It can also determine an ordering error as the reason for return. Furthermore, it can determine customer convenience as the reason for return. For example, the discrimination unit may detect a product defect and determine it as the reason for return. It can also detect an ordering error and determine it as the reason for return. It can also detect customer convenience and determine it as the reason for return. The discrimination unit uses AI to analyze customer input and automatically determine the reason for return. For example, it can use natural language processing technology to analyze text input and identify reasons for return such as product defects, ordering errors, and customer convenience. In the case of voice input, it can use speech recognition technology to convert it into text data and then similarly analyze it to determine the reason for return. In the case of multiple-choice input, it can automatically determine the reason for return based on the selected option. This allows the discrimination unit to quickly and accurately analyze customer input and identify the appropriate reason for return. Furthermore, the discrimination unit can utilize historical data and statistical information to analyze trends and patterns in return reasons. For example, based on past return data, it can understand trends in return reasons for specific products or periods, and formulate future countermeasures. It can also use anomaly detection algorithms to detect unusual patterns or abnormal data and issue warnings early. As a result, the discrimination unit can not only determine return reasons in real time but also handle long-term trend analysis and anomaly detection, improving the reliability and efficiency of the entire system.

[0078] The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes, but is not limited to, external damage, malfunction, and signs of use. For example, the determination unit can determine external damage to the product. The determination unit can also determine malfunctions in the product. Furthermore, the determination unit can also determine signs of use. For example, the determination unit can determine whether there is external damage to the product. The determination unit can also determine, for example, whether there are malfunctions in the product's operation. The determination unit can also determine, for example, whether there are signs of use. The determination unit automatically determines the condition of the product using AI. For example, it can analyze the appearance of the product using image recognition technology to determine the presence and extent of damage. In the case of malfunctions, it can inspect the product's operation using sensors and test equipment to identify the faulty part. Regarding signs of use, it can analyze the surface and internal condition of the product to determine traces of use. This allows the determination unit to quickly and accurately determine the condition of the product and provide information for appropriate processing. Furthermore, the determination unit can improve the accuracy of product condition determination by utilizing past data and statistical information. For example, based on past judgment data, it is possible to understand the damage patterns and malfunction trends of specific products and optimize the judgment algorithm. Furthermore, anomaly detection algorithms can be used to detect unusual patterns or abnormal conditions and issue early warnings. This allows the judgment unit to handle not only real-time condition judgment but also long-term trend analysis and anomaly detection, improving the overall reliability and efficiency of the system.

[0079] The decision unit determines whether a return and refund is possible based on the condition of the product determined by the judgment unit. The decision regarding return and refund eligibility includes, but is not limited to, the return policy, the condition of the product, and the number of days elapsed since the purchase date. For example, the decision unit may determine whether a return and refund is possible based on the return policy. The decision unit may also determine whether a return and refund is possible based on the condition of the product. Furthermore, the decision unit may also determine whether a return and refund is possible based on the number of days elapsed since the purchase date. For example, the decision unit may determine whether a return and refund is possible according to the return policy. The decision unit may also determine whether a return and refund is possible considering, for example, the condition of the product. The decision unit may also determine whether a return and refund is possible considering, for example, the number of days elapsed since the purchase date. The decision unit uses AI to automatically determine whether a return and refund is possible. For example, it can use a rule-based algorithm based on the return policy to determine whether a return and refund is possible, taking into account the condition of the product and the number of days elapsed since the purchase date. Regarding the condition of the product, the system evaluates the presence of external damage, malfunctions, and signs of use based on information provided by the judgment unit, and determines whether a return and refund are possible. For the number of days elapsed since the purchase date, the system retrieves the purchase date from its database and makes an appropriate decision according to the return policy. This allows the judgment unit to quickly and accurately determine whether a return and refund are possible and provide appropriate support to the customer. Furthermore, the judgment unit can improve the accuracy of its judgment algorithm by utilizing historical data and statistical information. For example, it can analyze return trends and refund rates for specific products based on past return and refund data to optimize the judgment criteria. It can also use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the judgment unit to handle not only real-time decisions but also long-term trend analysis and anomaly detection, improving the overall reliability and efficiency of the system.

[0080] The execution unit performs refund or exchange processing based on the results determined by the decision unit. Refund and exchange processing includes, but is not limited to, the refund method and the shipping procedure for the replacement product. For example, the execution unit performs the refund processing according to the refund method. The execution unit can also perform the exchange processing according to the shipping procedure for the replacement product. Furthermore, the execution unit can combine the refund method and the shipping procedure for the replacement product to perform the processing. For example, the execution unit performs the refund processing according to the refund method. The execution unit can also perform the exchange processing according to, for example, the shipping procedure for the replacement product. The execution unit can also combine the refund method and the shipping procedure for the replacement product to perform the processing. Based on the information provided by the decision unit, the execution unit performs the refund or exchange processing quickly and accurately. For example, in the case of a refund, the refund is made according to the customer's payment method. In the case of a credit card payment, the refund procedure is requested from the credit card company, and in the case of a bank transfer, the refund is made to the customer's bank account. In the case of an exchange, the inventory status of the replacement product is checked and the replacement product is shipped to the customer according to the appropriate shipping procedure. This allows the execution unit to provide customers with a quick and appropriate response and improve customer satisfaction. Furthermore, the execution unit can monitor the progress of refund and exchange processing in real time and adjust responses as needed. For example, if a refund is delayed, it can identify the cause and take prompt action. Similarly, if the shipment of a replacement product is delayed, it can check the inventory status and take appropriate action. This allows the execution unit to improve the efficiency and reliability of refund and exchange processing. In addition, the execution unit can collect customer feedback and continuously improve the accuracy and effectiveness of the processing. For example, it can improve processing flows and systems based on customer opinions and requests regarding refund and exchange processing. This allows the execution unit to provide better service to customers and improve the reliability and efficiency of the overall system.

