system

Abstract

We provide the system. [Solution] A means for receiving customer inquiries, A means of analyzing the content of received inquiries and classifying them into the appropriate category, A means of routing inquiries to the person in charge who corresponds to the category, A means of sending the response from the person in charge to the customer, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional customer support system, there are different counters for each product, and customers often get confused about which counter to inquire when making an inquiry. In addition, the load distribution among the persons in charge is insufficient, resulting in a problem of reduced customer satisfaction. The present invention aims to solve these problems, improve customer satisfaction by enabling customers to make inquiries through only one counter, and efficiently distribute the load of the persons in charge.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving customer inquiries, means for analyzing the received inquiries and classifying them into the appropriate categories, means for routing inquiries to the appropriate personnel in charge of the categories, and means for sending the responses from the personnel to the customers. Specifically, by analyzing the inquiry content using natural language processing technology and automatically routing it to the appropriate personnel, an efficient system is realized for both customers and personnel.

[0006] A "customer" is someone who uses the system to make an inquiry.

[0007] "Inquiry details" refer to the information of questions and requests that customers submit through the system.

[0008] "Means of receiving" refers to functions provided by a system to receive information from external sources.

[0009] "Means of analysis" refers to functions used to decode received information and understand its meaning.

[0010] A "means of classification" refers to a function for sorting analyzed information into specific categories.

[0011] "Routing means" refers to the function of sending classified information to the appropriate person in charge.

[0012] A "person in charge" is someone who handles inquiries according to their classification.

[0013] "Means of transmission" refers to the function used by the person in charge to send response information to the customer.

[0014] A "category" is a classification item used to organize and manage inquiries.

[0015] "Natural language processing technology" is the technology that enables computers to understand human language. [Brief explanation of the drawing]

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0028] 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.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] The 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.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system has the functionality to receive customer inquiries, analyze them, route them to the appropriate person in charge, and finally send the answer to the customer.

[0038] User actions

[0039] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0040] Server Processing

[0041] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0042] The server then selects the appropriate person to handle the inquiry based on the classified category and routes the inquiry to that person. The list of persons is pre-registered within the server, and the person in charge for each category is defined. For example, an inquiry in the "New Product Support" category will be routed to the new product support person.

[0043] Operation by the person in charge

[0044] The person using the terminal receives a notification from the server and checks the content of the inquiry. The person checks the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates a response saying, "Please check the following steps for how to use the new product," and sends it to the user via the server.

[0045] User reception

[0046] The user receives a response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user can also submit additional questions.

[0047] Specific example

[0048] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it under "repair services." It then routes the inquiry to the appropriate representative, who creates and responds with appropriate repair service information. This process is repeated until the user receives the response and the problem is resolved.

[0049] In this way, the system of the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0053] Step 2:

[0054] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0055] Step 3:

[0056] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0057] Step 4:

[0058] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0059] Step 5:

[0060] The server selects the appropriate person in charge based on its classification category. The person in charge is chosen from a predefined list of persons in charge for each category. For example, a person in charge of the "New Product Support" category is selected.

[0061] Step 6:

[0062] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification.

[0063] Step 7:

[0064] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0065] Step 8:

[0066] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0067] Step 9:

[0068] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0069] Step 10:

[0070] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0071] Step 11:

[0072] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0073] In this way, by executing each processing step sequentially, the process from receiving the inquiry to providing the answer is carried out efficiently.

[0074] (Example 1)

[0075] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0076] To respond quickly and appropriately to customer inquiries, it is necessary to properly analyze incoming inquiries and route them to the appropriate personnel. However, in conventional systems, this process was often done manually, which was time-consuming and carried the risk of delays and errors in responses by personnel. This resulted in decreased customer satisfaction and negatively impacted the company's credibility.

[0077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0078] In this invention, the server includes means for receiving user-entered inquiry content, means for temporarily storing the received inquiry content, means for analyzing the stored inquiry content using natural language processing technology and classifying it into categories, means for selecting an appropriate person in charge based on the category and routing the inquiry, and means for sending the response created by the person in charge to the user. This enables rapid and accurate analysis of inquiry content and automatic routing to the appropriate person in charge, thereby improving customer satisfaction and reducing the workload on the person in charge.

[0079] A "user" is a person or entity that uses the system to submit a request.

[0080] "Inquiry content" refers to the text data of information and questions that a user sends to the server through the system.

[0081] "Means of receiving" refers to the methods and system components that allow the server to retrieve the content of inquiries sent by users.

[0082] "Means of temporary storage" refers to the method or system for storing received inquiry content in temporary data storage.

[0083] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human language, and specifically refers to algorithms and tools that perform text analysis and keyword extraction.

[0084] A "category" refers to the type or group of inquiry content, and is an area or section classified based on the analysis results.

[0085] A "person in charge" is a specialist or employee selected to handle inquiries in a specific category.

[0086] "Routing methods" refer to the methods and systems used to distribute inquiries to the appropriate personnel after analyzing the content.

[0087] A "response" is a solution or information that a representative creates based on an inquiry and provides to the user.

[0088] "Means of transmission" refers to the methods and systems used to deliver the responses prepared by the person in charge to the user.

[0089] A "server" is a central processing unit that receives user inquiries, analyzes them, routes them to the appropriate person, and sends the response.

[0090] Modes for carrying out the invention

[0091] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates a series of processes, including receiving customer inquiries, analyzing them, routing them to the appropriate personnel, and finally sending the answers to the customers.

[0092] Hardware and software configuration

[0093] server

[0094] The server will use a computer equipped with a high-performance processor and sufficient memory. Furthermore, it will utilize high-speed storage (e.g., Amazon S3, Google Cloud Storage) for temporary data storage. The server will also have software installed to implement natural language processing technologies (e.g., Google Cloud Natural Language API, Microsoft Azure Text Analytics).

[0095] terminal

[0096] The devices that users use to access the system are internet-connected devices such as personal computers and smartphones. These devices are equipped with a web browser and can access the system's web pages. Similarly, administrators also access the system using devices such as personal computers and tablets.

[0097] Inquiry reception and analysis

[0098] The user enters their inquiry in text format through their device's web browser and clicks the submit button. The server receives the inquiry sent from the user's device and temporarily stores it in storage. The stored data is analyzed using natural language processing techniques, and the content of the inquiry is classified into a specific category.

[0099] Category classification and routing

[0100] The server categorizes the analyzed query content and selects the appropriate person to handle it. A list of assigned personnel is pre-registered within the server, with each category defined accordingly. The server automatically routes the query to the appropriate person based on its category.

[0101] Create and submit your response.

[0102] The person in charge receives a notification from the server and reviews the inquiry. They create an appropriate response and send it back to the user via the server. The user receives the response on their device and checks if the problem has been resolved. If necessary, the user can resubmit the inquiry.

[0103] Specific example

[0104] For example, the following shows the specific process when a user submits an inquiry asking about repair services. The server analyzes the inquiry using the Google Cloud Natural Language API and categorizes it as "repair services." The server selects a person in charge of "repair services" and routes the inquiry to that person. The person in charge creates detailed information about the repair services and sends the response to the user. The user receives the response and checks whether the problem has been resolved.

[0105] Examples of prompt statements

[0106] An example of input to the AI ​​model generated by the system is, "Analyze the following inquiry and classify it into a category: 'I want to know about repair services.'" Using this prompt, the AI ​​model can appropriately analyze the inquiry and identify the category.

[0107] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0108] Step 1:

[0109] Users access the system's webpage using a browser on a device such as a PC or smartphone. They enter text such as "I don't know how to use the new product" into the inquiry form and click the submit button. The entered text data is sent to the server.

[0110] Step 2:

[0111] The server receives HTTP POST requests sent from the user's device. The received query content is temporarily stored in storage (e.g., Amazon S3 or Google Cloud Storage). The input is text data from the user, and the output is the data stored in temporary storage.

[0112] Step 3:

[0113] The server retrieves stored query data and performs analysis using natural language processing technology (e.g., Google Cloud Natural Language API). The input is stored text data, and the output is keyword and category information extracted as a result of the analysis. Specifically, it extracts the keyword "how to use the new product" from the text and classifies it into the "new product support" category.

[0114] Step 4:

[0115] The server categorizes queries into specific categories based on the analysis results. Inputs are keywords and analysis results, while output is category information. For example, a query like "I want to know about repair services" would be categorized as "repair services."

[0116] Step 5:

[0117] The server selects the appropriate contact person from a list of contact persons defined for each category and routes the inquiry to that contact person. The input is category information, and the output is routing information to the contact person. For example, an inquiry in the "New Product Support" category will be routed to the New Product Support contact person.

[0118] Step 6:

[0119] The person using the terminal receives a notification from the server and checks the content of the inquiry. The input is routing information sent from the server, and the output is the result of the person's confirmation. The person checks the content of the inquiry, which is "I don't know how to use the new product."

[0120] Step 7:

[0121] The person in charge creates an appropriate response to the inquiry they have received. The input is the inquiry, and the output is the response text. For example, the person in charge would write specific instructions such as "Please check the following steps for how to use the new product" and send the response to the server.

[0122] Step 8:

[0123] The server resends the response received from the person in charge to the user. The input is the response text created by the person in charge, and the output is the response sent to the user. The user receives the response on their terminal and checks whether the problem has been resolved. Specifically, the server sends the response to the user via an HTTP response.

[0124] Step 9:

[0125] The user reviews the response sent from the server on their device and evaluates whether the problem has been resolved. The input is the response text sent from the server, and the output is the user's evaluation result. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user will submit another question.

[0126] (Application Example 1)

[0127] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0128] Traditional customer support systems had the problem of requiring manual analysis and routing of inquiries, resulting in time-consuming processing. Furthermore, the lack of real-time inquiry support via smartphones made it difficult to improve customer satisfaction.

[0129] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0130] In this invention, the server includes means for receiving customer inquiries, means for analyzing the inquiry content and classifying it into the appropriate category, means for routing the inquiry to the person in charge corresponding to the category, means for sending the person in charge's response to the customer, means for inputting the inquiry using a terminal including a smartphone, means for the user to select a voice input option, means for the customer to send the inquiry through a smartphone application, and means for analyzing the inquiry content in real time. This enables quick and appropriate responses to inquiries.

[0131] A "customer" refers to a consumer who makes inquiries or purchases from a company or organization that provides services or products.

[0132] "Means for receiving inquiries" refers to devices or software used to receive questions and requests sent by customers.

[0133] "Means of analysis" refers to devices or software used to analyze the content of received inquiries and understand their purpose and intent.

[0134] "Means of categorization" refers to a device or software that classifies the analyzed query content as belonging to a specific category.

[0135] "Means for routing inquiries to the appropriate person" refers to a device or software that forwards inquiry content to the appropriate person based on its classified category.

[0136] "Means of sending responses from the person in charge to the customer" refers to a device or software that returns the response prepared by the person in charge to the customer.

[0137] "Means of entering inquiries using a device including a smartphone" refers to a device or method of entering inquiry details using a mobile device such as a smartphone.

[0138] "Means for users to select voice input options" refers to a device or software that provides users with the option to input their inquiry content by voice instead of text.

[0139] "Means by which customers submit inquiries via smartphone applications" refers to devices or software that allow customers to submit inquiries using a smartphone application.

[0140] "Means of real-time analysis" refers to a device or software that performs analysis the moment the inquiry is sent.

[0141] System Overview

[0142] This invention is a customer inquiry handling system designed to provide prompt and appropriate customer support. Its main components include a server, a customer terminal (e.g., a smartphone), and a staff terminal.

[0143] Program Overview

[0144] The server receives inquiries from customers and analyzes the content using natural language processing (NLP) techniques. The analyzed content is categorized and routed to the appropriate person in charge. The person in charge then sends their response back to the customer via the server.

[0145] Hardware and software configuration

[0146] Hardware:

[0147] Server: For example, a cloud server such as AWS® EC2.

[0148] Customer device: Smartphone (ANDROID® / iOS)

[0149] Personnel terminal: PC or smartphone

[0150] software:

[0151] Server-side: Flask (Python microframework), TextBlob (NLP library), JSON (data format)

[0152] Customer terminal: Smartphone application for sending inquiries

[0153] Processing flow

[0154] 1. Customer actions:

[0155] Users use their smartphones to input their inquiries as text or voice. For example, they might type, "I don't know how to use the new product," and then send it.

[0156] 2. Server processing:

[0157] The server receives customer inquiries and analyzes them in real time. Based on the analysis, inquiries are categorized, such as "New Product Support," and routed to the appropriate pre-registered representative. The server uses Flask to receive and analyze inquiries and TextBlob for natural language processing.

[0158] 3. Actions taken by the person in charge:

[0159] A notification arrives on the employee's terminal, and they check the inquiry details. The employee then creates a response based on the content and sends it to the customer via the server. For example, they might create specific instructions such as, "Please check the following steps for how to use the new product," and send the response.

[0160] 4. Customer receipt:

[0161] The customer receives a response from the representative and confirms whether the issue has been resolved. They can also contact the representative again if necessary.

[0162] Specific example

[0163] For example, if a user submits an inquiry stating, "I don't know how to use the new product," the server analyzes the content and categorizes it as "New Product Support." Then, a representative creates a specific response, such as "Please follow these steps to learn how to use the new product," and sends it to the user via the server.

[0164] Example of a prompt

[0165] "I don't know how to use the new product."

[0166] "I want to know about repair services."

[0167] In this way, the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0168] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0169] Program processing steps

[0170] Step 1:

[0171] User inquiry input

[0172] Users use their smartphones to enter their inquiries as text or voice.

[0173] Input: Inquiry content entered by the user on the smartphone application.

[0174] Output: The inquiry details are sent to the smartphone application and then forwarded to the server.

[0175] Specific action: The user types "I don't know how to use the new product" into their smartphone and presses the send button.

[0176] Step 2:

[0177] Server query received

[0178] The server receives the query content sent by the user.

[0179] Input: Inquiry content sent from a smartphone application

[0180] Output: The query content is temporarily stored on the server.

[0181] Specific operation: The server uses Flask to receive the query content sent by the user in JSON format.

[0182] Step 3:

[0183] Server query analysis

[0184] The server analyzes the received query content using natural language processing technology and classifies it into categories.

[0185] Input: Query content stored on the server

[0186] Output: Category as an analysis result (e.g., "New Product Support")

[0187] Specific operation: The server uses the TextBlob library to analyze the query content and classifies it into the "New Product Support" category based on the keyword "How to use the new product".

[0188] Step 4:

[0189] Server assignment routing

[0190] The server routes inquiries to the appropriate person based on the analyzed category.

[0191] Input: Inquiry content categorized

[0192] Output: Inquiry notification to the person in charge

[0193] Specific operation: The server selects a representative from the list of representatives who corresponds to the "New Product Support" category and forwards the inquiry details to the representative's terminal.

[0194] Step 5:

[0195] Confirmation of inquiries and creation of responses by the person in charge

[0196] After receiving the notification, the person in charge will review the inquiry and prepare a response.

[0197] Input: Inquiry details routed to the assigned representative.

[0198] Output: Created response content

[0199] Specific action: The person in charge will use a PC or smartphone to create a specific response such as, "Please check the following steps for instructions on how to use the new product."

[0200] Step 6:

[0201] Server response submission

[0202] The server receives the response prepared by the person in charge and sends it to the customer.

[0203] Input: Response sent by the person in charge

[0204] Output: Sending a response to the customer

[0205] Specific operation: The server receives the response from the person in charge and sends it to the customer via a smartphone application.

[0206] Step 7:

[0207] Receiving and confirming user responses

[0208] The user receives the response sent from the server and confirms it.

[0209] Input: Response sent from the server

[0210] Output: Problem solved or additional inquiry

[0211] Specific actions: The user opens the smartphone application, checks the response from the representative, and sends additional inquiries if necessary.

[0212] Through this series of processing steps, customer inquiries are addressed quickly and appropriately.

[0213] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0214] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system receives and analyzes customer inquiries, routes them to the appropriate personnel, and ultimately sends the response to the customer. Furthermore, by incorporating an emotion engine, this invention makes it possible to recognize user emotions and reflect them in prioritizing responses and selecting the appropriate personnel.