[0081] The analysis department can analyze data on return reasons and customer attributes. For example, the analysis department can analyze the details of return reasons. For example, the analysis department can analyze the details of return reasons and consider measures to reduce the return rate. The analysis department can also analyze the age of customers. For example, the analysis department can analyze the age of customers and develop measures for specific age groups. Furthermore, the analysis department can also analyze the gender of customers. For example, the analysis department can analyze the gender of customers and develop measures for specific genders. The analysis department can also analyze the purchase history of customers. For example, the analysis department can analyze the purchase history of customers and develop measures based on specific purchase histories. This allows the analysis department to consider measures to reduce the return rate by analyzing data on return reasons and customer attributes. Some or all of the above processing in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input detailed data on return reasons into a generating AI and have the generating AI develop measures to reduce the return rate.

[0082] The research department can conduct customer satisfaction surveys. For example, the research department can conduct questionnaire surveys. For example, the research department can conduct questionnaires with customers to investigate customer satisfaction. The research department can also conduct interviews. For example, the research department can conduct interviews with customers to investigate customer satisfaction. Furthermore, the research department can collect evaluation scores. For example, the research department can collect evaluation scores from customers to investigate customer satisfaction. By conducting customer satisfaction surveys, measures to improve customer satisfaction can be formulated. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input customer satisfaction survey data into a generating AI and have the generating AI formulate measures to improve customer satisfaction.

[0083] The delivery department can communicate with delivery companies. The delivery department can, for example, perform API integration. For example, the delivery department can use the delivery company's API to automatically process product shipments. The delivery department can also send email notifications. For example, the delivery department can send email notifications to delivery companies to process product shipments. Furthermore, the delivery department can also make telephone contacts. For example, the delivery department can contact delivery companies by telephone to process product shipments. In this way, product shipments can be automatically executed by communicating with delivery companies. Some or all of the above processes in the delivery department may be performed using AI, for example, or not using AI. For example, the delivery department can input communication data with delivery companies into a generating AI and have the generating AI execute product shipment procedures.

[0084] The discrimination unit can determine the condition of a product using image recognition technology. The discrimination unit can analyze the appearance of a product using, for example, object detection technology. For example, the discrimination unit can determine whether there is any damage to the appearance of a product using object detection technology. The discrimination unit can also classify the condition of a product using image classification technology. For example, the discrimination unit can classify the condition of a product into "new," "used," "damaged," etc., using image classification technology. Furthermore, the discrimination unit can analyze the detailed condition of a product using segmentation technology. For example, the discrimination unit can detect scratches and stains on the surface of a product using segmentation technology. As a result, the condition of a product can be automatically determined using image recognition technology. Some or all of the above-described processes in the discrimination unit may be performed using, for example, AI, or without AI. For example, the discrimination unit can input image data of a product into a generating AI and have the generating AI perform the determination of the condition of the product.

[0085] The execution unit can perform refund or exchange processing based on the reason for return. For example, the execution unit can perform refund processing according to the processing procedure for each reason for return. For example, if the reason for return is a product defect, the execution unit will prioritize the refund process. The execution unit can also perform exchange processing based on the priority of each reason for return. For example, if the reason for return is an order error, the execution unit will prioritize the exchange process. Furthermore, the execution unit can combine processing procedures and priorities for each reason for return. For example, if the reason for return is due to customer reasons, the execution unit can perform both refund and exchange processing. This allows for the automatic execution of refund and exchange processing based on the reason for return. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input return reason data into a generating AI and have the generating AI perform the refund or exchange processing.

[0086] The reception desk can estimate the user's emotions and adjust the timing of the reception based on the estimated emotions. For example, if the user is feeling stressed, the reception desk can delay the reception and wait until the user is relaxed. The reception desk can also speed up the reception if the user is in a hurry. Furthermore, if the user is feeling anxious, the reception desk can adjust the timing of the reception to provide reassurance. By adjusting the timing of the reception according to the user's emotions, reception can be conducted at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user emotion data into a generating AI and have the AI ​​adjust the timing of the reception process.

[0087] The reception department can analyze a user's past return history and select the optimal return method. For example, if a user has made frequent returns in the past, the reception department can provide a simplified return method. The reception department can also provide detailed guidance to support the return process if the user has never made a return before. Furthermore, the reception department can suggest the optimal return method for a specific reason based on the user's past return history. This allows the reception department to select the optimal return method by analyzing the user's past return history. Some or all of the above processing in the reception department may be performed using AI, or not. For example, the reception department can input the user's past return history data into a generating AI and have the generating AI select the optimal return method.

[0088] The reception unit can filter the user's current purchase history and areas of interest at the time of reception. For example, the reception unit can automatically filter items eligible for return from the user's purchase history. The reception unit can also prioritize the acceptance of returns of items related to the user's areas of interest. Furthermore, the reception unit can combine the user's purchase history and areas of interest to suggest the optimal return acceptance method. This allows for priority acceptance of returns of related items by filtering based on the user's current purchase history and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the user's purchase history data and areas of interest data into a generating AI and have the generating AI perform the filtering.

[0089] The reception desk can estimate the user's emotions and determine the priority of returns to be processed based on the estimated emotions. For example, if the user is dissatisfied, the reception desk will prioritize the return. For example, if the user is dissatisfied, the reception desk will prioritize the return. The reception desk can also process the return with the normal priority if the user is satisfied. For example, if the reception desk is satisfied, the reception desk will prioritize the return with the normal priority. Furthermore, if the user is in a hurry, the reception desk can process the return with the highest priority. For example, if the reception desk is in a hurry, the return will prioritize the return. This allows for processing returns in a more appropriate order by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user emotion data into a generating AI and have the AI ​​determine the priority of returns.

[0090] The reception desk can prioritize the acceptance of highly relevant returns by considering the user's geographical location information at the time of acceptance. For example, if the user lives nearby, the reception desk will prioritize the acceptance of that user's return. The reception desk can also accept returns with normal priority if the user lives far away. For example, if the reception desk lives far away, the reception desk will prioritize the acceptance of that user's return. Furthermore, the reception desk can also suggest the optimal return acceptance method based on the user's geographical location information. For example, the reception desk will suggest the optimal return acceptance method based on the user's geographical location information. This allows for the priority acceptance of highly relevant returns by considering the user's geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location information data into a generating AI and have the generating AI perform the priority acceptance of highly relevant returns.

[0091] The reception department can analyze the user's social media activity at the time of reception and accept related returns. For example, the reception department can collect information related to the reason for return from the user's social media activity and accept the return. The reception department can also analyze the user's social media activity and propose the optimal method for accepting returns. Furthermore, the reception department can prioritize accepting returns of related products based on the user's social media activity. For example, the reception department prioritizes accepting returns of related products based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to accept related returns. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the user's social media activity data into a generating AI and have the generating AI execute the acceptance of related returns.

[0092] The discrimination unit can estimate the user's emotions and adjust the expression of the discrimination based on the estimated user emotions. For example, if the user is dissatisfied, the discrimination unit can convey the discrimination result in polite language. For example, if the user is dissatisfied, the discrimination unit can convey the discrimination result in polite language. The discrimination unit can also convey the discrimination result in normal language if the user is satisfied. For example, if the user is satisfied, the discrimination unit can convey the discrimination result in normal language. Furthermore, if the user is in a hurry, the discrimination unit can convey the discrimination result in concise language. For example, if the user is in a hurry, the discrimination unit can convey the discrimination result in concise language. In this way, by adjusting the expression of the discrimination according to the user's emotions, the discrimination result can be conveyed in a more appropriate expression. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without using AI. For example, the discrimination unit can input user emotion data into the generating AI and have the generating AI adjust the way the discrimination is expressed.

[0093] The discrimination unit can adjust the level of detail in its discrimination process based on the importance of the reason for return. For example, the discrimination unit can perform a detailed discrimination if the reason for return is important. The discrimination unit can also perform a normal discrimination if the reason for return is common. Furthermore, the discrimination unit can perform a simplified discrimination if the reason for return is minor. By adjusting the level of detail in the discrimination process based on the importance of the reason for return, a more appropriate discrimination can be achieved. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the return reason data into a generating AI and have the generating AI perform the adjustment of the level of detail in the discrimination process.

[0094] The discrimination unit can apply different discrimination algorithms depending on the category of the reason for return during discrimination. For example, if the reason for return is related to product damage, the discrimination unit can apply an image recognition algorithm. For example, if the reason for return is related to product damage, the discrimination unit can apply an algorithm that discriminates based on the delivery history. For example, if the reason for return is related to product misdelivery, the discrimination unit can apply an algorithm that discriminates based on the delivery history. Furthermore, if the reason for return is related to product quality, the discrimination unit can apply a quality inspection algorithm. For example, if the reason for return is related to product quality, the discrimination unit can apply a quality inspection algorithm. By applying different discrimination algorithms depending on the category of the reason for return, more accurate discrimination can be achieved. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the return reason data into a generating AI and have the generating AI execute the application of different discrimination algorithms.

[0095] The discrimination unit can estimate the user's emotions and adjust the length of the discrimination based on the estimated emotions. For example, if the user is dissatisfied, the discrimination unit can perform a detailed discrimination and provide a longer explanation. The discrimination unit can also perform a normal discrimination and provide a standard explanation if the user is satisfied. Furthermore, if the user is in a hurry, the discrimination unit can perform a concise discrimination and provide a shorter explanation. By adjusting the length of the discrimination according to the user's emotions, the discrimination results can be conveyed at a more appropriate length. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input user emotion data into the generating AI and have the generating AI adjust the length of the discrimination process.

[0096] The discrimination unit can determine the priority of discrimination based on the submission timing of the return reason. For example, if the return reason is submitted early, the discrimination unit will prioritize its discrimination. The discrimination unit can also determine the return reason with the normal priority if it is submitted at the normal submission time. Furthermore, the discrimination unit can postpone the discrimination of a return reason if it is submitted late. By determining the priority of discrimination based on the submission timing of the return reason, discrimination can be performed in a more appropriate order. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input the submission timing data of the return reason into a generating AI and have the generating AI determine the priority of discrimination.

[0097] The discrimination unit can adjust the order of discrimination based on the relevance of the return reasons during discrimination. For example, the discrimination unit can prioritize discrimination when the return reason is related to the quality of the product. The discrimination unit can also perform discrimination in the normal order when the return reason is related to delivery. Furthermore, the discrimination unit can postpone discrimination when the return reason is related to a minor issue. In this way, discrimination can be performed in a more appropriate order by adjusting the order of discrimination based on the relevance of the return reasons. Some or all of the above processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can input data on the relevance of the return reasons into a generating AI and have the generating AI perform the adjustment of the discrimination order.

[0098] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated user emotions. For example, if the user is dissatisfied, the judgment unit can make a judgment using strict criteria. For example, if the user is dissatisfied, the judgment unit can make a judgment using strict criteria. The judgment unit can also make a judgment using normal criteria if the user is satisfied. For example, if the judgment unit is satisfied, the judgment unit can make a judgment using normal criteria. Furthermore, if the user is in a hurry, the judgment unit can make a judgment using rapid criteria. For example, if the judgment unit is in a hurry, the judgment unit can make a judgment using rapid criteria. In this way, by adjusting the judgment criteria according to the user's emotions, a more appropriate judgment can be made. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input user emotion data into the generating AI and have the generating AI adjust the judgment criteria.

[0099] The judgment unit can improve the accuracy of its judgment by considering the interrelationships between products during the judgment process. For example, the judgment unit can make a judgment by considering the interrelationships between products in the same category. The judgment unit can also make a judgment based on the interrelationships between similar products. For example, the judgment unit can make a judgment based on the interrelationships between similar products. Furthermore, the judgment unit can analyze the interrelationships between products and make the optimal judgment. For example, the judgment unit can analyze the interrelationships between products and make the optimal judgment. In this way, the accuracy of the judgment can be improved by considering the interrelationships between products. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input product interrelationship data into a generating AI and have the generating AI perform the task of improving the accuracy of the judgment.