[0215] User actions

[0216] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0217] Server Processing

[0218] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0219] How the emotion engine works

[0220] The server then passes the received inquiry to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0221] Category classification and selection of responsible persons

[0222] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "New Product Support," it will assign a representative with particularly high responsiveness to users who appear confused.

[0223] Priority setting

[0224] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[0225] Routing to the responsible person

[0226] The server routes inquiries to the selected contact person. The routed inquiry details are then sent to the contact person's terminal. For example, the "New Product Support" person receives the notification and checks the inquiry details.

[0227] Operation by the person in charge

[0228] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow the instructions below for how to use the new product," and sends it to the user via the server.

[0229] User reception

[0230] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[0231] Specific example

[0232] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it as "repair services." If the emotion engine then detects that the user is experiencing anxiety, it prioritizes the inquiry and responds quickly. The inquiry is routed to the appropriate representative, who promptly provides the user with information about repair services. In this way, responses that consider the user's emotions become possible, leading to improved customer satisfaction.

[0233] The system of this invention automates a series of processes including receiving, analyzing, classifying, routing, sending responses, sentiment recognition, and prioritizing inquiries, thereby improving customer satisfaction and distributing the workload of staff.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0237] Step 2:

[0238] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0239] Step 3:

[0240] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0241] Step 4:

[0242] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0243] Step 5:

[0244] The server passes the query content to the emotion engine. The emotion engine analyzes the text content and recognizes the user's emotions (e.g., anger, frustration, joy). For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0245] Step 6:

[0246] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, it will be given a higher priority.

[0247] Step 7:

[0248] The server selects the most suitable representative based on the emotion engine's analysis results and categories. For example, for a user in the "New Product Support" category who is confused, a representative with particularly high responsiveness will be selected.

[0249] Step 8:

[0250] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification and checks the inquiry details.

[0251] Step 9:

[0252] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0253] Step 10:

[0254] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0255] Step 11:

[0256] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0257] Step 12:

[0258] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0259] Step 13:

[0260] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0261] In this way, by executing each processing step sequentially, the process from receiving inquiries to providing answers, and even recognizing user sentiment and prioritizing responses, is carried out efficiently.

[0262] (Example 2)

[0263] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0264] While there is a demand for prompt and appropriate responses to customer inquiries, traditional systems often rely on manual processes for analyzing inquiry content, recognizing sentiment, routing inquiries to the appropriate personnel, and prioritizing them, resulting in inefficiency. Furthermore, responses that do not consider customer emotions can lead to decreased customer satisfaction. This, in turn, presents challenges in terms of accuracy and speed in handling inquiries.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0266] In this invention, the server includes means for receiving inquiry content, means for analyzing the received inquiry content and classifying it into the appropriate category, means for sentiment analysis of the received inquiry content, means for setting response priorities based on the analysis results, means for routing the inquiry to the person in charge corresponding to the category and priority, and means for sending the response from the person in charge to the entity that made the inquiry. This enables automatic analysis of inquiry content, priority setting based on sentiment recognition, and automatic routing to the most suitable person in charge.

[0267] "Inquiry content" refers to text data such as questions, requests, and complaints that customers send to the system.

[0268] "Analysis" is the process of understanding, classifying, or evaluating the meaning and intent of a query using natural language processing techniques.

[0269] "Natural language processing technology" refers to the technology that enables computers to understand and process human language. Specifically, it includes text analysis, sentiment analysis, and semantic analysis.

[0270] A "category" is a group of inquiries that are classified based on a specific topic or theme. Examples include "new product support" and "repair services."

[0271] "Sentiment analysis" is the process of extracting and evaluating the user's emotions (e.g., joy, anger, confusion, dissatisfaction, etc.) contained in the inquiry content from text data.

[0272] "Priority" is a criterion used to determine the order in which inquiries are handled. Typically, it is set based on sentiment analysis results, and high-priority inquiries are handled more quickly.

[0273] A "person in charge" refers to a person or team responsible for handling a specific category or inquiry.

[0274] "Routing" is the process of automatically assigning inquiries to the appropriate person in charge based on analysis results and priority settings.

[0275] A "response" is text data containing information or solutions provided by the person in charge in response to an inquiry.

[0276] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates the reception, analysis, sentiment analysis, categorization, prioritization, routing to the appropriate person, and response transmission of inquiries. To implement this system, a high-performance server and terminals for users and staff are required.

[0277] System hardware and software configuration

[0278] The server requires a high-performance processor (e.g., an Intel Xeon processor) and large-capacity storage (e.g., an SSD). This server utilizes natural language processing technology to analyze query content and sentiment analysis. Specifically, it uses Python and libraries such as TENSORFLOW® and spaCy. Furthermore, it uses generative AI models such as GPT-3® for sentiment analysis.

[0279] Users and staff members need internet-connected devices such as personal computers or smartphones. Users access the system using a web browser (such as Google Chrome® or Safari), enter their inquiries, and submit them. Staff members receive inquiry notifications from the server using a web browser or a dedicated application.

[0280] System operation example

[0281] The user accesses the inquiry form through a web browser, enters, for example, "I don't know how to use the new product", and clicks the send button. This inquiry content is sent to the server and temporarily stored in cloud storage such as Amazon S3 or Google Cloud Storage. The stored data is analyzed by natural language processing technology using TensorFlow or spaCy and classified into the "New Product Support" category.

[0282] Next, the server passes the inquiry content to the sentiment engine and analyzes the user's sentiment using a generative AI model (e.g., GPT-3). For example, from the content "I don't know how to use the new product!", it is determined that the user is confused.

[0283] Based on the analysis results, the server sets the response priority of the inquiry content. A high priority is set for confused users, and a prompt response is required. Based on the category and priority, the inquiry content is automatically routed to the most appropriate person in charge. The person in charge receives the inquiry content through a dedicated application or email notification and responds promptly.

[0284] The person in charge checks the inquiry content and creates an appropriate answer. For example, create a specific answer such as "Please check the following procedures for how to use the new product" and send it to the user via the server. The user receives the answer sent from the server and the problem is solved.

[0285] Examples of prompt sentences

[0286] "Please create a system that analyzes the inquiry content from customers, classifies it into appropriate categories, performs sentiment analysis to set the priority of response, and routes it to the person in charge."

[0287] This system automates a series of processes including inquiry reception, analysis, sentiment recognition, category classification, priority setting, routing, and answer sending, achieving improved customer satisfaction and load distribution for the person in charge.

[0288] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0289] Step 1:

[0290] Users access the system using devices such as personal computers and smartphones. They access the inquiry form through a web browser (such as Google Chrome or Safari), enter their inquiry in text format, and click the submit button. For example, a user might enter "I don't know how to use the new product" and submit it. This action sends the inquiry to the server. The input is the user's text data, and the output is the data sent to the server.

[0291] Step 2:

[0292] The server receives user inquiries and temporarily stores them in cloud storage (such as Amazon S3 or Google Cloud Storage). After storage, it analyzes the inquiry content using natural language processing libraries such as TensorFlow or spaCy with Python code. As a result of the analysis, the inquiry content is classified into a specific category. For example, the keyword "How to use the new product" is classified into the "New Product Support" category. The input is the received text data, and the output is the analysis results and category classification data.

[0293] Step 3:

[0294] The server passes the received inquiry to the sentiment engine. The sentiment engine uses a generative AI model (e.g., GPT-3) to perform sentiment analysis on the inquiry. It recognizes the user's emotions (e.g., anger, confusion, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused. The input is the text data to be analyzed, and the output is the sentiment analysis result.

[0295] Step 4:

[0296] The server further classifies the inquiry content based on the NLP analysis results and sentiment analysis results, and assigns it to the appropriate category. For example, if it is classified under the "New Product Support" category, it selects a highly capable representative to assist the confused user. The input is category classification data and sentiment analysis data, and the output is information on the selection of the optimal representative.

[0297] Step 5:

[0298] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, the server will set a high priority for the response, requiring a quick response. The input is emotion analysis data, and the output is priority setting data.

[0299] Step 6:

[0300] The server routes inquiries to the designated contact person. The routing is automated, and notifications are sent to the contact person's device (e.g., laptop or desktop PC). For example, a "new product support" contact person receives the notification and checks the inquiry. Inputs include the contact person's selection information and the inquiry content, while output is the notification sent to the contact person.

[0301] Step 7:

[0302] The person using the terminal receives a notification from the server and displays the inquiry details. The person reviews the content and creates an appropriate response. For example, they might create a specific response such as, "Please follow the instructions below for how to use the new product," and send it back to the user via the server. The input consists of the inquiry and the response, and the output is the response data.

[0303] Step 8:

[0304] The user receives the answer sent from the server. The user checks the received answer and evaluates whether the problem has been solved. For example, if the user checks the detailed procedures of "how to use a new product" and feels that the problem has been solved, no additional inquiries are required. If necessary, the user can also input additional questions and resend them. The input is the received answer data, and the output is the user's evaluation and new inquiry data.

[0305] (Application Example 2)

[0306] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0307] In modern physical stores, it is extremely important to respond quickly and appropriately to customer inquiries in order to improve customer satisfaction. However, conventional inquiry response systems do not consider the customer's feelings and it is difficult to route inquiries to the appropriate person in charge. Therefore, even when customers feel dissatisfied or in urgent need, they are often not responded to promptly, which may lead to a decrease in customer satisfaction and a risk of damaging the store's reputation. To solve this problem, a system that considers the customer's feelings and priorities and optimally processes inquiries is necessary.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0309] In this invention, the server includes means for receiving the inquiry content from the customer, means for analyzing the received inquiry content and classifying it into the corresponding category, means for analyzing the inquiry content to recognize the customer's feelings, means for setting the priority of response based on the category and the recognized feelings, means for routing the inquiry to the person in charge corresponding to the category and according to the priority, and means for transmitting the answer from the person in charge to the customer. Thereby, it becomes possible to make a quick and appropriate response considering the customer's feelings and the priority of the inquiry in a physical store.

[0310] "Means for receiving customer inquiries" refers to the technical equipment that allows customers to input questions about products and services using devices such as smartphones or smart glasses within a physical store, and for a server to receive those inquiries.

[0311] "A means of analyzing received inquiries and classifying them into the appropriate category" refers to a system that uses natural language processing technology to analyze received text data and classify it into the appropriate category, such as product support or customer service, based on its content.

[0312] "Means of analyzing inquiry content to recognize customer emotions" refers to a function that uses natural language processing technology to automatically detect and recognize customer emotions (e.g., joy, dissatisfaction, confusion, etc.) from received text.

[0313] "Means for setting response priorities based on categories and perceived emotions" refers to a technology for evaluating the necessity and urgency of a response based on analyzed categories and customer emotion information, and for setting the priority of the response (high, medium, low, etc.).

[0314] "A means of routing inquiries to the appropriate person based on category and priority" refers to a system that automatically distributes inquiries to the most suitable person according to the set category and priority, and notifies the person's terminal.

[0315] "Means of sending responses from staff to customers" refers to the technical equipment used to send responses prepared by staff to customers, allowing customers to view the responses on devices such as smartphones or smart glasses.

[0316] "Natural language processing technology" refers to artificial intelligence technologies used for processing text data, such as analysis, classification, and sentiment recognition. Examples include libraries like TextBlob and NLTK.

[0317] "Customer emotions" refers to the emotional nuances of the words included in an inquiry, encompassing emotional states such as joy, anger, dissatisfaction, and confusion.

[0318] "Response priority" is an indicator that shows how quickly a customer inquiry needs to be addressed, and is expressed as a rank such as "high priority" or "low priority."

[0319] This invention is a system for responding quickly and appropriately to customer inquiries in physical stores. The system receives customer inquiries, analyzes them, routes them to the appropriate staff member, and finally sends the answer to the customer. Furthermore, by incorporating an emotion engine, it can recognize customer emotions and reflect them in prioritizing responses and selecting the appropriate staff member.

[0320] User actions

[0321] Users access the system using devices such as smartphones or smart glasses and enter their inquiries by scanning a QR code (registered trademark) in the store. The inquiries are entered in text format and sent to the server by clicking the send button. For example, a user might enter and send "I don't know how to use my new smartphone!"

[0322] Server Processing

[0323] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "How to use a new smartphone" might be classified into the "Product Support" category.

[0324] How the emotion engine works

[0325] The server then passes the received inquiry to the sentiment engine, which analyzes the user's emotions. The sentiment engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use my new smartphone!", it determines that the user is confused.

[0326] Category classification and selection of responsible persons

[0327] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "product support," it will assign a representative with particularly high responsiveness to users who appear confused.

[0328] Priority setting

[0329] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[0330] Routing to the responsible person

[0331] The server routes the inquiry to the selected person in charge. The routed inquiry is then notified to the person in charge's terminal. For example, the "product support" person receives the notification and checks the inquiry.

[0332] Operation by the person in charge

[0333] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow these steps for instructions on how to use your new smartphone," and sends it to the user via the server.

[0334] User reception

[0335] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions on "How to use your new smartphone" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[0336] Specific example

[0337] For example, a user in a store might type, "I don't know how to use my new smartphone!" The system categorizes this as "Product Support," recognizes the user's emotion as "Confused," and sets the priority to "High." It then sends a notification to the relevant staff member indicating "Urgent Support Needed" to encourage a quick response. An example of user input in this case is as follows:

[0338] I don't know how to use my new smartphone!

[0339] Through the above process, it becomes possible to provide prompt and appropriate responses in physical stores, taking into account customer emotions and the priority of inquiries.

[0340] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0341] Step 1:

[0342] Users scan a QR code in the store using their smartphone or smart glasses, enter their inquiry, and press the submit button. This input data is in text format and is sent to the server when the submit button is pressed.

[0343] Input: Inquiry details (text format)

[0344] Output: Query content sent to the server

[0345] Step 2:

[0346] The server receives the query content sent by the user and temporarily stores it in storage. This process makes the query content accessible within the server.

[0347] Input: Inquiry received from the user

[0348] Output: Query content stored in storage

[0349] Step 3:

[0350] The server analyzes the query data stored in storage using natural language processing (NLP) techniques. The analyzed data is then categorized into specific categories. For example, based on the keyword "How to use a new smartphone," it might be categorized as "product support."

[0351] Input: Query content stored in storage

[0352] Output: Inquiry content categorized

[0353] Step 4:

[0354] The server uses an emotion engine to recognize the user's emotions based on the analyzed query content. Specifically, it analyzes the context and vocabulary of the input text to identify the emotions the user is experiencing (e.g., confusion, anger, joy, etc.).

[0355] Input: Analyzed query content

[0356] Output: Recognized emotion information

[0357] Step 5:

[0358] The server prioritizes responses based on the results of category classification and sentiment recognition. For example, if the user is confused, it sets a high priority and clearly indicates that a prompt response is needed.

[0359] Input: Inquiry content categorized and recognized sentiment information

[0360] Output: Set response priority

[0361] Step 6:

[0362] The server selects the appropriate person in charge based on category and priority, and routes the inquiry to that person. A notification of the inquiry is sent to the person in charge's terminal. For example, a "product support" person receives the notification.

[0363] Input: Category, recognized emotion information, set response priority

[0364] Output: Inquiry notification sent to the person in charge

[0365] Step 7:

[0366] The person using the terminal receives a notification from the server, displays the inquiry details, and creates the necessary response. Once the response is complete, the person sends it to the server.

[0367] Input: Inquiry details notified to the person in charge

[0368] Output: Answer created by the person in charge

[0369] Step 8:

[0370] The server receives the response sent by the representative and forwards it to the customer. This is done by displaying the response on the customer's smartphone or smart glasses. This process allows the customer to verify the received response.

[0371] Input: Response received from the person in charge

[0372] Output: Response sent to the customer

[0373] Step 9:

[0374] The user receives the response sent from the server and evaluates whether the problem has been resolved. If necessary, the user may enter and resubmit additional inquiries.

[0375] Input: Response received from the server

[0376] Output: User ratings and additional inquiries (if applicable)

[0377] 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.

[0378] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0380] [Second Embodiment]

[0381] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0382] 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.

[0383] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0384] 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.

[0385] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0386] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0387] 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.

[0388] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0389] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0390] The 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.

[0391] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0392] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0393] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system has the functionality to receive customer inquiries, analyze them, route them to the appropriate person in charge, and finally send the answer to the customer.