[0100] The judgment unit can make a judgment by considering the attribute information of the product submitter. For example, the judgment unit can make a judgment by considering the submitter's age and gender. The judgment unit can also make a judgment based on the submitter's past purchase history. Furthermore, the judgment unit can also make a judgment based on the submitter's regional information. By considering the attribute information of the product submitter, a more appropriate judgment can be made. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the judgment.

[0101] The judgment unit can estimate the user's emotions and adjust the order in which the judgment results are displayed based on the estimated user emotions. For example, if the user is dissatisfied, the judgment unit can display the most important results first. For example, if the user is dissatisfied, the judgment unit can display the most important results first. The judgment unit can also display the results in the normal order if the user is satisfied. For example, if the user is satisfied, the judgment unit can display the results in the normal order. Furthermore, if the user is in a hurry, the judgment unit can display the main points first. For example, if the user is in a hurry, the judgment unit can display the main points first. In this way, by adjusting the order in which the judgment results are displayed according to the user's emotions, the results can be displayed in a more appropriate order. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input user emotion data into the generating AI and have the generating AI adjust the display order of the judgment results.

[0102] The judgment unit can make a judgment while considering the geographical distribution of the product. For example, the judgment unit can make the optimal judgment based on the geographical distribution of the product. The judgment unit can also determine the quality of the product based on its geographical distribution. For example, the judgment unit can determine the quality of the product based on its geographical distribution. Furthermore, the judgment unit can also determine whether a return is possible while considering the geographical distribution. For example, the judgment unit can determine whether a return is possible while considering the geographical distribution. This allows for a more appropriate judgment by considering the geographical distribution of the product. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input geographical distribution data of the product into a generating AI and have the generating AI perform the judgment.

[0103] The judgment unit can improve the accuracy of its judgment by referring to relevant literature on the product during the judgment process. For example, the judgment unit can determine the quality based on relevant literature on the product. The judgment unit can also determine the condition of the product by referring to relevant literature. Furthermore, the judgment unit can determine whether a product is eligible for return based on relevant literature. In this way, the accuracy of the judgment can be improved by referring to relevant literature on the product. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input relevant literature data on the product into a generating AI and have the generating AI perform the task of improving the accuracy of the judgment.

[0104] The decision unit can estimate the user's emotions and adjust the way the decision is displayed based on the estimated emotions. For example, if the user is dissatisfied, the decision unit can provide a polite display method. The decision unit can also provide a normal display method if the user is satisfied. Furthermore, if the user is in a hurry, the decision unit can provide a concise display method. By adjusting the way the decision is displayed according to the user's emotions, the results can be conveyed in a more appropriate way. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the decision unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input user emotion data into the generating AI and have the generating AI adjust how the decision is displayed.

[0105] The decision-making unit can predict the current decision by referring to past decision data when making a decision. For example, the decision-making unit predicts the current decision based on past decision data. The decision-making unit can also analyze past decision patterns to make the optimal decision. For example, the decision-making unit analyzes past decision patterns to make the optimal decision. Furthermore, the decision-making unit can improve the accuracy of the current decision by referring to past decision data. For example, the decision-making unit improves the accuracy of the current decision by referring to past decision data. In this way, the accuracy of the current decision can be improved by referring to past decision data. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input past decision data into a generating AI and have the generating AI perform a prediction of the current decision.

[0106] The decision-making unit can apply different decision-making analysis methods to each product category when making a decision. For example, the decision-making unit can apply different decision-making analysis methods depending on the product category. For example, the decision-making unit can apply different decision-making analysis methods depending on the product category. The decision-making unit can also make the optimal decision by considering the characteristics of each category. For example, the decision-making unit can make the optimal decision by considering the characteristics of each category. Furthermore, the decision-making unit can make a decision by applying different algorithms based on the product category. For example, the decision-making unit can make a decision by applying different algorithms based on the product category. This allows for more appropriate decisions to be made by applying different decision-making analysis methods to each product category. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input product category data into a generating AI and have the generating AI execute the application of decision-making analysis methods.

[0107] The decision-making unit can estimate the user's emotions and adjust the importance of the decision based on the estimated emotions. For example, if the user is dissatisfied, the decision-making unit can set the importance to high and make a decision. For example, if the user is dissatisfied, the decision-making unit can set the importance to high and make a decision. For example, if the user is satisfied, the decision-making unit can make a decision to the normal level of importance. For example, if the user is in a hurry, the decision-making unit can set the importance to low and make a decision quickly. For example, if the user is in a hurry, the decision-making unit can set the importance to low and make a decision quickly. In this way, by adjusting the importance of the decision according to the user's emotions, decisions can be made with a more appropriate level of importance. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input user emotion data into the generating AI and have the generating AI adjust the importance of the decision.

[0108] The decision unit can analyze changes in judgment based on the product submission timing when making a decision. For example, the decision unit can analyze changes in judgment based on the product submission timing. The decision unit can also analyze decision patterns for each submission timing to make the optimal decision. For example, the decision unit can analyze decision patterns for each submission timing to make the optimal decision. Furthermore, the decision unit can predict changes in judgment depending on the submission timing. For example, the decision unit can predict changes in judgment depending on the submission timing. This allows for more appropriate decisions to be made by analyzing changes in judgment based on the product submission timing. Some or all of the above processing in the decision unit may be performed using AI, for example, or without AI. For example, the decision unit can input product submission timing data into a generating AI and have the generating AI perform the analysis of changes in judgment.

[0109] The decision-making unit can analyze its decision by referring to relevant market data for the product. For example, the decision-making unit can analyze its decision based on relevant market data for the product. The decision-making unit can also determine the quality of the product by referring to market data. For example, the decision-making unit can determine the quality of the product by referring to market data. Furthermore, the decision-making unit can determine whether a return is possible based on market data. For example, the decision-making unit can determine whether a return is possible based on market data. This allows for more appropriate decisions to be made by referring to relevant market data for the product. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input relevant market data for the product into a generating AI and have the generating AI perform the analysis of the decision.

[0110] The execution unit can estimate the user's emotions and determine the priority of the processes to be executed based on the estimated user emotions. For example, if the user is dissatisfied, the execution unit will prioritize the process that the user is dissatisfied with. The execution unit can also execute processes with the normal priority if the user is satisfied. Furthermore, if the user is in a hurry, the execution unit will prioritize that process. In this way, by determining the priority of the processes to be executed according to the user's emotions, processes can be executed in a more appropriate order. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processes in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input user emotion data into the generating AI and have the generating AI determine the processing priorities.

[0111] The execution unit can improve the accuracy of execution by considering the interrelationships between products during execution. For example, the execution unit can perform execution by considering the interrelationships between products in the same category. The execution unit can also perform execution based on the interrelationships between similar products. Furthermore, the execution unit can analyze the interrelationships between products and perform the optimal execution. In this way, the accuracy of execution can be improved by considering the interrelationships between products. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input product interrelationship data into a generating AI and have the generating AI perform the execution accuracy improvement.

[0112] The execution unit can perform actions while considering the attribute information of the product submitter. For example, the execution unit can perform actions while considering the submitter's age and gender. The execution unit can also perform actions based on the submitter's past purchase history. Furthermore, the execution unit can also perform actions while considering the submitter's regional information. This allows for more appropriate execution by considering the attribute information of the product submitter. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input the submitter's attribute information data into a generating AI and have the generating AI perform the execution.

[0113] The execution unit can estimate the user's emotions and adjust how the process to be executed is displayed based on the estimated user emotions. For example, if the user is dissatisfied, the execution unit can provide a polite display method. The execution unit can also provide a normal display method if the user is satisfied. For example, if the user is satisfied, the execution unit can provide a normal display method. Furthermore, if the user is in a hurry, the execution unit can provide a concise display method. For example, if the user is in a hurry, the execution unit can provide a concise display method. By adjusting how the process to be executed is displayed according to the user's emotions, results can be conveyed in a more appropriate display method. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input user emotion data into the generating AI and have the generating AI adjust how the processing is displayed.

[0114] The execution unit can perform actions while considering the geographical distribution of the products. For example, the execution unit can perform optimal actions based on the geographical distribution of the products. The execution unit can also perform actions on product quality based on geographical distribution. Furthermore, the execution unit can also determine whether or not a product is eligible for return, taking geographical distribution into consideration. This allows for more appropriate actions by considering the geographical distribution of the products. Some or all of the above-described processes in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input geographical distribution data of the products into a generating AI and have the generating AI perform the actions.

[0115] The execution unit can improve the accuracy of its execution by referring to relevant literature on the product during execution. For example, the execution unit can perform quality checks based on relevant literature on the product. The execution unit can also perform condition checks based on relevant literature. Furthermore, the execution unit can determine whether a product is eligible for return based on relevant literature. In this way, the accuracy of the execution can be improved by referring to relevant literature on the product. Some or all of the above processing in the execution unit may be performed using AI, for example, or without AI. For example, the execution unit can input relevant literature data on the product into a generating AI and have the generating AI perform the improvement of execution accuracy.

[0116] The analysis unit can estimate the user's emotions and select analysis data based on the estimated emotions. For example, if the user is dissatisfied, the analysis unit will prioritize analyzing data related to that emotion. The analysis unit can also analyze normal data if the user is satisfied. Furthermore, if the user is in a hurry, the analysis unit can select data that can be analyzed quickly. By selecting analysis data according to the user's emotions, more appropriate data can be analyzed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI select the data to be analyzed.

[0117] The analysis unit can optimize its analysis algorithm by referring to past analysis data during the analysis process. For example, the analysis unit can optimize the current analysis algorithm based on past analysis data. The analysis unit can also analyze past analysis patterns and apply the most suitable algorithm. Furthermore, the analysis unit can improve the accuracy of the current analysis by referring to past analysis data. For example, the analysis unit can improve the accuracy of the current analysis by referring to past analysis data. This allows the accuracy of the current analysis to be improved by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0118] The analysis unit can estimate the user's emotions and adjust the frequency of analysis based on the estimated emotions. For example, if the user is dissatisfied, the analysis unit will perform analyses more frequently. For example, if the user is dissatisfied, the analysis unit will perform analyses more frequently. For example, if the user is satisfied, the analysis unit will perform analyses at a normal frequency. Furthermore, if the user is in a hurry, the analysis unit will perform analyses quickly. For example, if the user is in a hurry, the analysis unit will perform analyses quickly. This allows for more appropriate analysis frequency by adjusting the frequency of analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the frequency of analysis.

[0119] The analysis department can weight the analysis data based on when the return reasons were submitted. For example, if the return reasons were submitted early, the analysis department can assign a higher weight to that data for analysis. The analysis department can also perform the analysis with normal weights if the return reasons were submitted at the normal submission time. Furthermore, the analysis department can assign a lower weight to the data if the return reasons were submitted late. This allows for a more appropriate analysis by weighting the analysis data based on when the return reasons were submitted. Some or all of the above processing in the analysis department may be performed using AI, for example, or without AI. For example, the analysis department can input the return reason submission time data into a generating AI and have the generating AI perform the weighting of the analysis data.

[0120] The research department can estimate the user's emotions and adjust the research advice based on the estimated emotions. For example, if the user is dissatisfied, the research department can provide careful advice. For example, if the user is dissatisfied, the research department can provide careful advice. The research department can also provide standard advice if the user is satisfied. For example, if the research department is satisfied, the research department can provide standard advice. Furthermore, if the user is in a hurry, the research department can provide concise advice. For example, if the research department is in a hurry, the research department can provide concise advice. This allows for more appropriate advice to be provided by adjusting the research advice according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research department may be performed using AI or not using AI. For example, the research department can input user emotion data into a generative AI and have the generative AI adjust the research advice.