[0394] User actions

[0395] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0396] Server Processing

[0397] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0398] The server then selects the appropriate person to handle the inquiry based on the classified category and routes the inquiry to that person. The list of persons is pre-registered within the server, and the person in charge for each category is defined. For example, an inquiry in the "New Product Support" category will be routed to the new product support person.

[0399] Operation by the person in charge

[0400] The person using the terminal receives a notification from the server and checks the content of the inquiry. The person checks the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates a response saying, "Please check the following steps for how to use the new product," and sends it to the user via the server.

[0401] User reception

[0402] The user receives a response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user can also submit additional questions.

[0403] Specific example

[0404] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it under "repair services." It then routes the inquiry to the appropriate representative, who creates and responds with appropriate repair service information. This process is repeated until the user receives the response and the problem is resolved.

[0405] In this way, the system of the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0406] The following describes the processing flow.

[0407] Step 1:

[0408] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0409] Step 2:

[0410] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0411] Step 3:

[0412] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0413] Step 4:

[0414] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0415] Step 5:

[0416] The server selects the appropriate person in charge based on its classification category. The person in charge is chosen from a predefined list of persons in charge for each category. For example, a person in charge of the "New Product Support" category is selected.

[0417] Step 6:

[0418] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification.

[0419] Step 7:

[0420] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0421] Step 8:

[0422] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0423] Step 9:

[0424] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0425] Step 10:

[0426] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0427] Step 11:

[0428] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0429] In this way, by executing each processing step sequentially, the process from receiving the inquiry to providing the answer is carried out efficiently.

[0430] (Example 1)

[0431] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0432] To respond quickly and appropriately to customer inquiries, it is necessary to properly analyze incoming inquiries and route them to the appropriate personnel. However, in conventional systems, this process was often done manually, which was time-consuming and carried the risk of delays and errors in responses by personnel. This resulted in decreased customer satisfaction and negatively impacted the company's credibility.

[0433] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0434] In this invention, the server includes means for receiving user-entered inquiry content, means for temporarily storing the received inquiry content, means for analyzing the stored inquiry content using natural language processing technology and classifying it into categories, means for selecting an appropriate person in charge based on the category and routing the inquiry, and means for sending the response created by the person in charge to the user. This enables rapid and accurate analysis of inquiry content and automatic routing to the appropriate person in charge, thereby improving customer satisfaction and reducing the workload on the person in charge.

[0435] A "user" is a person or entity that uses the system to submit a request.

[0436] "Inquiry content" refers to the text data of information and questions that a user sends to the server through the system.

[0437] "Means of receiving" refers to the methods and system components that allow the server to retrieve the content of inquiries sent by users.

[0438] "Means of temporary storage" refers to the method or system for storing received inquiry content in temporary data storage.

[0439] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human language, and specifically refers to algorithms and tools that perform text analysis and keyword extraction.

[0440] A "category" refers to the type or group of inquiry content, and is an area or section classified based on the analysis results.

[0441] A "person in charge" is a specialist or employee selected to handle inquiries in a specific category.

[0442] "Routing methods" refer to the methods and systems used to distribute inquiries to the appropriate personnel after analyzing the content.

[0443] A "response" is a solution or information that a representative creates based on an inquiry and provides to the user.

[0444] "Means of transmission" refers to the methods and systems used to deliver the responses prepared by the person in charge to the user.

[0445] A "server" is a central processing unit that receives user inquiries, analyzes them, routes them to the appropriate person, and sends the response.

[0446] Modes for carrying out the invention

[0447] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates a series of processes, including receiving customer inquiries, analyzing them, routing them to the appropriate personnel, and finally sending the answers to the customers.

[0448] Hardware and software configuration

[0449] server

[0450] The server will be a computer equipped with a high-performance processor and sufficient memory. Furthermore, it will utilize high-speed storage (e.g., Amazon S3, Google Cloud Storage) for temporary data storage. The server will also have software installed to implement natural language processing technologies (e.g., Google Cloud Natural Language API, Microsoft Azure Text Analytics).

[0451] terminal

[0452] The devices that users use to access the system are internet-connected devices such as personal computers and smartphones. These devices are equipped with a web browser and can access the system's web pages. Similarly, administrators also access the system using devices such as personal computers and tablets.

[0453] Inquiry reception and analysis

[0454] The user enters their inquiry in text format through their device's web browser and clicks the submit button. The server receives the inquiry sent from the user's device and temporarily stores it in storage. The stored data is analyzed using natural language processing techniques, and the content of the inquiry is classified into a specific category.

[0455] Category classification and routing

[0456] The server categorizes the analyzed query content and selects the appropriate person to handle it. A list of assigned personnel is pre-registered within the server, with each category defined accordingly. The server automatically routes the query to the appropriate person based on its category.

[0457] Create and submit your response.

[0458] The person in charge receives a notification from the server and reviews the inquiry. They create an appropriate response and send it back to the user via the server. The user receives the response on their device and checks if the problem has been resolved. If necessary, the user can resubmit the inquiry.

[0459] Specific example

[0460] For example, the following shows the specific process when a user submits an inquiry asking about repair services. The server analyzes the inquiry using the Google Cloud Natural Language API and categorizes it as "repair services." The server selects a person in charge of "repair services" and routes the inquiry to that person. The person in charge creates detailed information about the repair services and sends the response to the user. The user receives the response and checks whether the problem has been resolved.

[0461] Examples of prompt statements

[0462] An example of input to the AI ​​model generated by the system is, "Analyze the following inquiry and classify it into a category: 'I want to know about repair services.'" Using this prompt, the AI ​​model can appropriately analyze the inquiry and identify the category.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] Users access the system's webpage using a browser on a device such as a PC or smartphone. They enter text such as "I don't know how to use the new product" into the inquiry form and click the submit button. The entered text data is sent to the server.

[0466] Step 2:

[0467] The server receives HTTP POST requests sent from the user's device. The received query content is temporarily stored in storage (e.g., Amazon S3 or Google Cloud Storage). The input is text data from the user, and the output is the data stored in temporary storage.

[0468] Step 3:

[0469] The server retrieves stored query data and performs analysis using natural language processing technology (e.g., Google Cloud Natural Language API). The input is stored text data, and the output is keyword and category information extracted as a result of the analysis. Specifically, it extracts the keyword "how to use the new product" from the text and classifies it into the "new product support" category.

[0470] Step 4:

[0471] The server categorizes queries into specific categories based on the analysis results. Inputs are keywords and analysis results, while output is category information. For example, a query like "I want to know about repair services" would be categorized as "repair services."

[0472] Step 5:

[0473] The server selects the appropriate contact person from a list of contact persons defined for each category and routes the inquiry to that contact person. The input is category information, and the output is routing information to the contact person. For example, an inquiry in the "New Product Support" category will be routed to the New Product Support contact person.

[0474] Step 6:

[0475] The person using the terminal receives a notification from the server and checks the content of the inquiry. The input is routing information sent from the server, and the output is the result of the person's confirmation. The person checks the content of the inquiry, which is "I don't know how to use the new product."

[0476] Step 7:

[0477] The person in charge creates an appropriate response to the inquiry they have received. The input is the inquiry, and the output is the response text. For example, the person in charge would write specific instructions such as "Please check the following steps for how to use the new product" and send the response to the server.

[0478] Step 8:

[0479] The server resends the response received from the person in charge to the user. The input is the response text created by the person in charge, and the output is the response sent to the user. The user receives the response on their terminal and checks whether the problem has been resolved. Specifically, the server sends the response to the user via an HTTP response.

[0480] Step 9:

[0481] The user reviews the response sent from the server on their device and evaluates whether the problem has been resolved. The input is the response text sent from the server, and the output is the user's evaluation result. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user will submit another question.

[0482] (Application Example 1)

[0483] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0484] Traditional customer support systems had the problem of requiring manual analysis and routing of inquiries, resulting in time-consuming processing. Furthermore, the lack of real-time inquiry support via smartphones made it difficult to improve customer satisfaction.

[0485] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0486] In this invention, the server includes means for receiving customer inquiries, means for analyzing the inquiry content and classifying it into the appropriate category, means for routing the inquiry to the person in charge corresponding to the category, means for sending the person in charge's response to the customer, means for inputting the inquiry using a terminal including a smartphone, means for the user to select a voice input option, means for the customer to send the inquiry through a smartphone application, and means for analyzing the inquiry content in real time. This enables quick and appropriate responses to inquiries.

[0487] A "customer" refers to a consumer who makes inquiries or purchases from a company or organization that provides services or products.

[0488] "Means for receiving inquiries" refers to devices or software used to receive questions and requests sent by customers.

[0489] "Means of analysis" refers to devices or software used to analyze the content of received inquiries and understand their purpose and intent.

[0490] "Means of categorization" refers to a device or software that classifies the analyzed query content as belonging to a specific category.

[0491] "Means for routing inquiries to the appropriate person" refers to a device or software that forwards inquiry content to the appropriate person based on its classified category.

[0492] "Means of sending responses from the person in charge to the customer" refers to a device or software that returns the response prepared by the person in charge to the customer.

[0493] "Means of entering inquiries using a device including a smartphone" refers to a device or method of entering inquiry details using a mobile device such as a smartphone.

[0494] "Means for users to select voice input options" refers to a device or software that provides users with the option to input their inquiry content by voice instead of text.

[0495] "Means by which customers submit inquiries via smartphone applications" refers to devices or software that allow customers to submit inquiries using a smartphone application.

[0496] "Means of real-time analysis" refers to a device or software that performs analysis the moment the inquiry is sent.

[0497] System Overview

[0498] This invention is a customer inquiry handling system designed to provide prompt and appropriate customer support. Its main components include a server, a customer terminal (e.g., a smartphone), and a staff terminal.

[0499] Program Overview

[0500] The server receives inquiries from customers and analyzes the content using natural language processing (NLP) techniques. The analyzed content is categorized and routed to the appropriate person in charge. The person in charge then sends their response back to the customer via the server.

[0501] Hardware and software configuration

[0502] Hardware:

[0503] Server: For example, a cloud server such as AWS EC2.

[0504] Customer device: Smartphone (Android / iOS)

[0505] Personnel terminal: PC or smartphone

[0506] software:

[0507] Server-side: Flask (Python microframework), TextBlob (NLP library), JSON (data format)

[0508] Customer terminal: Smartphone application for sending inquiries

[0509] Processing flow

[0510] 1. Customer actions:

[0511] Users use their smartphones to input their inquiries as text or voice. For example, they might type, "I don't know how to use the new product," and then send it.

[0512] 2. Server processing:

[0513] The server receives customer inquiries and analyzes them in real time. Based on the analysis, inquiries are categorized, such as "New Product Support," and routed to the appropriate pre-registered representative. The server uses Flask to receive and analyze inquiries and TextBlob for natural language processing.

[0514] 3. Actions taken by the person in charge:

[0515] A notification arrives on the employee's terminal, and they check the inquiry details. The employee then creates a response based on the content and sends it to the customer via the server. For example, they might create specific instructions such as, "Please check the following steps for how to use the new product," and send the response.

[0516] 4. Customer receipt:

[0517] The customer receives a response from the representative and confirms whether the issue has been resolved. They can also contact the representative again if necessary.

[0518] Specific example

[0519] For example, if a user submits an inquiry stating, "I don't know how to use the new product," the server analyzes the content and categorizes it as "New Product Support." Then, a representative creates a specific response, such as "Please follow these steps to learn how to use the new product," and sends it to the user via the server.

[0520] Example of a prompt

[0521] "I don't know how to use the new product."

[0522] "I want to know about repair services."

[0523] In this way, the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Program processing steps

[0526] Step 1:

[0527] User inquiry input

[0528] Users use their smartphones to enter their inquiries as text or voice.

[0529] Input: Inquiry content entered by the user on the smartphone application.

[0530] Output: The inquiry details are sent to the smartphone application and then forwarded to the server.

[0531] Specific action: The user types "I don't know how to use the new product" into their smartphone and presses the send button.

[0532] Step 2:

[0533] Server query received

[0534] The server receives the query content sent by the user.

[0535] Input: Inquiry content sent from a smartphone application

[0536] Output: The query content is temporarily stored on the server.

[0537] Specific operation: The server uses Flask to receive the query content sent by the user in JSON format.

[0538] Step 3:

[0539] Server query analysis

[0540] The server analyzes the received query content using natural language processing technology and classifies it into categories.

[0541] Input: Query content stored on the server

[0542] Output: Category as an analysis result (e.g., "New Product Support")

[0543] Specific operation: The server uses the TextBlob library to analyze the query content and classifies it into the "New Product Support" category based on the keyword "How to use the new product".

[0544] Step 4:

[0545] Server assignment routing

[0546] The server routes inquiries to the appropriate person based on the analyzed category.

[0547] Input: Inquiry content categorized

[0548] Output: Inquiry notification to the person in charge

[0549] Specific operation: The server selects a representative from the list of representatives who corresponds to the "New Product Support" category and forwards the inquiry details to the representative's terminal.

[0550] Step 5:

[0551] Confirmation of inquiries and creation of responses by the person in charge

[0552] After receiving the notification, the person in charge will review the inquiry and prepare a response.

[0553] Input: Inquiry details routed to the assigned representative.

[0554] Output: Created response content

[0555] Specific action: The person in charge will use a PC or smartphone to create a specific response such as, "Please check the following steps for instructions on how to use the new product."

[0556] Step 6:

[0557] Server response submission

[0558] The server receives the response prepared by the person in charge and sends it to the customer.

[0559] Input: Response sent by the person in charge

[0560] Output: Sending a response to the customer

[0561] Specific operation: The server receives the response from the person in charge and sends it to the customer via a smartphone application.

[0562] Step 7:

[0563] Receiving and confirming user responses

[0564] The user receives the response sent from the server and confirms it.

[0565] Input: Response sent from the server

[0566] Output: Problem solved or additional inquiry

[0567] Specific actions: The user opens the smartphone application, checks the response from the representative, and sends additional inquiries if necessary.

[0568] Through this series of processing steps, customer inquiries are addressed quickly and appropriately.

[0569] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0570] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system receives and analyzes customer inquiries, routes them to the appropriate personnel, and ultimately sends the response to the customer. Furthermore, by incorporating an emotion engine, this invention makes it possible to recognize user emotions and reflect them in prioritizing responses and selecting the appropriate personnel.

[0571] User actions

[0572] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0573] Server Processing

[0574] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0575] How the emotion engine works

[0576] The server then passes the received inquiry to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0577] Category classification and selection of responsible persons

[0578] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "New Product Support," it will assign a representative with particularly high responsiveness to users who appear confused.

[0579] Priority setting

[0580] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[0581] Routing to the responsible person

[0582] The server routes inquiries to the selected contact person. The routed inquiry details are then sent to the contact person's terminal. For example, the "New Product Support" person receives the notification and checks the inquiry details.

[0583] Operation by the person in charge

[0584] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow the instructions below for how to use the new product," and sends it to the user via the server.

[0585] User reception

[0586] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[0587] Specific example

[0588] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it as "repair services." If the emotion engine then detects that the user is experiencing anxiety, it prioritizes the inquiry and responds quickly. The inquiry is routed to the appropriate representative, who promptly provides the user with information about repair services. In this way, responses that consider the user's emotions become possible, leading to improved customer satisfaction.

[0589] The system of this invention automates a series of processes including receiving, analyzing, classifying, routing, sending responses, sentiment recognition, and prioritizing inquiries, thereby improving customer satisfaction and distributing the workload of staff.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0593] Step 2:

[0594] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0595] Step 3:

[0596] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0597] Step 4:

[0598] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0599] Step 5:

[0600] The server passes the query content to the emotion engine. The emotion engine analyzes the text content and recognizes the user's emotions (e.g., anger, frustration, joy). For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0601] Step 6:

[0602] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, it will be given a higher priority.

[0603] Step 7:

[0604] The server selects the most suitable representative based on the emotion engine's analysis results and categories. For example, for a user in the "New Product Support" category who is confused, a representative with particularly high responsiveness will be selected.

[0605] Step 8:

[0606] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification and checks the inquiry details.

[0607] Step 9:

[0608] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0609] Step 10:

[0610] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0611] Step 11:

[0612] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0613] Step 12:

[0614] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0615] Step 13:

[0616] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0617] In this way, by executing each processing step sequentially, the process from receiving inquiries to providing answers, and even recognizing user sentiment and prioritizing responses, is carried out efficiently.