[0121] The research department can provide optimal advice by referring to the user's past research history when advising on research. For example, the research department can provide optimal advice based on the user's past research history. The research department can also provide optimal advice by analyzing past research patterns. For example, the research department can provide optimal advice by analyzing past research patterns. Furthermore, the research department can improve the accuracy of the current research by referring to past research history. For example, the research department can improve the accuracy of the current research by referring to past research history. This allows the research department to provide more appropriate advice by referring to the user's past research history. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input the user's past research history data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0122] The research department can estimate the user's emotions and determine the priority of the research based on the estimated user emotions. For example, if the research department is dissatisfied, it will prioritize that research. For example, if the research department is dissatisfied, it will prioritize that research. For example, if the research department is satisfied, it will prioritize that research. For example, if the research department is satisfied, it will prioritize that research. Furthermore, if the research department is in a hurry, it will prioritize that research. For example, if the research department is in a hurry, it will prioritize that research. In this way, by determining the priority of the research according to the user's emotions, the research can be conducted in a more appropriate order. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input user sentiment data into a generative AI and have the AI ​​determine the priorities of the research.

[0123] The research department can provide optimal advice by considering the user's device information when providing research advice. For example, if the user is using a smartphone, the research department can provide advice tailored to the screen size. For example, if the user is using a tablet, the research department can provide advice optimized for a larger screen. For example, if the user is using a tablet, the research department can provide advice optimized for a larger screen. Furthermore, if the user is using a smartwatch, the research department can provide concise and easy-to-read advice. For example, if the user is using a smartwatch, the research department can provide concise and easy-to-read advice. This allows for the provision of more appropriate advice by considering the user's device information. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can input user device information data into a generating AI and have the generating AI provide optimal advice.

[0124] The delivery unit can estimate the user's emotions and adjust the delivery method based on the estimated emotions. For example, if the user is dissatisfied, the delivery unit can provide an expedited delivery method. For example, if the user is dissatisfied, the delivery unit can provide an expedited delivery method. The delivery unit can also provide a standard delivery method if the user is satisfied. For example, if the delivery unit is satisfied, the delivery unit can provide a standard delivery method. Furthermore, if the user is in a hurry, the delivery unit can provide the fastest possible delivery method. For example, if the delivery unit is in a hurry, the delivery unit can provide the fastest possible delivery method. This allows for more appropriate delivery by adjusting the delivery method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery department can input user emotion data into a generating AI and have the AI ​​adjust the delivery method.

[0125] The delivery department can select the optimal delivery method by referring to the user's past delivery history during delivery. For example, the delivery department can select the optimal delivery method based on the user's past delivery history. The delivery department can also analyze past delivery patterns and propose the optimal delivery method. Furthermore, the delivery department can improve the accuracy of current deliveries by referring to past delivery history. For example, the delivery department can improve the accuracy of current deliveries by referring to past delivery history. This allows for the selection of a more appropriate delivery method by referring to the user's past delivery history. Some or all of the above processes in the delivery department may be performed using AI, for example, or without AI. For example, the delivery department can input the user's past delivery history data into a generating AI and have the generating AI select the optimal delivery method.

[0126] The delivery unit can estimate the user's emotions and determine delivery priorities based on those emotions. For example, if the user is dissatisfied, the delivery unit will prioritize that delivery. The delivery unit can also prioritize deliveries at the normal priority level if the user is satisfied. Furthermore, if the user is in a hurry, the delivery unit can give that delivery the highest priority. This allows for deliveries to be made in a more appropriate order by determining delivery priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery department can input user emotion data into a generative AI and have the AI ​​determine delivery priorities.

[0127] The delivery unit can select the optimal delivery method by considering the user's geographical location information during delivery. For example, the delivery unit can select the optimal delivery method based on the user's geographical location information. The delivery unit can also provide the fastest delivery method based on geographical location information. Furthermore, the delivery unit can propose the optimal delivery route by considering geographical location information. For example, the delivery unit proposes the optimal delivery route by considering geographical location information. This allows for the selection of a more appropriate delivery method by considering the user's geographical location information. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input the user's geographical location data into a generating AI and have the generating AI select the optimal delivery method.

[0128] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0129] The reception desk can improve the accuracy of user input by referring to the user's past purchase history. For example, the reception desk can suggest input options based on information about products the user has purchased in the past. It can also prioritize displaying information about frequently returned items based on the user's past purchase history. Furthermore, the reception desk can analyze the user's past purchase history and provide an auto-completion function for input. This improves the accuracy of user input and streamlines the reception process.

[0130] The discrimination unit can estimate the user's emotions and adjust the method for determining the reason for return based on those emotions. For example, if the user is dissatisfied, the discrimination unit will ask detailed questions to accurately understand the reason for return. If the user is satisfied, the discrimination unit can also ask concise questions to quickly determine the reason for return. Furthermore, if the user is in a hurry, the discrimination unit can focus on the most important questions. By adjusting the method for determining the reason for return according to the user's emotions, a more appropriate determination can be made.

[0131] The judgment unit can refer to quality assurance data provided by the product manufacturer when determining the condition of a product. For example, the judgment unit can determine the condition of a product in detail based on the quality assurance data provided by the product manufacturer. Furthermore, the judgment unit can also make a determination that takes into account the product's usage and storage conditions, based on the quality assurance data. In addition, the judgment unit can refer to the quality assurance data to provide additional information about the product's condition. This allows for a more accurate determination of the product's condition.

[0132] The decision-making unit can estimate the user's emotions when determining whether a return or refund is possible, and adjust the decision criteria based on those emotions. For example, if the user is dissatisfied, the decision-making unit will make a decision using strict criteria. If the user is satisfied, the decision-making unit can also make a decision using normal criteria. Furthermore, if the user is in a hurry, the decision-making unit can make a decision using rapid criteria. By adjusting the decision criteria according to the user's emotions, a more appropriate decision can be made.

[0133] The execution unit can select the optimal processing method by referring to the user's past return history when performing refund or exchange processing. For example, the execution unit can propose the most suitable refund method based on information about products the user has returned in the past. Furthermore, the execution unit can prioritize the execution of exchange methods for frequently returned items based on past return history. In addition, the execution unit can analyze the user's past return history and automate refund and exchange processing. This improves the efficiency of refund and exchange processing.