[0618] (Example 2)

[0619] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0620] While there is a demand for prompt and appropriate responses to customer inquiries, traditional systems often rely on manual processes for analyzing inquiry content, recognizing sentiment, routing inquiries to the appropriate personnel, and prioritizing them, resulting in inefficiency. Furthermore, responses that do not consider customer emotions can lead to decreased customer satisfaction. This, in turn, presents challenges in terms of accuracy and speed in handling inquiries.

[0621] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0622] In this invention, the server includes means for receiving inquiry content, means for analyzing the received inquiry content and classifying it into the appropriate category, means for sentiment analysis of the received inquiry content, means for setting response priorities based on the analysis results, means for routing the inquiry to the person in charge corresponding to the category and priority, and means for sending the response from the person in charge to the entity that made the inquiry. This enables automatic analysis of inquiry content, priority setting based on sentiment recognition, and automatic routing to the most suitable person in charge.

[0623] "Inquiry content" refers to text data such as questions, requests, and complaints that customers send to the system.

[0624] "Analysis" is the process of understanding, classifying, or evaluating the meaning and intent of a query using natural language processing techniques.

[0625] "Natural language processing technology" refers to the technology that enables computers to understand and process human language. Specifically, it includes text analysis, sentiment analysis, and semantic analysis.

[0626] A "category" is a group of inquiries that are classified based on a specific topic or theme. Examples include "new product support" and "repair services."

[0627] "Sentiment analysis" is the process of extracting and evaluating the user's emotions (e.g., joy, anger, confusion, dissatisfaction, etc.) contained in the inquiry content from text data.

[0628] "Priority" is a criterion used to determine the order in which inquiries are handled. Typically, it is set based on sentiment analysis results, and high-priority inquiries are handled more quickly.

[0629] A "person in charge" refers to a person or team responsible for handling a specific category or inquiry.

[0630] "Routing" is the process of automatically assigning inquiries to the appropriate person in charge based on analysis results and priority settings.

[0631] A "response" is text data containing information or solutions provided by the person in charge in response to an inquiry.

[0632] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates the reception, analysis, sentiment analysis, categorization, prioritization, routing to the appropriate person, and response transmission of inquiries. To implement this system, a high-performance server and terminals for users and staff are required.

[0633] System hardware and software configuration

[0634] The server requires a high-performance processor (e.g., an Intel Xeon processor) and large-capacity storage (e.g., an SSD). This server utilizes natural language processing techniques to analyze query content and sentiment analysis. Specifically, it uses Python and libraries such as TensorFlow and spaCy. Furthermore, it employs generative AI models such as GPT-3 for sentiment analysis.

[0635] Users and staff members need internet-connected devices such as personal computers or smartphones. Users access the system using a web browser (such as Google Chrome or Safari), enter their inquiries, and submit them. Staff members receive inquiry notifications from the server using a web browser or a dedicated application.

[0636] System operation example

[0637] Users access the inquiry form through a web browser, enter a message such as "I don't know how to use the new product," and click the submit button. This inquiry is sent to the server and temporarily stored in cloud storage such as Amazon S3 or Google Cloud Storage. The stored data is analyzed using natural language processing techniques with TensorFlow or spaCy and categorized under "New Product Support."

[0638] Next, the server passes the inquiry to the emotion engine, which uses a generative AI model (e.g., GPT-3) to analyze the user's emotions. For example, from the query "I don't know how to use the new product!", it determines that the user is confused.

[0639] Based on the analysis results, the server sets the priority for responding to inquiries. Users who are confused are given a high priority and require a quick response. Based on category and priority, inquiries are automatically routed to the most suitable person in charge. The person in charge receives the inquiry through a dedicated application or email notification and responds promptly.

[0640] The person in charge reviews the inquiry and creates an appropriate response. For example, they create a specific response such as, "Please follow the steps below for instructions on how to use the new product," and send it to the user via the server. The user receives the response from the server, and the problem is resolved.

[0641] Example of a prompt

[0642] "Create a system that analyzes customer inquiries, categorizes them appropriately, performs sentiment analysis to prioritize responses, and routes them to the appropriate staff member."

[0643] This system automates a series of processes, including receiving, analyzing, recognizing sentiment, categorizing, prioritizing, routing, and sending responses, thereby improving customer satisfaction and distributing the workload among staff.

[0644] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0645] Step 1:

[0646] Users access the system using devices such as personal computers and smartphones. They access the inquiry form through a web browser (such as Google Chrome or Safari), enter their inquiry in text format, and click the submit button. For example, a user might enter "I don't know how to use the new product" and submit it. This action sends the inquiry to the server. The input is the user's text data, and the output is the data sent to the server.

[0647] Step 2:

[0648] The server receives user inquiries and temporarily stores them in cloud storage (such as Amazon S3 or Google Cloud Storage). After storage, it analyzes the inquiry content using natural language processing libraries such as TensorFlow or spaCy with Python code. As a result of the analysis, the inquiry content is classified into a specific category. For example, the keyword "How to use the new product" is classified into the "New Product Support" category. The input is the received text data, and the output is the analysis results and category classification data.

[0649] Step 3:

[0650] The server passes the received inquiry to the sentiment engine. The sentiment engine uses a generative AI model (e.g., GPT-3) to perform sentiment analysis on the inquiry. It recognizes the user's emotions (e.g., anger, confusion, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused. The input is the text data to be analyzed, and the output is the sentiment analysis result.

[0651] Step 4:

[0652] The server further classifies the inquiry content based on the NLP analysis results and sentiment analysis results, and assigns it to the appropriate category. For example, if it is classified under the "New Product Support" category, it selects a highly capable representative to assist the confused user. The input is category classification data and sentiment analysis data, and the output is information on the selection of the optimal representative.

[0653] Step 5:

[0654] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, the server will set a high priority for the response, requiring a quick response. The input is emotion analysis data, and the output is priority setting data.

[0655] Step 6:

[0656] The server routes inquiries to the designated contact person. The routing is automated, and notifications are sent to the contact person's device (e.g., laptop or desktop PC). For example, a "new product support" contact person receives the notification and checks the inquiry. Inputs include the contact person's selection information and the inquiry content, while output is the notification sent to the contact person.

[0657] Step 7:

[0658] The person using the terminal receives a notification from the server and displays the inquiry details. The person reviews the content and creates an appropriate response. For example, they might create a specific response such as, "Please follow the instructions below for how to use the new product," and send it back to the user via the server. The input consists of the inquiry and the response, and the output is the response data.

[0659] Step 8:

[0660] The user receives the response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiry is necessary. If needed, the user can enter additional questions and resubmit. The input is the received response data, and the output is the user's evaluation and new inquiry data.

[0661] (Application Example 2)

[0662] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0663] In modern brick-and-mortar stores, prompt and appropriate responses to customer inquiries are crucial for improving customer satisfaction. However, traditional inquiry response systems often failed to consider customer emotions and were ineffective at routing inquiries to the appropriate staff. As a result, even in cases of customer dissatisfaction or urgency, prompt responses were frequently delayed, leading to decreased customer satisfaction and damage to the store's reputation. To address this challenge, a system is needed that considers customer emotions and priorities to optimally handle inquiries.

[0664] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0665] In this invention, the server includes means for receiving customer inquiries, means for analyzing the received inquiries and classifying them into the appropriate categories, means for analyzing the inquiries and recognizing the customer's emotions, means for setting response priorities based on the categories and recognized emotions, means for routing inquiries to personnel corresponding to the categories and priorities, and means for sending responses from personnel to the customers. This enables quick and appropriate responses in physical stores that take into account customer emotions and inquiry priorities.

[0666] "Means for receiving customer inquiries" refers to the technical equipment that allows customers to input questions about products and services using devices such as smartphones or smart glasses within a physical store, and for a server to receive those inquiries.

[0667] "A means of analyzing received inquiries and classifying them into the appropriate category" refers to a system that uses natural language processing technology to analyze received text data and classify it into the appropriate category, such as product support or customer service, based on its content.

[0668] "Means of analyzing inquiry content to recognize customer emotions" refers to a function that uses natural language processing technology to automatically detect and recognize customer emotions (e.g., joy, dissatisfaction, confusion, etc.) from received text.

[0669] "Means for setting response priorities based on categories and perceived emotions" refers to a technology for evaluating the necessity and urgency of a response based on analyzed categories and customer emotion information, and for setting the priority of the response (high, medium, low, etc.).

[0670] "A means of routing inquiries to the appropriate person based on category and priority" refers to a system that automatically distributes inquiries to the most suitable person according to the set category and priority, and notifies the person's terminal.

[0671] "Means of sending responses from staff to customers" refers to the technical equipment used to send responses prepared by staff to customers, allowing customers to view the responses on devices such as smartphones or smart glasses.

[0672] "Natural language processing technology" refers to artificial intelligence technologies used for processing text data, such as analysis, classification, and sentiment recognition. Examples include libraries like TextBlob and NLTK.

[0673] "Customer emotions" refers to the emotional nuances of the words included in an inquiry, encompassing emotional states such as joy, anger, dissatisfaction, and confusion.

[0674] "Response priority" is an indicator that shows how quickly a customer inquiry needs to be addressed, and is expressed as a rank such as "high priority" or "low priority."

[0675] This invention is a system for responding quickly and appropriately to customer inquiries in physical stores. The system receives customer inquiries, analyzes them, routes them to the appropriate staff member, and finally sends the answer to the customer. Furthermore, by incorporating an emotion engine, it can recognize customer emotions and reflect them in prioritizing responses and selecting the appropriate staff member.

[0676] User actions

[0677] Users access the system using devices such as smartphones or smart glasses and enter their inquiries by scanning QR codes in the store. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit "I don't know how to use my new smartphone!"

[0678] Server Processing

[0679] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "How to use a new smartphone" might be classified into the "Product Support" category.

[0680] How the emotion engine works

[0681] The server then passes the received inquiry to the sentiment engine, which analyzes the user's emotions. The sentiment engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use my new smartphone!", it determines that the user is confused.

[0682] Category classification and selection of responsible persons

[0683] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "product support," it will assign a representative with particularly high responsiveness to users who appear confused.

[0684] Priority setting

[0685] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[0686] Routing to the responsible person

[0687] The server routes the inquiry to the selected person in charge. The routed inquiry is then notified to the person in charge's terminal. For example, the "product support" person receives the notification and checks the inquiry.

[0688] Operation by the person in charge

[0689] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow these steps for instructions on how to use your new smartphone," and sends it to the user via the server.

[0690] User reception

[0691] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions on "How to use your new smartphone" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[0692] Specific example

[0693] For example, a user in a store might type, "I don't know how to use my new smartphone!" The system categorizes this as "Product Support," recognizes the user's emotion as "Confused," and sets the priority to "High." It then sends a notification to the relevant staff member indicating "Urgent Support Needed" to encourage a quick response. An example of user input in this case is as follows:

[0694] I don't know how to use my new smartphone!

[0695] Through the above process, it becomes possible to provide prompt and appropriate responses in physical stores, taking into account customer emotions and the priority of inquiries.

[0696] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0697] Step 1:

[0698] Users scan a QR code in the store using their smartphone or smart glasses, enter their inquiry, and press the submit button. This input data is in text format and is sent to the server when the submit button is pressed.

[0699] Input: Inquiry details (text format)

[0700] Output: Query content sent to the server

[0701] Step 2:

[0702] The server receives the query content sent by the user and temporarily stores it in storage. This process makes the query content accessible within the server.

[0703] Input: Inquiry received from the user

[0704] Output: Query content stored in storage

[0705] Step 3:

[0706] The server analyzes the query data stored in storage using natural language processing (NLP) techniques. The analyzed data is then categorized into specific categories. For example, based on the keyword "How to use a new smartphone," it might be categorized as "product support."

[0707] Input: Query content stored in storage

[0708] Output: Inquiry content categorized

[0709] Step 4:

[0710] The server uses an emotion engine to recognize the user's emotions based on the analyzed query content. Specifically, it analyzes the context and vocabulary of the input text to identify the emotions the user is experiencing (e.g., confusion, anger, joy, etc.).

[0711] Input: Analyzed query content

[0712] Output: Recognized emotion information

[0713] Step 5:

[0714] The server prioritizes responses based on the results of category classification and sentiment recognition. For example, if the user is confused, it sets a high priority and clearly indicates that a prompt response is needed.

[0715] Input: Inquiry content categorized and recognized sentiment information

[0716] Output: Set response priority

[0717] Step 6:

[0718] The server selects the appropriate person in charge based on category and priority, and routes the inquiry to that person. A notification of the inquiry is sent to the person in charge's terminal. For example, a "product support" person receives the notification.

[0719] Input: Category, recognized emotion information, set response priority

[0720] Output: Inquiry notification sent to the person in charge

[0721] Step 7:

[0722] The person using the terminal receives a notification from the server, displays the inquiry details, and creates the necessary response. Once the response is complete, the person sends it to the server.

[0723] Input: Inquiry details notified to the person in charge

[0724] Output: Answer created by the person in charge

[0725] Step 8:

[0726] The server receives the response sent by the representative and forwards it to the customer. This is done by displaying the response on the customer's smartphone or smart glasses. This process allows the customer to verify the received response.

[0727] Input: Response received from the person in charge

[0728] Output: Response sent to the customer

[0729] Step 9:

[0730] The user receives the response sent from the server and evaluates whether the problem has been resolved. If necessary, the user may enter and resubmit additional inquiries.

[0731] Input: Response received from the server

[0732] Output: User ratings and additional inquiries (if applicable)

[0733] 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.

[0734] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0735] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0736] [Third Embodiment]

[0737] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0738] 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.

[0739] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0740] 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.

[0741] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0742] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0743] 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.

[0744] 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.

[0745] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0746] The 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.

[0747] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0748] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0749] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system has the functionality to receive customer inquiries, analyze them, route them to the appropriate person in charge, and finally send the answer to the customer.

[0750] User actions

[0751] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0752] Server Processing

[0753] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0754] The server then selects the appropriate person to handle the inquiry based on the classified category and routes the inquiry to that person. The list of persons is pre-registered within the server, and the person in charge for each category is defined. For example, an inquiry in the "New Product Support" category will be routed to the new product support person.

[0755] Operation by the person in charge

[0756] The person using the terminal receives a notification from the server and checks the content of the inquiry. The person checks the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates a response saying, "Please check the following steps for how to use the new product," and sends it to the user via the server.

[0757] User reception

[0758] The user receives a response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user can also submit additional questions.

[0759] Specific example

[0760] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it under "repair services." It then routes the inquiry to the appropriate representative, who creates and responds with appropriate repair service information. This process is repeated until the user receives the response and the problem is resolved.

[0761] In this way, the system of the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0762] The following describes the processing flow.

[0763] Step 1:

[0764] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0765] Step 2:

[0766] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0767] Step 3:

[0768] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0769] Step 4:

[0770] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0771] Step 5:

[0772] The server selects the appropriate person in charge based on its classification category. The person in charge is chosen from a predefined list of persons in charge for each category. For example, a person in charge of the "New Product Support" category is selected.

[0773] Step 6:

[0774] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification.

[0775] Step 7:

[0776] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0777] Step 8:

[0778] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0779] Step 9:

[0780] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0781] Step 10:

[0782] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0783] Step 11:

[0784] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0785] In this way, by executing each processing step sequentially, the process from receiving the inquiry to providing the answer is carried out efficiently.

[0786] (Example 1)

[0787] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0788] To respond quickly and appropriately to customer inquiries, it is necessary to properly analyze incoming inquiries and route them to the appropriate personnel. However, in conventional systems, this process was often done manually, which was time-consuming and carried the risk of delays and errors in responses by personnel. This resulted in decreased customer satisfaction and negatively impacted the company's credibility.

[0789] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0790] In this invention, the server includes means for receiving user-entered inquiry content, means for temporarily storing the received inquiry content, means for analyzing the stored inquiry content using natural language processing technology and classifying it into categories, means for selecting an appropriate person in charge based on the category and routing the inquiry, and means for sending the response created by the person in charge to the user. This enables rapid and accurate analysis of inquiry content and automatic routing to the appropriate person in charge, thereby improving customer satisfaction and reducing the workload on the person in charge.

[0791] A "user" is a person or entity that uses the system to submit a request.

[0792] "Inquiry content" refers to the text data of information and questions that a user sends to the server through the system.

[0793] "Means of receiving" refers to the methods and system components that allow the server to retrieve the content of inquiries sent by users.

[0794] "Means of temporary storage" refers to the method or system for storing received inquiry content in temporary data storage.

[0795] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human language, and specifically refers to algorithms and tools that perform text analysis and keyword extraction.

[0796] A "category" refers to the type or group of inquiry content, and is an area or section classified based on the analysis results.

[0797] A "person in charge" is a specialist or employee selected to handle inquiries in a specific category.

[0798] "Routing methods" refer to the methods and systems used to distribute inquiries to the appropriate personnel after analyzing the content.

[0799] A "response" is a solution or information that a representative creates based on an inquiry and provides to the user.

[0800] "Means of transmission" refers to the methods and systems used to deliver the responses prepared by the person in charge to the user.

[0801] A "server" is a central processing unit that receives user inquiries, analyzes them, routes them to the appropriate person, and sends the response.

[0802] Modes for carrying out the invention

[0803] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates a series of processes, including receiving customer inquiries, analyzing them, routing them to the appropriate personnel, and finally sending the answers to the customers.

[0804] Hardware and software configuration

[0805] server

[0806] The server will be a computer equipped with a high-performance processor and sufficient memory. Furthermore, it will utilize high-speed storage (e.g., Amazon S3, Google Cloud Storage) for temporary data storage. The server will also have software installed to implement natural language processing technologies (e.g., Google Cloud Natural Language API, Microsoft Azure Text Analytics).

[0807] terminal

[0808] The devices that users use to access the system are internet-connected devices such as personal computers and smartphones. These devices are equipped with a web browser and can access the system's web pages. Similarly, administrators also access the system using devices such as personal computers and tablets.

[0809] Inquiry reception and analysis

[0810] The user enters their inquiry in text format through their device's web browser and clicks the submit button. The server receives the inquiry sent from the user's device and temporarily stores it in storage. The stored data is analyzed using natural language processing techniques, and the content of the inquiry is classified into a specific category.

[0811] Category classification and routing

[0812] The server categorizes the analyzed query content and selects the appropriate person to handle it. A list of assigned personnel is pre-registered within the server, with each category defined accordingly. The server automatically routes the query to the appropriate person based on its category.

[0813] Create and submit your response.

[0814] The person in charge receives a notification from the server and reviews the inquiry. They create an appropriate response and send it back to the user via the server. The user receives the response on their device and checks if the problem has been resolved. If necessary, the user can resubmit the inquiry.

[0815] Specific example

[0816] For example, the following shows the specific process when a user submits an inquiry asking about repair services. The server analyzes the inquiry using the Google Cloud Natural Language API and categorizes it as "repair services." The server selects a person in charge of "repair services" and routes the inquiry to that person. The person in charge creates detailed information about the repair services and sends the response to the user. The user receives the response and checks whether the problem has been resolved.

[0817] Examples of prompt statements

[0818] An example of input to the AI ​​model generated by the system is, "Analyze the following inquiry and classify it into a category: 'I want to know about repair services.'" Using this prompt, the AI ​​model can appropriately analyze the inquiry and identify the category.

[0819] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0820] Step 1:

[0821] Users access the system's webpage using a browser on a device such as a PC or smartphone. They enter text such as "I don't know how to use the new product" into the inquiry form and click the submit button. The entered text data is sent to the server.

[0822] Step 2:

[0823] The server receives HTTP POST requests sent from the user's device. The received query content is temporarily stored in storage (e.g., Amazon S3 or Google Cloud Storage). The input is text data from the user, and the output is the data stored in temporary storage.

[0824] Step 3:

[0825] The server retrieves stored query data and performs analysis using natural language processing technology (e.g., Google Cloud Natural Language API). The input is stored text data, and the output is keyword and category information extracted as a result of the analysis. Specifically, it extracts the keyword "how to use the new product" from the text and classifies it into the "new product support" category.

[0826] Step 4:

[0827] The server categorizes queries into specific categories based on the analysis results. Inputs are keywords and analysis results, while output is category information. For example, a query like "I want to know about repair services" would be categorized as "repair services."

[0828] Step 5:

[0829] The server selects the appropriate contact person from a list of contact persons defined for each category and routes the inquiry to that contact person. The input is category information, and the output is routing information to the contact person. For example, an inquiry in the "New Product Support" category will be routed to the New Product Support contact person.

[0830] Step 6:

[0831] The person using the terminal receives a notification from the server and checks the content of the inquiry. The input is routing information sent from the server, and the output is the result of the person's confirmation. The person checks the content of the inquiry, which is "I don't know how to use the new product."

[0832] Step 7:

[0833] The person in charge creates an appropriate response to the inquiry they have received. The input is the inquiry, and the output is the response text. For example, the person in charge would write specific instructions such as "Please check the following steps for how to use the new product" and send the response to the server.

[0834] Step 8:

[0835] The server resends the response received from the person in charge to the user. The input is the response text created by the person in charge, and the output is the response sent to the user. The user receives the response on their terminal and checks whether the problem has been resolved. Specifically, the server sends the response to the user via an HTTP response.

[0836] Step 9:

[0837] The user reviews the response sent from the server on their device and evaluates whether the problem has been resolved. The input is the response text sent from the server, and the output is the user's evaluation result. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user will submit another question.

[0838] (Application Example 1)

[0839] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0840] Traditional customer support systems had the problem of requiring manual analysis and routing of inquiries, resulting in time-consuming processing. Furthermore, the lack of real-time inquiry support via smartphones made it difficult to improve customer satisfaction.

[0841] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0842] In this invention, the server includes means for receiving customer inquiries, means for analyzing the inquiry content and classifying it into the appropriate category, means for routing the inquiry to the person in charge corresponding to the category, means for sending the person in charge's response to the customer, means for inputting the inquiry using a terminal including a smartphone, means for the user to select a voice input option, means for the customer to send the inquiry through a smartphone application, and means for analyzing the inquiry content in real time. This enables quick and appropriate responses to inquiries.

[0843] A "customer" refers to a consumer who makes inquiries or purchases from a company or organization that provides services or products.

[0844] "Means for receiving inquiries" refers to devices or software used to receive questions and requests sent by customers.

[0845] "Means of analysis" refers to devices or software used to analyze the content of received inquiries and understand their purpose and intent.

[0846] "Means of categorization" refers to a device or software that classifies the analyzed query content as belonging to a specific category.

[0847] "Means for routing inquiries to the appropriate person" refers to a device or software that forwards inquiry content to the appropriate person based on its classified category.

[0848] "Means of sending responses from the person in charge to the customer" refers to a device or software that returns the response prepared by the person in charge to the customer.

[0849] "Means of entering inquiries using a device including a smartphone" refers to a device or method of entering inquiry details using a mobile device such as a smartphone.

[0850] "Means for users to select voice input options" refers to a device or software that provides users with the option to input their inquiry content by voice instead of text.

[0851] "Means by which customers submit inquiries via smartphone applications" refers to devices or software that allow customers to submit inquiries using a smartphone application.

[0852] "Means of real-time analysis" refers to a device or software that performs analysis the moment the inquiry is sent.

[0853] System Overview

[0854] This invention is a customer inquiry handling system designed to provide prompt and appropriate customer support. Its main components include a server, a customer terminal (e.g., a smartphone), and a staff terminal.

[0855] Program Overview

[0856] The server receives inquiries from customers and analyzes the content using natural language processing (NLP) techniques. The analyzed content is categorized and routed to the appropriate person in charge. The person in charge then sends their response back to the customer via the server.

[0857] Hardware and software configuration

[0858] Hardware:

[0859] Server: For example, a cloud server such as AWS EC2.

[0860] Customer device: Smartphone (Android / iOS)

[0861] Personnel terminal: PC or smartphone

[0862] software:

[0863] Server-side: Flask (Python microframework), TextBlob (NLP library), JSON (data format)

[0864] Customer terminal: Smartphone application for sending inquiries

[0865] Processing flow

[0866] 1. Customer actions:

[0867] Users use their smartphones to input their inquiries as text or voice. For example, they might type, "I don't know how to use the new product," and then send it.

[0868] 2. Server processing:

[0869] The server receives customer inquiries and analyzes them in real time. Based on the analysis, inquiries are categorized, such as "New Product Support," and routed to the appropriate pre-registered representative. The server uses Flask to receive and analyze inquiries and TextBlob for natural language processing.

[0870] 3. Actions taken by the person in charge:

[0871] A notification arrives on the employee's terminal, and they check the inquiry details. The employee then creates a response based on the content and sends it to the customer via the server. For example, they might create specific instructions such as, "Please check the following steps for how to use the new product," and send the response.

[0872] 4. Customer receipt:

[0873] The customer receives a response from the representative and confirms whether the issue has been resolved. They can also contact the representative again if necessary.

[0874] Specific example

[0875] For example, if a user submits an inquiry stating, "I don't know how to use the new product," the server analyzes the content and categorizes it as "New Product Support." Then, a representative creates a specific response, such as "Please follow these steps to learn how to use the new product," and sends it to the user via the server.

[0876] Example of a prompt

[0877] "I don't know how to use the new product."

[0878] "I want to know about repair services."

[0879] In this way, the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[0880] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0881] Program processing steps

[0882] Step 1:

[0883] User inquiry input

[0884] Users use their smartphones to enter their inquiries as text or voice.

[0885] Input: Inquiry content entered by the user on the smartphone application.

[0886] Output: The inquiry details are sent to the smartphone application and then forwarded to the server.

[0887] Specific action: The user types "I don't know how to use the new product" into their smartphone and presses the send button.

[0888] Step 2:

[0889] Server query received

[0890] The server receives the query content sent by the user.

[0891] Input: Inquiry content sent from a smartphone application

[0892] Output: The query content is temporarily stored on the server.

[0893] Specific operation: The server uses Flask to receive the query content sent by the user in JSON format.

[0894] Step 3:

[0895] Server query analysis

[0896] The server analyzes the received query content using natural language processing technology and classifies it into categories.

[0897] Input: Query content stored on the server

[0898] Output: Category as an analysis result (e.g., "New Product Support")

[0899] Specific operation: The server uses the TextBlob library to analyze the query content and classifies it into the "New Product Support" category based on the keyword "How to use the new product".

[0900] Step 4:

[0901] Server assignment routing

[0902] The server routes inquiries to the appropriate person based on the analyzed category.

[0903] Input: Inquiry content categorized

[0904] Output: Inquiry notification to the person in charge

[0905] Specific operation: The server selects a representative from the list of representatives who corresponds to the "New Product Support" category and forwards the inquiry details to the representative's terminal.

[0906] Step 5:

[0907] Confirmation of inquiries and creation of responses by the person in charge

[0908] After receiving the notification, the person in charge will review the inquiry and prepare a response.

[0909] Input: Inquiry details routed to the assigned representative.

[0910] Output: Created response content

[0911] Specific action: The person in charge will use a PC or smartphone to create a specific response such as, "Please check the following steps for instructions on how to use the new product."

[0912] Step 6:

[0913] Server response submission

[0914] The server receives the response prepared by the person in charge and sends it to the customer.

[0915] Input: Response sent by the person in charge

[0916] Output: Sending a response to the customer

[0917] Specific operation: The server receives the response from the person in charge and sends it to the customer via a smartphone application.

[0918] Step 7:

[0919] Receiving and confirming user responses

[0920] The user receives the response sent from the server and confirms it.

[0921] Input: Response sent from the server

[0922] Output: Problem solved or additional inquiry

[0923] Specific actions: The user opens the smartphone application, checks the response from the representative, and sends additional inquiries if necessary.

[0924] Through this series of processing steps, customer inquiries are addressed quickly and appropriately.

[0925] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0926] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system receives and analyzes customer inquiries, routes them to the appropriate personnel, and ultimately sends the answers to the customers. Furthermore, by incorporating an emotion engine, this invention makes it possible to recognize user emotions and reflect them in prioritizing responses and selecting the appropriate personnel.

[0927] User actions

[0928] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[0929] Server Processing

[0930] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[0931] How the emotion engine works

[0932] The server then passes the received inquiry to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0933] Category classification and selection of responsible persons

[0934] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "New Product Support," it will assign a representative with particularly high responsiveness to users who appear confused.

[0935] Priority setting

[0936] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[0937] Routing to the responsible person

[0938] The server routes inquiries to the selected contact person. The routed inquiry details are then sent to the contact person's terminal. For example, the "New Product Support" person receives the notification and checks the inquiry details.

[0939] Operation by the person in charge

[0940] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow the instructions below for how to use the new product," and sends it to the user via the server.

[0941] User reception

[0942] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[0943] Specific example

[0944] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it as "repair services." If the emotion engine then detects that the user is experiencing anxiety, it prioritizes the inquiry and responds quickly. The inquiry is routed to the appropriate representative, who promptly provides the user with information about repair services. In this way, responses that consider the user's emotions become possible, leading to improved customer satisfaction.

[0945] The system of this invention automates a series of processes including receiving, analyzing, classifying, routing, sending responses, sentiment recognition, and prioritizing inquiries, thereby improving customer satisfaction and distributing the workload of staff.

[0946] The following describes the processing flow.

[0947] Step 1:

[0948] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[0949] Step 2:

[0950] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[0951] Step 3:

[0952] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[0953] Step 4:

[0954] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[0955] Step 5:

[0956] The server passes the query content to the emotion engine. The emotion engine analyzes the text content and recognizes the user's emotions (e.g., anger, frustration, joy). For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[0957] Step 6:

[0958] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, it will be given a higher priority.

[0959] Step 7:

[0960] The server selects the most suitable representative based on the emotion engine's analysis results and categories. For example, for a user in the "New Product Support" category who is confused, a representative with particularly high responsiveness will be selected.

[0961] Step 8:

[0962] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification and checks the inquiry details.

[0963] Step 9:

[0964] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[0965] Step 10:

[0966] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[0967] Step 11:

[0968] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[0969] Step 12:

[0970] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[0971] Step 13:

[0972] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[0973] In this way, by executing each processing step sequentially, the process from receiving inquiries to providing answers, and even recognizing user sentiment and prioritizing responses, is carried out efficiently.

[0974] (Example 2)

[0975] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0976] While there is a demand for prompt and appropriate responses to customer inquiries, traditional systems often rely on manual processes for analyzing inquiry content, recognizing sentiment, routing inquiries to the appropriate personnel, and prioritizing them, resulting in inefficiency. Furthermore, responses that do not consider customer emotions can lead to decreased customer satisfaction. This, in turn, presents challenges in terms of accuracy and speed in handling inquiries.

[0977] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0978] In this invention, the server includes means for receiving inquiry content, means for analyzing the received inquiry content and classifying it into the appropriate category, means for sentiment analysis of the received inquiry content, means for setting response priorities based on the analysis results, means for routing the inquiry to the person in charge corresponding to the category and priority, and means for sending the response from the person in charge to the entity that made the inquiry. This enables automatic analysis of inquiry content, priority setting based on sentiment recognition, and automatic routing to the most suitable person in charge.

[0979] "Inquiry content" refers to text data such as questions, requests, and complaints that customers send to the system.

[0980] "Analysis" is the process of understanding, classifying, or evaluating the meaning and intent of a query using natural language processing techniques.

[0981] "Natural language processing technology" refers to the technology that enables computers to understand and process human language. Specifically, it includes text analysis, sentiment analysis, and semantic analysis.

[0982] A "category" is a group of inquiries that are classified based on a specific topic or theme. Examples include "new product support" and "repair services."

[0983] "Sentiment analysis" is the process of extracting and evaluating the user's emotions (e.g., joy, anger, confusion, dissatisfaction, etc.) contained in the inquiry content from text data.

[0984] "Priority" is a criterion used to determine the order in which inquiries are handled. Typically, it is set based on sentiment analysis results, and high-priority inquiries are handled more quickly.

[0985] A "person in charge" refers to a person or team responsible for handling a specific category or inquiry.

[0986] "Routing" is the process of automatically assigning inquiries to the appropriate person in charge based on analysis results and priority settings.

[0987] A "response" is text data containing information or solutions provided by the person in charge in response to an inquiry.

[0988] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates the reception, analysis, sentiment analysis, categorization, prioritization, routing to the appropriate person, and response transmission of inquiries. To implement this system, a high-performance server and terminals for users and staff are required.