[0134] The reception desk can estimate the user's emotions and adjust the timing of the reception based on those estimates. For example, if the user is feeling stressed, the reception can be delayed to allow the user to relax. Conversely, if the user is in a hurry, the reception can be sped up for a quicker response. Furthermore, if the user is feeling anxious, the reception can be adjusted to provide reassurance. By adjusting the reception timing according to the user's emotions, reception can be conducted at a more appropriate time.

[0135] The discrimination unit can analyze user input using natural language processing technology when determining the reason for a return. For example, the discrimination unit can analyze text data entered by the user using natural language processing technology and automatically extract the reason for the return. Furthermore, the discrimination unit can use natural language processing technology to understand the context of the user's input and determine a more accurate reason for the return. In addition, the discrimination unit can use natural language processing technology to fill in ambiguous parts of the user's input. This improves the accuracy of determining the reason for a return.

[0136] The judgment unit can estimate the user's emotions when determining the condition of a product and adjust the way the judgment is expressed based on the estimated emotions. For example, if the user is dissatisfied, the judgment unit will convey the result in polite language. If the user is satisfied, it can convey the result in normal language. Furthermore, if the user is in a hurry, it can convey the result in concise language. In this way, by adjusting the way the judgment is expressed according to the user's emotions, the judgment can be conveyed in a more appropriate manner.

[0137] The execution unit can select the optimal processing method when performing refund or exchange processing, taking into account the user's geographical location. For example, if the user lives nearby, the execution unit will prioritize processing their return. If the user lives far away, it can process the return with the normal priority. Furthermore, the execution unit can suggest the most suitable refund or exchange method based on the user's geographical location. This allows for the selection of a more appropriate processing method by considering the user's geographical location.

[0138] The execution unit can estimate the user's emotions when performing refund or exchange processing and determine the processing priority based on the estimated emotions. For example, if the user is dissatisfied, that processing will be given priority. If the user is satisfied, it can be performed with the normal priority. Furthermore, if the user is in a hurry, that processing can be given the highest priority. In this way, by determining the processing priority according to the user's emotions, processing can be performed in a more appropriate order.

[0139] The following briefly describes the processing flow for example form 2.

[0140] Step 1: The reception desk receives customer input. Customer input includes text input, selection from multiple-choice options, and voice input. For example, the reception desk can receive text data entered by the customer, data selected from multiple-choice options, and data entered by voice. Step 2: The discrimination unit determines the reason for return based on the information received by the reception unit. Reasons for return include product defects, ordering mistakes, and customer convenience. For example, the discrimination unit can determine product defects, ordering mistakes, and customer convenience as reasons for return. Step 3: The determination unit determines the condition of the product based on the reason for return determined by the discrimination unit. The condition of the product includes external damage, malfunction, and signs of use. For example, the determination unit can determine external damage, malfunction, and signs of use. Step 4: The judgment unit determines whether a return and refund are possible based on the condition of the product determined by the assessment unit. Factors in determining whether a return and refund are possible include the return policy, the condition of the product, and the number of days elapsed since the purchase date. For example, the judgment unit can determine whether a return and refund are possible based on the return policy, the condition of the product, and the number of days elapsed since the purchase date. Step 5: The execution unit performs the refund or exchange process based on the result determined by the decision unit. The refund or exchange process includes the refund method and the procedure for shipping the replacement product. For example, the execution unit can perform the refund process according to the refund method and the exchange process according to the procedure for shipping the replacement product.

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0143] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the reception unit, discrimination unit, determination unit, decision unit, and execution unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives customer input. The discrimination unit is implemented by the identification processing unit 290 of the data processing device 12 and determines the reason for return based on the content received by the reception unit. The decision unit is implemented by the control unit 46A of the smart device 14 and determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit is implemented by the identification processing unit 290 of the data processing device 12 and determines whether a return and refund are possible based on the condition of the product determined by the decision unit. The execution unit is implemented by the control unit 46A of the smart device 14 and executes a refund or exchange process based on the result determined by the decision unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0145] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0146] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0148] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

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

[0152] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0155] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0157] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the reception unit, discrimination unit, determination unit, decision unit, and execution unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives customer input. The discrimination unit is implemented by the identification processing unit 290 of the data processing device 12 and determines the reason for return based on the content received by the reception unit. The decision unit is implemented by the control unit 46A of the smart glasses 214 and determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit is implemented by the identification processing unit 290 of the data processing device 12 and determines whether a return and refund are possible based on the condition of the product determined by the decision unit. The execution unit is implemented by the control unit 46A of the smart glasses 214 and executes a refund or exchange process based on the result determined by the decision unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0161] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0162] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0164] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