[0989] System hardware and software configuration

[0990] The server requires a high-performance processor (e.g., an Intel Xeon processor) and large-capacity storage (e.g., an SSD). This server utilizes natural language processing techniques to analyze query content and sentiment analysis. Specifically, it uses Python and libraries such as TensorFlow and spaCy. Furthermore, it employs generative AI models such as GPT-3 for sentiment analysis.

[0991] Users and staff members need internet-connected devices such as personal computers or smartphones. Users access the system using a web browser (such as Google Chrome or Safari), enter their inquiries, and submit them. Staff members receive inquiry notifications from the server using a web browser or a dedicated application.

[0992] System operation example

[0993] Users access the inquiry form through a web browser, enter a message such as "I don't know how to use the new product," and click the submit button. This inquiry is sent to the server and temporarily stored in cloud storage such as Amazon S3 or Google Cloud Storage. The stored data is analyzed using natural language processing techniques with TensorFlow or spaCy and categorized under "New Product Support."

[0994] Next, the server passes the inquiry to the emotion engine, which uses a generative AI model (e.g., GPT-3) to analyze the user's emotions. For example, from the query "I don't know how to use the new product!", it determines that the user is confused.

[0995] Based on the analysis results, the server sets the priority for responding to inquiries. Users who are confused are given a high priority and require a quick response. Based on category and priority, inquiries are automatically routed to the most suitable person in charge. The person in charge receives the inquiry through a dedicated application or email notification and responds promptly.

[0996] The person in charge reviews the inquiry and creates an appropriate response. For example, they create a specific response such as, "Please follow the steps below for instructions on how to use the new product," and send it to the user via the server. The user receives the response from the server, and the problem is resolved.

[0997] Example of a prompt

[0998] "Create a system that analyzes customer inquiries, categorizes them appropriately, performs sentiment analysis to prioritize responses, and routes them to the appropriate staff member."

[0999] This system automates a series of processes, including receiving, analyzing, recognizing sentiment, categorizing, prioritizing, routing, and sending responses, thereby improving customer satisfaction and distributing the workload among staff.

[1000] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1001] Step 1:

[1002] Users access the system using devices such as personal computers and smartphones. They access the inquiry form through a web browser (such as Google Chrome or Safari), enter their inquiry in text format, and click the submit button. For example, a user might enter "I don't know how to use the new product" and submit it. This action sends the inquiry to the server. The input is the user's text data, and the output is the data sent to the server.

[1003] Step 2:

[1004] The server receives user inquiries and temporarily stores them in cloud storage (such as Amazon S3 or Google Cloud Storage). After storage, it analyzes the inquiry content using natural language processing libraries such as TensorFlow or spaCy with Python code. As a result of the analysis, the inquiry content is classified into a specific category. For example, the keyword "How to use the new product" is classified into the "New Product Support" category. The input is the received text data, and the output is the analysis results and category classification data.

[1005] Step 3:

[1006] The server passes the received inquiry to the sentiment engine. The sentiment engine uses a generative AI model (e.g., GPT-3) to perform sentiment analysis on the inquiry. It recognizes the user's emotions (e.g., anger, confusion, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused. The input is the text data to be analyzed, and the output is the sentiment analysis result.

[1007] Step 4:

[1008] The server further classifies the inquiry content based on the NLP analysis results and sentiment analysis results, and assigns it to the appropriate category. For example, if it is classified under the "New Product Support" category, it selects a highly capable representative to assist the confused user. The input is category classification data and sentiment analysis data, and the output is information on the selection of the optimal representative.

[1009] Step 5:

[1010] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, the server will set a high priority for the response, requiring a quick response. The input is emotion analysis data, and the output is priority setting data.

[1011] Step 6:

[1012] The server routes inquiries to the designated contact person. The routing is automated, and notifications are sent to the contact person's device (e.g., laptop or desktop PC). For example, a "new product support" contact person receives the notification and checks the inquiry. Inputs include the contact person's selection information and the inquiry content, while output is the notification sent to the contact person.

[1013] Step 7:

[1014] The person using the terminal receives a notification from the server and displays the inquiry details. The person reviews the content and creates an appropriate response. For example, they might create a specific response such as, "Please follow the instructions below for how to use the new product," and send it back to the user via the server. The input consists of the inquiry and the response, and the output is the response data.

[1015] Step 8:

[1016] The user receives the response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiry is necessary. If needed, the user can enter additional questions and resubmit. The input is the received response data, and the output is the user's evaluation and new inquiry data.

[1017] (Application Example 2)

[1018] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1019] In modern brick-and-mortar stores, prompt and appropriate responses to customer inquiries are crucial for improving customer satisfaction. However, traditional inquiry response systems often failed to consider customer emotions and were ineffective at routing inquiries to the appropriate staff. As a result, even in cases of customer dissatisfaction or urgency, prompt responses were frequently delayed, leading to decreased customer satisfaction and damage to the store's reputation. To address this challenge, a system is needed that considers customer emotions and priorities to optimally handle inquiries.

[1020] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1021] In this invention, the server includes means for receiving customer inquiries, means for analyzing the received inquiries and classifying them into the appropriate categories, means for analyzing the inquiries and recognizing the customer's emotions, means for setting response priorities based on the categories and recognized emotions, means for routing inquiries to personnel corresponding to the categories and priorities, and means for sending responses from personnel to the customers. This enables quick and appropriate responses in physical stores that take into account customer emotions and inquiry priorities.

[1022] "Means for receiving customer inquiries" refers to the technical equipment that allows customers to input questions about products and services using devices such as smartphones or smart glasses within a physical store, and for a server to receive those inquiries.

[1023] "A means of analyzing received inquiries and classifying them into the appropriate category" refers to a system that uses natural language processing technology to analyze received text data and classify it into the appropriate category, such as product support or customer service, based on its content.

[1024] "Means of analyzing inquiry content to recognize customer emotions" refers to a function that uses natural language processing technology to automatically detect and recognize customer emotions (e.g., joy, dissatisfaction, confusion, etc.) from received text.

[1025] "Means for setting response priorities based on categories and perceived emotions" refers to a technology for evaluating the necessity and urgency of a response based on analyzed categories and customer emotion information, and for setting the priority of the response (high, medium, low, etc.).

[1026] "A means of routing inquiries to the appropriate person based on category and priority" refers to a system that automatically distributes inquiries to the most suitable person according to the set category and priority, and notifies the person's terminal.

[1027] "Means of sending responses from staff to customers" refers to the technical equipment used to send responses prepared by staff to customers, allowing customers to view the responses on devices such as smartphones or smart glasses.

[1028] "Natural language processing technology" refers to artificial intelligence technologies used for processing text data, such as analysis, classification, and sentiment recognition. Examples include libraries like TextBlob and NLTK.

[1029] "Customer emotions" refers to the emotional nuances of the words included in an inquiry, encompassing emotional states such as joy, anger, dissatisfaction, and confusion.

[1030] "Response priority" is an indicator that shows how quickly a customer inquiry needs to be addressed, and is expressed as a rank such as "high priority" or "low priority."

[1031] This invention is a system for responding quickly and appropriately to customer inquiries in physical stores. The system receives customer inquiries, analyzes them, routes them to the appropriate staff member, and finally sends the answer to the customer. Furthermore, by incorporating an emotion engine, it can recognize customer emotions and reflect them in prioritizing responses and selecting the appropriate staff member.

[1032] User actions

[1033] Users access the system using devices such as smartphones or smart glasses and enter their inquiries by scanning QR codes in the store. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit "I don't know how to use my new smartphone!"

[1034] Server Processing

[1035] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "How to use a new smartphone" might be classified into the "Product Support" category.

[1036] How the emotion engine works

[1037] The server then passes the received inquiry to the sentiment engine, which analyzes the user's emotions. The sentiment engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use my new smartphone!", it determines that the user is confused.

[1038] Category classification and selection of responsible persons

[1039] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "product support," it will assign a representative with particularly high responsiveness to users who appear confused.

[1040] Priority setting

[1041] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[1042] Routing to the responsible person

[1043] The server routes the inquiry to the selected person in charge. The routed inquiry is then notified to the person in charge's terminal. For example, the "product support" person receives the notification and checks the inquiry.

[1044] Operation by the person in charge

[1045] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow these steps for instructions on how to use your new smartphone," and sends it to the user via the server.

[1046] User reception

[1047] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions on "How to use your new smartphone" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[1048] Specific example

[1049] For example, a user in a store might type, "I don't know how to use my new smartphone!" The system categorizes this as "Product Support," recognizes the user's emotion as "Confused," and sets the priority to "High." It then sends a notification to the relevant staff member indicating "Urgent Support Needed" to encourage a quick response. An example of user input in this case is as follows:

[1050] I don't know how to use my new smartphone!

[1051] Through the above process, it becomes possible to provide prompt and appropriate responses in physical stores, taking into account customer emotions and the priority of inquiries.

[1052] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1053] Step 1:

[1054] Users scan a QR code in the store using their smartphone or smart glasses, enter their inquiry, and press the submit button. This input data is in text format and is sent to the server when the submit button is pressed.

[1055] Input: Inquiry details (text format)

[1056] Output: Query content sent to the server

[1057] Step 2:

[1058] The server receives the query content sent by the user and temporarily stores it in storage. This process makes the query content accessible within the server.

[1059] Input: Inquiry received from the user

[1060] Output: Query content stored in storage

[1061] Step 3:

[1062] The server analyzes the query data stored in storage using natural language processing (NLP) techniques. The analyzed data is then categorized into specific categories. For example, based on the keyword "How to use a new smartphone," it might be categorized as "product support."

[1063] Input: Query content stored in storage

[1064] Output: Inquiry content categorized

[1065] Step 4:

[1066] The server uses an emotion engine to recognize the user's emotions based on the analyzed query content. Specifically, it analyzes the context and vocabulary of the input text to identify the emotions the user is experiencing (e.g., confusion, anger, joy, etc.).

[1067] Input: Analyzed query content

[1068] Output: Recognized emotion information

[1069] Step 5:

[1070] The server prioritizes responses based on the results of category classification and sentiment recognition. For example, if the user is confused, it sets a high priority and clearly indicates that a prompt response is needed.

[1071] Input: Inquiry content categorized and recognized sentiment information

[1072] Output: Set response priority

[1073] Step 6:

[1074] The server selects the appropriate person in charge based on category and priority, and routes the inquiry to that person. A notification of the inquiry is sent to the person in charge's terminal. For example, a "product support" person receives the notification.

[1075] Input: Category, recognized emotion information, set response priority

[1076] Output: Inquiry notification sent to the person in charge

[1077] Step 7:

[1078] The person using the terminal receives a notification from the server, displays the inquiry details, and creates the necessary response. Once the response is complete, the person sends it to the server.

[1079] Input: Inquiry details notified to the person in charge

[1080] Output: Answer created by the person in charge

[1081] Step 8:

[1082] The server receives the response sent by the representative and forwards it to the customer. This is done by displaying the response on the customer's smartphone or smart glasses. This process allows the customer to verify the received response.

[1083] Input: Response received from the person in charge

[1084] Output: Response sent to the customer

[1085] Step 9:

[1086] The user receives the response sent from the server and evaluates whether the problem has been resolved. If necessary, the user may enter and resubmit additional inquiries.

[1087] Input: Response received from the server

[1088] Output: User ratings and additional inquiries (if applicable)

[1089] 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.

[1090] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1091] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1092] [Fourth Embodiment]

[1093] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1094] 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.

[1095] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[1096] 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.

[1097] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[1098] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1099] 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.

[1100] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1101] 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.

[1102] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1103] The 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.

[1104] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1105] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1106] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system has the functionality to receive customer inquiries, analyze them, route them to the appropriate person in charge, and finally send the answer to the customer.

[1107] User actions

[1108] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[1109] Server Processing

[1110] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[1111] The server then selects the appropriate person to handle the inquiry based on the classified category and routes the inquiry to that person. The list of persons is pre-registered within the server, and the person in charge for each category is defined. For example, an inquiry in the "New Product Support" category will be routed to the new product support person.

[1112] Operation by the person in charge

[1113] The person using the terminal receives a notification from the server and checks the content of the inquiry. The person checks the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates a response saying, "Please check the following steps for how to use the new product," and sends it to the user via the server.

[1114] User reception

[1115] The user receives a response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user can also submit additional questions.

[1116] Specific example

[1117] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it under "repair services." It then routes the inquiry to the appropriate representative, who creates and responds with appropriate repair service information. This process is repeated until the user receives the response and the problem is resolved.

[1118] In this way, the system of the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[1119] The following describes the processing flow.

[1120] Step 1:

[1121] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[1122] Step 2:

[1123] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[1124] Step 3:

[1125] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[1126] Step 4:

[1127] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[1128] Step 5:

[1129] The server selects the appropriate person in charge based on its classification category. The person in charge is chosen from a predefined list of persons in charge for each category. For example, a person in charge of the "New Product Support" category is selected.

[1130] Step 6:

[1131] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification.

[1132] Step 7:

[1133] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[1134] Step 8:

[1135] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[1136] Step 9:

[1137] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[1138] Step 10:

[1139] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[1140] Step 11:

[1141] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[1142] In this way, by executing each processing step sequentially, the process from receiving the inquiry to providing the answer is carried out efficiently.

[1143] (Example 1)

[1144] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1145] To respond quickly and appropriately to customer inquiries, it is necessary to properly analyze incoming inquiries and route them to the appropriate personnel. However, in conventional systems, this process was often done manually, which was time-consuming and carried the risk of delays and errors in responses by personnel. This resulted in decreased customer satisfaction and negatively impacted the company's credibility.

[1146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1147] In this invention, the server includes means for receiving user-entered inquiry content, means for temporarily storing the received inquiry content, means for analyzing the stored inquiry content using natural language processing technology and classifying it into categories, means for selecting an appropriate person in charge based on the category and routing the inquiry, and means for sending the response created by the person in charge to the user. This enables rapid and accurate analysis of inquiry content and automatic routing to the appropriate person in charge, thereby improving customer satisfaction and reducing the workload on the person in charge.

[1148] A "user" is a person or entity that uses the system to submit a request.

[1149] "Inquiry content" refers to the text data of information and questions that a user sends to the server through the system.

[1150] "Means of receiving" refers to the methods and system components that allow the server to retrieve the content of inquiries sent by users.

[1151] "Means of temporary storage" refers to the method or system for storing received inquiry content in temporary data storage.

[1152] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human language, and specifically refers to algorithms and tools that perform text analysis and keyword extraction.

[1153] A "category" refers to the type or group of inquiry content, and is an area or section classified based on the analysis results.

[1154] A "person in charge" is a specialist or employee selected to handle inquiries in a specific category.

[1155] "Routing methods" refer to the methods and systems used to distribute inquiries to the appropriate personnel after analyzing the content.

[1156] A "response" is a solution or information that a representative creates based on an inquiry and provides to the user.

[1157] "Means of transmission" refers to the methods and systems used to deliver the responses prepared by the person in charge to the user.

[1158] A "server" is a central processing unit that receives user inquiries, analyzes them, routes them to the appropriate person, and sends the response.

[1159] Modes for carrying out the invention

[1160] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates a series of processes, including receiving customer inquiries, analyzing them, routing them to the appropriate personnel, and finally sending the answers to the customers.

[1161] Hardware and software configuration

[1162] server

[1163] The server will be a computer equipped with a high-performance processor and sufficient memory. Furthermore, it will utilize high-speed storage (e.g., Amazon S3, Google Cloud Storage) for temporary data storage. The server will also have software installed to implement natural language processing technologies (e.g., Google Cloud Natural Language API, Microsoft Azure Text Analytics).

[1164] terminal

[1165] The devices that users use to access the system are internet-connected devices such as personal computers and smartphones. These devices are equipped with a web browser and can access the system's web pages. Similarly, administrators also access the system using devices such as personal computers and tablets.

[1166] Inquiry reception and analysis

[1167] The user enters their inquiry in text format through their device's web browser and clicks the submit button. The server receives the inquiry sent from the user's device and temporarily stores it in storage. The stored data is analyzed using natural language processing techniques, and the content of the inquiry is classified into a specific category.

[1168] Category classification and routing

[1169] The server categorizes the analyzed query content and selects the appropriate person to handle it. A list of assigned personnel is pre-registered within the server, with each category defined accordingly. The server automatically routes the query to the appropriate person based on its category.