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

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

[0168] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the reception unit, discrimination unit, determination unit, decision unit, and execution unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives customer input. The discrimination unit is implemented by the specific processing unit 290 of the data processing unit 12 and determines the reason for return based on the content received by the reception unit. The decision unit is implemented by the control unit 46A of the headset terminal 314 and determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and determines whether a return and refund are possible based on the condition of the product determined by the decision unit. The execution unit is implemented by the control unit 46A of the headset terminal 314 and executes a refund or exchange process based on the result determined by the decision unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0177] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0178] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0179] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0180] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0181] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0182] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0183] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0184] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0185] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0186] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0187] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0188] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0189] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0190] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0191] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0192] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0193] Each of the multiple elements described above, including the reception unit, discrimination unit, determination unit, decision unit, and execution unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives customer input. The discrimination unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and determines the reason for return based on the content received by the reception unit. The decision unit is implemented by, for example, the control unit 46A of the robot 414 and determines the condition of the product based on the reason for return determined by the discrimination unit. The decision unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and determines whether a return and refund are possible based on the condition of the product determined by the decision unit. The execution unit is implemented by, for example, the control unit 46A of the robot 414 and executes a refund or exchange process based on the result determined by the decision unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0194] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0195] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0196] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0197] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0198] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0199] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0200] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0201] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0202] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0203] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0204] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0205] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0206] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0207] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0208] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0209] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0210] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0211] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0212] (Note 1) A reception desk that receives customer input, A determination unit that determines the reason for return based on the information received by the aforementioned reception unit, A determination unit that determines the condition of the product based on the reason for return determined by the aforementioned determination unit, A determination unit that determines whether a return and refund are possible based on the condition of the product determined by the aforementioned determination unit, The system includes an execution unit that performs refund or exchange processing based on the results determined by the aforementioned determination unit. A system characterized by the following features. (Note 2) We have an analytics department that analyzes data on return reasons and customer attributes. The system described in Appendix 1, characterized by the features described herein. (Note 3) The company has a research department that conducts customer satisfaction surveys. The system described in Appendix 1, characterized by the features described herein. (Note 4) It has a delivery department that communicates with delivery companies. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned discrimination unit is The condition of a product is determined using image recognition technology. The system described in Appendix 1, characterized by the features described herein. (Note 6) The execution unit is, We will process refunds or exchanges based on the reason for return. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of the reception based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past return history to select the most suitable return processing method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is During registration, filtering is performed based on the user's current purchase history and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the user's emotions and determines the priority of returns to be accepted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When processing a return, the system prioritizes processing returns that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is At the time of processing, the system analyzes the user's social media activity and processes related returns. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned discrimination unit is The system estimates the user's emotions and adjusts the way the discrimination is expressed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned discrimination unit is During the review process, the level of detail in the review is adjusted based on the importance of the reason for return. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned discrimination unit is When determining the reason for return, a different determination algorithm is applied depending on the category of the reason for return. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned discrimination unit is The system estimates the user's emotions and adjusts the length of the decision based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned discrimination unit is When determining the return, the priority of the determination will be based on when the reason for return was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned discrimination unit is During the review process, the order of review will be adjusted based on the relevance of the return reasons. The system described in Appendix 1, characterized by the features described herein. (Note 19) The determination unit, The system estimates the user's emotions and adjusts the criteria for judgment based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The determination unit, When making a judgment, we improve the accuracy of the judgment by considering the interrelationships between products. The system described in Appendix 1, characterized by the features described herein. (Note 21) The determination unit, When making a decision, the attribute information of the person who submitted the product will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The determination unit, It estimates the user's emotions and adjusts the order in which the judgment results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The determination unit, When making a decision, the geographical distribution of the products is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The determination unit, When making a determination, we refer to relevant literature on the product to improve the accuracy of the determination. The system described in Appendix 1, characterized by the features described herein. (Note 25) The unit that makes the determination said, It estimates the user's emotions and adjusts how decisions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The unit that makes the determination said, When making a decision, refer to past decision data to predict the current decision. The system described in Appendix 1, characterized by the features described herein. (Note 27) The unit that makes the determination said, When making a decision, different decision-making and analysis methods are applied to each product category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The unit that makes the determination said, It estimates the user's emotions and adjusts the importance of decisions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The unit that makes the determination said, When making a decision, we analyze how the decision might change based on when the product was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The unit that makes the determination said, When making a decision, we analyze the decision by referring to relevant market data for the product. The system described in Appendix 1, characterized by the features described herein. (Note 31) The execution unit is, It estimates the user's emotions and determines the priority of actions to perform based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The execution unit is, During execution, the system improves execution accuracy by considering the interrelationships between products. The system described in Appendix 1, characterized by the features described herein. (Note 33) The execution unit is, During execution, the system will take into account the attribute information of the product submitter. The system described in Appendix 1, characterized by the features described herein. (Note 34) The execution unit is, We estimate the user's emotions and adjust how the actions performed based on those emotions are displayed. The system described in Appendix 1, characterized by the features described herein. (Note 35) The execution unit is, During execution, the geographical distribution of the products will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 36) The execution unit is, During execution, the system references relevant literature related to the product to improve execution accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned analysis unit is The system estimates the user's emotions and selects analysis data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned analysis unit is During analysis, the analysis algorithm is optimized by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned analysis unit is It estimates the user's sentiment and adjusts the frequency of analysis based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned analysis unit is During the analysis, the analysis data is weighted based on when the return reason was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned investigation department, We estimate user sentiment and adjust research advice based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned investigation department, When providing advice on a survey, we refer to the user's past survey history to provide the most suitable advice. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned investigation department, We estimate user sentiment and determine research priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned investigation department, When providing advice during the investigation, we take the user's device information into consideration to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned delivery department, The system estimates the user's emotions and adjusts the delivery method based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned delivery department, During delivery, the system selects the most suitable delivery method by referring to the user's past delivery history. The system described in Appendix 1, characterized by the features described herein. (Note 47) The aforementioned delivery department, The system estimates the user's emotions and determines delivery priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 48) The aforementioned delivery department, During delivery, the system selects the optimal delivery method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that receives customer input, A determination unit that determines the reason for return based on the information received by the aforementioned reception unit, A determination unit that determines the condition of the product based on the reason for return determined by the aforementioned determination unit, A determination unit that determines whether a return and refund are possible based on the condition of the product determined by the aforementioned determination unit, The system includes an execution unit that performs refund or exchange processing based on the results determined by the aforementioned determination unit. A system characterized by the following features.

2. We have an analytics department that analyzes data on return reasons and customer attributes. The system according to feature 1.

3. The company has a research department that conducts customer satisfaction surveys. The system according to feature 1.

4. It has a delivery department that communicates with delivery companies. The system according to feature 1.

5. The aforementioned discrimination unit is The condition of a product is determined using image recognition technology. The system according to feature 1.

6. The execution unit is, We will process refunds or exchanges based on the reason for return. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of the reception based on those emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the user's past return history to select the most suitable return processing method. The system according to feature 1.

9. The aforementioned reception unit is During registration, filtering is performed based on the user's current purchase history and areas of interest. The system according to feature 1.

Images