[1170] Create and submit your response.

[1171] The person in charge receives a notification from the server and reviews the inquiry. They create an appropriate response and send it back to the user via the server. The user receives the response on their device and checks if the problem has been resolved. If necessary, the user can resubmit the inquiry.

[1172] Specific example

[1173] For example, the following shows the specific process when a user submits an inquiry asking about repair services. The server analyzes the inquiry using the Google Cloud Natural Language API and categorizes it as "repair services." The server selects a person in charge of "repair services" and routes the inquiry to that person. The person in charge creates detailed information about the repair services and sends the response to the user. The user receives the response and checks whether the problem has been resolved.

[1174] Examples of prompt statements

[1175] An example of input to the AI ​​model generated by the system is, "Analyze the following inquiry and classify it into a category: 'I want to know about repair services.'" Using this prompt, the AI ​​model can appropriately analyze the inquiry and identify the category.

[1176] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1177] Step 1:

[1178] Users access the system's webpage using a browser on a device such as a PC or smartphone. They enter text such as "I don't know how to use the new product" into the inquiry form and click the submit button. The entered text data is sent to the server.

[1179] Step 2:

[1180] The server receives HTTP POST requests sent from the user's device. The received query content is temporarily stored in storage (e.g., Amazon S3 or Google Cloud Storage). The input is text data from the user, and the output is the data stored in temporary storage.

[1181] Step 3:

[1182] The server retrieves stored query data and performs analysis using natural language processing technology (e.g., Google Cloud Natural Language API). The input is stored text data, and the output is keyword and category information extracted as a result of the analysis. Specifically, it extracts the keyword "how to use the new product" from the text and classifies it into the "new product support" category.

[1183] Step 4:

[1184] The server categorizes queries into specific categories based on the analysis results. Inputs are keywords and analysis results, while output is category information. For example, a query like "I want to know about repair services" would be categorized as "repair services."

[1185] Step 5:

[1186] The server selects the appropriate contact person from a list of contact persons defined for each category and routes the inquiry to that contact person. The input is category information, and the output is routing information to the contact person. For example, an inquiry in the "New Product Support" category will be routed to the New Product Support contact person.

[1187] Step 6:

[1188] The person using the terminal receives a notification from the server and checks the content of the inquiry. The input is routing information sent from the server, and the output is the result of the person's confirmation. The person checks the content of the inquiry, which is "I don't know how to use the new product."

[1189] Step 7:

[1190] The person in charge creates an appropriate response to the inquiry they have received. The input is the inquiry, and the output is the response text. For example, the person in charge would write specific instructions such as "Please check the following steps for how to use the new product" and send the response to the server.

[1191] Step 8:

[1192] The server resends the response received from the person in charge to the user. The input is the response text created by the person in charge, and the output is the response sent to the user. The user receives the response on their terminal and checks whether the problem has been resolved. Specifically, the server sends the response to the user via an HTTP response.

[1193] Step 9:

[1194] The user reviews the response sent from the server on their device and evaluates whether the problem has been resolved. The input is the response text sent from the server, and the output is the user's evaluation result. For example, if a user reviews the detailed instructions for "how to use the new product" and the problem is resolved, they will not need to submit any further inquiries. If necessary, the user will submit another question.

[1195] (Application Example 1)

[1196] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1197] Traditional customer support systems had the problem of requiring manual analysis and routing of inquiries, resulting in time-consuming processing. Furthermore, the lack of real-time inquiry support via smartphones made it difficult to improve customer satisfaction.

[1198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1199] In this invention, the server includes means for receiving customer inquiries, means for analyzing the inquiry content and classifying it into the appropriate category, means for routing the inquiry to the person in charge corresponding to the category, means for sending the person in charge's response to the customer, means for inputting the inquiry using a terminal including a smartphone, means for the user to select a voice input option, means for the customer to send the inquiry through a smartphone application, and means for analyzing the inquiry content in real time. This enables quick and appropriate responses to inquiries.

[1200] A "customer" refers to a consumer who makes inquiries or purchases from a company or organization that provides services or products.

[1201] "Means for receiving inquiries" refers to devices or software used to receive questions and requests sent by customers.

[1202] "Means of analysis" refers to devices or software used to analyze the content of received inquiries and understand their purpose and intent.

[1203] "Means of categorization" refers to a device or software that classifies the analyzed query content as belonging to a specific category.

[1204] "Means for routing inquiries to the appropriate person" refers to a device or software that forwards inquiry content to the appropriate person based on its classified category.

[1205] "Means of sending responses from the person in charge to the customer" refers to a device or software that returns the response prepared by the person in charge to the customer.

[1206] "Means of entering inquiries using a device including a smartphone" refers to a device or method of entering inquiry details using a mobile device such as a smartphone.

[1207] "Means for users to select voice input options" refers to a device or software that provides users with the option to input their inquiry content by voice instead of text.

[1208] "Means by which customers submit inquiries via smartphone applications" refers to devices or software that allow customers to submit inquiries using a smartphone application.

[1209] "Means of real-time analysis" refers to a device or software that performs analysis the moment the inquiry is sent.

[1210] System Overview

[1211] This invention is a customer inquiry handling system designed to provide prompt and appropriate customer support. Its main components include a server, a customer terminal (e.g., a smartphone), and a staff terminal.

[1212] Program Overview

[1213] The server receives inquiries from customers and analyzes the content using natural language processing (NLP) techniques. The analyzed content is categorized and routed to the appropriate person in charge. The person in charge then sends their response back to the customer via the server.

[1214] Hardware and software configuration

[1215] Hardware:

[1216] Server: For example, a cloud server such as AWS EC2.

[1217] Customer device: Smartphone (Android / iOS)

[1218] Personnel terminal: PC or smartphone

[1219] software:

[1220] Server-side: Flask (Python microframework), TextBlob (NLP library), JSON (data format)

[1221] Customer terminal: Smartphone application for sending inquiries

[1222] Processing flow

[1223] 1. Customer actions:

[1224] Users use their smartphones to input their inquiries as text or voice. For example, they might type, "I don't know how to use the new product," and then send it.

[1225] 2. Server processing:

[1226] The server receives customer inquiries and analyzes them in real time. Based on the analysis, inquiries are categorized, such as "New Product Support," and routed to the appropriate pre-registered representative. The server uses Flask to receive and analyze inquiries and TextBlob for natural language processing.

[1227] 3. Actions taken by the person in charge:

[1228] A notification arrives on the employee's terminal, and they check the inquiry details. The employee then creates a response based on the content and sends it to the customer via the server. For example, they might create specific instructions such as, "Please check the following steps for how to use the new product," and send the response.

[1229] 4. Customer receipt:

[1230] The customer receives a response from the representative and confirms whether the issue has been resolved. They can also contact the representative again if necessary.

[1231] Specific example

[1232] For example, if a user submits an inquiry stating, "I don't know how to use the new product," the server analyzes the content and categorizes it as "New Product Support." Then, a representative creates a specific response, such as "Please follow these steps to learn how to use the new product," and sends it to the user via the server.

[1233] Example of a prompt

[1234] "I don't know how to use the new product."

[1235] "I want to know about repair services."

[1236] In this way, the present invention automates a series of processes including receiving, analyzing, classifying, routing, and sending responses to inquiries, thereby improving customer satisfaction and distributing the workload of staff members.

[1237] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1238] Program processing steps

[1239] Step 1:

[1240] User inquiry input

[1241] Users use their smartphones to enter their inquiries as text or voice.

[1242] Input: Inquiry content entered by the user on the smartphone application.

[1243] Output: The inquiry details are sent to the smartphone application and then forwarded to the server.

[1244] Specific action: The user types "I don't know how to use the new product" into their smartphone and presses the send button.

[1245] Step 2:

[1246] Server query received

[1247] The server receives the query content sent by the user.

[1248] Input: Inquiry content sent from a smartphone application

[1249] Output: The query content is temporarily stored on the server.

[1250] Specific operation: The server uses Flask to receive the query content sent by the user in JSON format.

[1251] Step 3:

[1252] Server query analysis

[1253] The server analyzes the received query content using natural language processing technology and classifies it into categories.

[1254] Input: Query content stored on the server

[1255] Output: Category as an analysis result (e.g., "New Product Support")

[1256] Specific operation: The server uses the TextBlob library to analyze the query content and classifies it into the "New Product Support" category based on the keyword "How to use the new product".

[1257] Step 4:

[1258] Server assignment routing

[1259] The server routes inquiries to the appropriate person based on the analyzed category.

[1260] Input: Inquiry content categorized

[1261] Output: Inquiry notification to the person in charge

[1262] Specific operation: The server selects a representative from the list of representatives who corresponds to the "New Product Support" category and forwards the inquiry details to the representative's terminal.

[1263] Step 5:

[1264] Confirmation of inquiries and creation of responses by the person in charge

[1265] After receiving the notification, the person in charge will review the inquiry and prepare a response.

[1266] Input: Inquiry details routed to the assigned representative.

[1267] Output: Created response content

[1268] Specific action: The person in charge will use a PC or smartphone to create a specific response such as, "Please check the following steps for instructions on how to use the new product."

[1269] Step 6:

[1270] Server response submission

[1271] The server receives the response prepared by the person in charge and sends it to the customer.

[1272] Input: Response sent by the person in charge

[1273] Output: Sending a response to the customer

[1274] Specific operation: The server receives the response from the person in charge and sends it to the customer via a smartphone application.

[1275] Step 7:

[1276] Receiving and confirming user responses

[1277] The user receives the response sent from the server and confirms it.

[1278] Input: Response sent from the server

[1279] Output: Problem solved or additional inquiry

[1280] Specific actions: The user opens the smartphone application, checks the response from the representative, and sends additional inquiries if necessary.

[1281] Through this series of processing steps, customer inquiries are addressed quickly and appropriately.

[1282] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1283] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. The system receives and analyzes customer inquiries, routes them to the appropriate personnel, and ultimately sends the answers to the customers. Furthermore, by incorporating an emotion engine, this invention makes it possible to recognize user emotions and reflect them in prioritizing responses and selecting the appropriate personnel.

[1284] User actions

[1285] Users access the system using devices such as PCs or smartphones and enter their inquiries. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit the message, "I don't know how to use the new product."

[1286] Server Processing

[1287] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "how to use the new product" might be classified into the "new product support" category.

[1288] How the emotion engine works

[1289] The server then passes the received inquiry to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[1290] Category classification and selection of responsible persons

[1291] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "New Product Support," it will assign a representative with particularly high responsiveness to users who appear confused.

[1292] Priority setting

[1293] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[1294] Routing to the responsible person

[1295] The server routes inquiries to the selected contact person. The routed inquiry details are then sent to the contact person's terminal. For example, the "New Product Support" person receives the notification and checks the inquiry details.

[1296] Operation by the person in charge

[1297] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow the instructions below for how to use the new product," and sends it to the user via the server.

[1298] User reception

[1299] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[1300] Specific example

[1301] For example, if a user submits an inquiry asking about repair services, the server analyzes the content and categorizes it as "repair services." If the emotion engine then detects that the user is experiencing anxiety, it prioritizes the inquiry and responds quickly. The inquiry is routed to the appropriate representative, who promptly provides the user with information about repair services. In this way, responses that consider the user's emotions become possible, leading to improved customer satisfaction.

[1302] The system of this invention automates a series of processes including receiving, analyzing, classifying, routing, sending responses, sentiment recognition, and prioritizing inquiries, thereby improving customer satisfaction and distributing the workload of staff.

[1303] The following describes the processing flow.

[1304] Step 1:

[1305] The user enters their inquiry into the input form and clicks the submit button. For example, they might enter, "I don't know how to use the new product."

[1306] Step 2:

[1307] The server receives the user's inquiry. The received data is stored in text format. For example, it is stored in the database as a record with attributes such as "user_id", "message", and "timestamp".

[1308] Step 3:

[1309] The server analyzes the content of the received inquiry. Natural language processing (NLP) techniques are used to analyze the message and extract important keywords and phrases. For example, it might recognize the phrase "how to use the new product."

[1310] Step 4:

[1311] The server categorizes inquiries based on keywords it extracts. For example, "How to use the new product" would be categorized under "New Product Support."

[1312] Step 5:

[1313] The server passes the query content to the emotion engine. The emotion engine analyzes the text content and recognizes the user's emotions (e.g., anger, frustration, joy). For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused.

[1314] Step 6:

[1315] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, it will be given a higher priority.

[1316] Step 7:

[1317] The server selects the most suitable representative based on the emotion engine's analysis results and categories. For example, for a user in the "New Product Support" category who is confused, a representative with particularly high responsiveness will be selected.

[1318] Step 8:

[1319] The server routes the inquiry to the designated contact person. The routed inquiry is then notified to the contact person's terminal. For example, the "New Product Support" contact person receives the notification and checks the inquiry details.

[1320] Step 9:

[1321] The person using the terminal checks the notification from the server and displays the inquiry. For example, the person who receives the notification checks the inquiry, "I don't know how to use the new product."

[1322] Step 10:

[1323] The person using the terminal creates the response to the inquiry. For example, they might enter a response such as, "Please follow the instructions below for how to use the new product."

[1324] Step 11:

[1325] The person using the terminal sends the response they've created to the server. The response is then forwarded to the user via the server. For example, the response data is sent to the server, and the server then sends that response to the user.

[1326] Step 12:

[1327] The user receives a response from the server. For example, they might receive a response via email or app notification stating, "Please follow the instructions below for how to use the new product."

[1328] Step 13:

[1329] The user reviews the answer and checks if the problem has been resolved. If necessary, the user can submit additional questions. For example, if they submit an additional question such as "Please provide more detailed instructions," the user returns to step 1.

[1330] In this way, by executing each processing step sequentially, the process from receiving inquiries to providing answers, and even recognizing user sentiment and prioritizing responses, is carried out efficiently.

[1331] (Example 2)

[1332] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1333] While there is a demand for prompt and appropriate responses to customer inquiries, traditional systems often rely on manual processes for analyzing inquiry content, recognizing sentiment, routing inquiries to the appropriate personnel, and prioritizing them, resulting in inefficiency. Furthermore, responses that do not consider customer emotions can lead to decreased customer satisfaction. This, in turn, presents challenges in terms of accuracy and speed in handling inquiries.

[1334] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1335] In this invention, the server includes means for receiving inquiry content, means for analyzing the received inquiry content and classifying it into the appropriate category, means for sentiment analysis of the received inquiry content, means for setting response priorities based on the analysis results, means for routing the inquiry to the person in charge corresponding to the category and priority, and means for sending the response from the person in charge to the entity that made the inquiry. This enables automatic analysis of inquiry content, priority setting based on sentiment recognition, and automatic routing to the most suitable person in charge.

[1336] "Inquiry content" refers to text data such as questions, requests, and complaints that customers send to the system.

[1337] "Analysis" is the process of understanding, classifying, or evaluating the meaning and intent of a query using natural language processing techniques.

[1338] "Natural language processing technology" refers to the technology that enables computers to understand and process human language. Specifically, it includes text analysis, sentiment analysis, and semantic analysis.

[1339] A "category" is a group of inquiries that are classified based on a specific topic or theme. Examples include "new product support" and "repair services."

[1340] "Sentiment analysis" is the process of extracting and evaluating the user's emotions (e.g., joy, anger, confusion, dissatisfaction, etc.) contained in the inquiry content from text data.

[1341] "Priority" is a criterion used to determine the order in which inquiries are handled. Typically, it is set based on sentiment analysis results, and high-priority inquiries are handled more quickly.

[1342] A "person in charge" refers to a person or team responsible for handling a specific category or inquiry.

[1343] "Routing" is the process of automatically assigning inquiries to the appropriate person in charge based on analysis results and priority settings.

[1344] A "response" is text data containing information or solutions provided by the person in charge in response to an inquiry.

[1345] This invention is an integrated customer service system for responding quickly and appropriately to customer inquiries. This system automates the reception, analysis, sentiment analysis, categorization, prioritization, routing to the appropriate person, and response transmission of inquiries. To implement this system, a high-performance server and terminals for users and staff are required.

[1346] System hardware and software configuration

[1347] The server requires a high-performance processor (e.g., an Intel Xeon processor) and large-capacity storage (e.g., an SSD). This server utilizes natural language processing techniques to analyze query content and sentiment analysis. Specifically, it uses Python and libraries such as TensorFlow and spaCy. Furthermore, it employs generative AI models such as GPT-3 for sentiment analysis.

[1348] Users and staff members need internet-connected devices such as personal computers or smartphones. Users access the system using a web browser (such as Google Chrome or Safari), enter their inquiries, and submit them. Staff members receive inquiry notifications from the server using a web browser or a dedicated application.

[1349] System operation example

[1350] Users access the inquiry form through a web browser, enter a message such as "I don't know how to use the new product," and click the submit button. This inquiry is sent to the server and temporarily stored in cloud storage such as Amazon S3 or Google Cloud Storage. The stored data is analyzed using natural language processing techniques with TensorFlow or spaCy and categorized under "New Product Support."

[1351] Next, the server passes the inquiry to the emotion engine, which uses a generative AI model (e.g., GPT-3) to analyze the user's emotions. For example, from the query "I don't know how to use the new product!", it determines that the user is confused.

[1352] Based on the analysis results, the server sets the priority for responding to inquiries. Users who are confused are given a high priority and require a quick response. Based on category and priority, inquiries are automatically routed to the most suitable person in charge. The person in charge receives the inquiry through a dedicated application or email notification and responds promptly.

[1353] The person in charge reviews the inquiry and creates an appropriate response. For example, they create a specific response such as, "Please follow the steps below for instructions on how to use the new product," and send it to the user via the server. The user receives the response from the server, and the problem is resolved.

[1354] Example of a prompt

[1355] "Create a system that analyzes customer inquiries, categorizes them appropriately, performs sentiment analysis to prioritize responses, and routes them to the appropriate staff member."

[1356] This system automates a series of processes, including receiving, analyzing, recognizing sentiment, categorizing, prioritizing, routing, and sending responses, thereby improving customer satisfaction and distributing the workload among staff.

[1357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1358] Step 1:

[1359] Users access the system using devices such as personal computers and smartphones. They access the inquiry form through a web browser (such as Google Chrome or Safari), enter their inquiry in text format, and click the submit button. For example, a user might enter "I don't know how to use the new product" and submit it. This action sends the inquiry to the server. The input is the user's text data, and the output is the data sent to the server.

[1360] Step 2:

[1361] The server receives user inquiries and temporarily stores them in cloud storage (such as Amazon S3 or Google Cloud Storage). After storage, it analyzes the inquiry content using natural language processing libraries such as TensorFlow or spaCy with Python code. As a result of the analysis, the inquiry content is classified into a specific category. For example, the keyword "How to use the new product" is classified into the "New Product Support" category. The input is the received text data, and the output is the analysis results and category classification data.

[1362] Step 3:

[1363] The server passes the received inquiry to the sentiment engine. The sentiment engine uses a generative AI model (e.g., GPT-3) to perform sentiment analysis on the inquiry. It recognizes the user's emotions (e.g., anger, confusion, joy) from the text content. For example, from the emphasized content, "I don't know how to use the new product!", it determines that the user is confused. The input is the text data to be analyzed, and the output is the sentiment analysis result.

[1364] Step 4:

[1365] The server further classifies the inquiry content based on the NLP analysis results and sentiment analysis results, and assigns it to the appropriate category. For example, if it is classified under the "New Product Support" category, it selects a highly capable representative to assist the confused user. The input is category classification data and sentiment analysis data, and the output is information on the selection of the optimal representative.

[1366] Step 5:

[1367] The server prioritizes responses based on the analysis results of the emotion engine. For example, if a user is highly dissatisfied, the server will set a high priority for the response, requiring a quick response. The input is emotion analysis data, and the output is priority setting data.

[1368] Step 6:

[1369] The server routes inquiries to the designated contact person. The routing is automated, and notifications are sent to the contact person's device (e.g., laptop or desktop PC). For example, a "new product support" contact person receives the notification and checks the inquiry. Inputs include the contact person's selection information and the inquiry content, while output is the notification sent to the contact person.

[1370] Step 7:

[1371] The person using the terminal receives a notification from the server and displays the inquiry details. The person reviews the content and creates an appropriate response. For example, they might create a specific response such as, "Please follow the instructions below for how to use the new product," and send it back to the user via the server. The input consists of the inquiry and the response, and the output is the response data.

[1372] Step 8:

[1373] The user receives the response sent from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions for "how to use the new product" and feels the problem is resolved, no further inquiry is necessary. If needed, the user can enter additional questions and resubmit. The input is the received response data, and the output is the user's evaluation and new inquiry data.

[1374] (Application Example 2)

[1375] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1376] In modern brick-and-mortar stores, prompt and appropriate responses to customer inquiries are crucial for improving customer satisfaction. However, traditional inquiry response systems often failed to consider customer emotions and were ineffective at routing inquiries to the appropriate staff. As a result, even in cases of customer dissatisfaction or urgency, prompt responses were frequently delayed, leading to decreased customer satisfaction and damage to the store's reputation. To address this challenge, a system is needed that considers customer emotions and priorities to optimally handle inquiries.

[1377] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1378] In this invention, the server includes means for receiving customer inquiries, means for analyzing the received inquiries and classifying them into the appropriate categories, means for analyzing the inquiries and recognizing the customer's emotions, means for setting response priorities based on the categories and recognized emotions, means for routing inquiries to personnel corresponding to the categories and priorities, and means for sending responses from personnel to the customers. This enables quick and appropriate responses in physical stores that take into account customer emotions and inquiry priorities.

[1379] "Means for receiving customer inquiries" refers to the technical equipment that allows customers to input questions about products and services using devices such as smartphones or smart glasses within a physical store, and for a server to receive those inquiries.

[1380] "A means of analyzing received inquiries and classifying them into the appropriate category" refers to a system that uses natural language processing technology to analyze received text data and classify it into the appropriate category, such as product support or customer service, based on its content.

[1381] "Means of analyzing inquiry content to recognize customer emotions" refers to a function that uses natural language processing technology to automatically detect and recognize customer emotions (e.g., joy, dissatisfaction, confusion, etc.) from received text.

[1382] "Means for setting response priorities based on categories and perceived emotions" refers to a technology for evaluating the necessity and urgency of a response based on analyzed categories and customer emotion information, and for setting the priority of the response (high, medium, low, etc.).

[1383] "A means of routing inquiries to the appropriate person based on category and priority" refers to a system that automatically distributes inquiries to the most suitable person according to the set category and priority, and notifies the person's terminal.

[1384] "Means of sending responses from staff to customers" refers to the technical equipment used to send responses prepared by staff to customers, allowing customers to view the responses on devices such as smartphones or smart glasses.

[1385] "Natural language processing technology" refers to artificial intelligence technologies used for processing text data, such as analysis, classification, and sentiment recognition. Examples include libraries like TextBlob and NLTK.

[1386] "Customer emotions" refers to the emotional nuances of the words included in an inquiry, encompassing emotional states such as joy, anger, dissatisfaction, and confusion.

[1387] "Response priority" is an indicator that shows how quickly a customer inquiry needs to be addressed, and is expressed as a rank such as "high priority" or "low priority."

[1388] This invention is a system for responding quickly and appropriately to customer inquiries in physical stores. The system receives customer inquiries, analyzes them, routes them to the appropriate staff member, and finally sends the answer to the customer. Furthermore, by incorporating an emotion engine, it can recognize customer emotions and reflect them in prioritizing responses and selecting the appropriate staff member.

[1389] User actions

[1390] Users access the system using devices such as smartphones or smart glasses and enter their inquiries by scanning QR codes in the store. The inquiries are entered in text format and sent to the server by clicking the submit button. For example, a user might enter and submit "I don't know how to use my new smartphone!"

[1391] Server Processing

[1392] The server receives inquiries from users. The received inquiries are temporarily stored in storage and their content is analyzed using natural language processing (NLP) technology. As a result of the analysis, the inquiries are classified into specific categories. For example, the keyword "How to use a new smartphone" might be classified into the "Product Support" category.

[1393] How the emotion engine works

[1394] The server then passes the received inquiry to the sentiment engine, which analyzes the user's emotions. The sentiment engine recognizes the user's emotions (e.g., anger, frustration, joy) from the text content. For example, from the emphasized content, "I don't know how to use my new smartphone!", it determines that the user is confused.

[1395] Category classification and selection of responsible persons

[1396] The server categorizes inquiries based on analysis results from both the emotion engine and NLP, and selects the most suitable representative. For example, after categorizing an inquiry under "product support," it will assign a representative with particularly high responsiveness to users who appear confused.

[1397] Priority setting

[1398] Based on the analysis results from the emotion engine, the server sets the priority of responses. For example, if a user is highly dissatisfied, the priority is set high, requiring a quick response.

[1399] Routing to the responsible person

[1400] The server routes the inquiry to the selected person in charge. The routed inquiry is then notified to the person in charge's terminal. For example, the "product support" person receives the notification and checks the inquiry.

[1401] Operation by the person in charge

[1402] The person using the terminal receives a notification from the server and displays the inquiry. The person reviews the content and creates the necessary response. Once the response is created, it is sent back to the user via the server. For example, the person creates the response, "Please follow these steps for instructions on how to use your new smartphone," and sends it to the user via the server.

[1403] User reception

[1404] The user receives a response from the server. They review the received response and evaluate whether the problem has been resolved. For example, if the user reviews the detailed instructions on "How to use your new smartphone" and feels the problem is resolved, no further inquiries are necessary. The user can also submit additional questions if needed.

[1405] Specific example

[1406] For example, a user in a store might type, "I don't know how to use my new smartphone!" The system categorizes this as "Product Support," recognizes the user's emotion as "Confused," and sets the priority to "High." It then sends a notification to the relevant staff member indicating "Urgent Support Needed" to encourage a quick response. An example of user input in this case is as follows:

[1407] I don't know how to use my new smartphone!

[1408] Through the above process, it becomes possible to provide prompt and appropriate responses in physical stores, taking into account customer emotions and the priority of inquiries.

[1409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1410] Step 1:

[1411] Users scan a QR code in the store using their smartphone or smart glasses, enter their inquiry, and press the submit button. This input data is in text format and is sent to the server when the submit button is pressed.

[1412] Input: Inquiry details (text format)

[1413] Output: Query content sent to the server

[1414] Step 2:

[1415] The server receives the query content sent by the user and temporarily stores it in storage. This process makes the query content accessible within the server.

[1416] Input: Inquiry received from the user

[1417] Output: Query content stored in storage

[1418] Step 3:

[1419] The server analyzes the query data stored in storage using natural language processing (NLP) techniques. The analyzed data is then categorized into specific categories. For example, based on the keyword "How to use a new smartphone," it might be categorized as "product support."

[1420] Input: Query content stored in storage

[1421] Output: Inquiry content categorized

[1422] Step 4:

[1423] The server uses an emotion engine to recognize the user's emotions based on the analyzed query content. Specifically, it analyzes the context and vocabulary of the input text to identify the emotions the user is experiencing (e.g., confusion, anger, joy, etc.).

[1424] Input: Analyzed query content

[1425] Output: Recognized emotion information

[1426] Step 5:

[1427] The server prioritizes responses based on the results of category classification and sentiment recognition. For example, if the user is confused, it sets a high priority and clearly indicates that a prompt response is needed.

[1428] Input: Inquiry content categorized and recognized sentiment information

[1429] Output: Set response priority

[1430] Step 6:

[1431] The server selects the appropriate person in charge based on category and priority, and routes the inquiry to that person. A notification of the inquiry is sent to the person in charge's terminal. For example, a "product support" person receives the notification.

[1432] Input: Category, recognized emotion information, set response priority

[1433] Output: Inquiry notification sent to the person in charge

[1434] Step 7:

[1435] The person using the terminal receives a notification from the server, displays the inquiry details, and creates the necessary response. Once the response is complete, the person sends it to the server.

[1436] Input: Inquiry details notified to the person in charge

[1437] Output: Answer created by the person in charge

[1438] Step 8:

[1439] The server receives the response sent by the representative and forwards it to the customer. This is done by displaying the response on the customer's smartphone or smart glasses. This process allows the customer to verify the received response.

[1440] Input: Response received from the person in charge

[1441] Output: Response sent to the customer

[1442] Step 9:

[1443] The user receives the response sent from the server and evaluates whether the problem has been resolved. If necessary, the user may enter and resubmit additional inquiries.

[1444] Input: Response received from the server

[1445] Output: User ratings and additional inquiries (if applicable)

[1446] 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.

[1447] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1448] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1449] 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.

[1450] Figure 9 shows an 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.

[1451] 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.

[1452] 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.

[1453] 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, motorcycles, etc., 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, for example, based 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.

[1454] 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."

[1455] 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.

[1456] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1457] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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 the like 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.

[1466] 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.

[1467] The following is further disclosed regarding the embodiments described above.

[1468] (Claim 1)

[1469] A means of receiving customer inquiries,

[1470] A means of analyzing the content of received inquiries and classifying them into the appropriate category,

[1471] A means of routing inquiries to the person in charge who corresponds to the category,

[1472] A means of sending the response from the person in charge to the customer,

[1473] A system that includes this.

[1474] (Claim 2)

[1475] The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

[1476] (Claim 3)

[1477] The system according to claim 1, which automates routing to the appropriate person.

[1478] "Example 1"

[1479] (Claim 1)

[1480] A means of receiving the inquiry content entered by the user,

[1481] A means of temporarily saving the content of received inquiries,

[1482] A means of analyzing and classifying saved query content into categories using natural language processing technology,

[1483] A means of selecting the appropriate person in charge and routing inquiries based on category,

[1484] A means of sending the response created by the person in charge to the user,

[1485] A system that includes this.

[1486] (Claim 2)

[1487] The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

[1488] (Claim 3)

[1489] The system according to claim 1, which automates routing to the appropriate person.

[1490] "Application Example 1"

[1491] (Claim 1)

[1492] A means of receiving customer inquiries,

[1493] A means of analyzing the content of received inquiries and classifying them into the appropriate category,

[1494] A means of routing inquiries to the person in charge who corresponds to the category,

[1495] A means of sending the response from the person in charge to the customer,

[1496] A means of entering an inquiry using a device including a smartphone,

[1497] A means for the user to select a voice input option,

[1498] A means for customers to submit inquiries via a smartphone application,

[1499] A means of analyzing inquiry content in real time,

[1500] A system that includes this.

[1501] (Claim 2)

[1502] The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

[1503] (Claim 3)

[1504] The system according to claim 1, which automates routing to the appropriate person.

[1505] "Example 2 of combining an emotion engine"

[1506] (Claim 1)

[1507] Means of receiving inquiries,

[1508] A means of analyzing the content of received inquiries and classifying them into the appropriate category,

[1509] A means of performing sentiment analysis on received inquiries,

[1510] A means of setting priority for response based on the analysis results,

[1511] A means of routing inquiries to the person in charge corresponding to the category and priority,

[1512] A means of sending the response from the person in charge to the entity that made the inquiry,

[1513] A system that includes this.

[1514] (Claim 2)

[1515] The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

[1516] (Claim 3)

[1517] The system according to claim 1, which uses a generative AI model for sentiment analysis of the content of an inquiry.

[1518] (Claim 4)

[1519] The system according to claim 1, which automates routing and notifies the person in charge.

[1520] "Application example 2 when combining with an emotional engine"

[1521] (Claim 1)

[1522] A means of receiving customer inquiries,

[1523] A means of analyzing the content of received inquiries and classifying them into the appropriate category,

[1524] A means of analyzing the content of inquiries to recognize customer emotions,

[1525] A means of setting priorities for responses based on categories and perceived emotions,

[1526] A means of routing inquiries to the appropriate person in charge based on category and priority,

[1527] A means of sending the response from the person in charge to the customer,

[1528] A system that includes this.

[1529] (Claim 2)

[1530] The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

[1531] (Claim 3)

[1532] The system according to claim 1, which automates routing to the appropriate person. [Explanation of symbols]

[1533] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving customer inquiries, A means of analyzing the content of received inquiries and classifying them into the appropriate category, A means of routing inquiries to the person in charge who corresponds to the category, A means of sending the response from the person in charge to the customer, A system that includes this.

2. The system according to claim 1, which analyzes the content of an inquiry using natural language processing technology.

3. The system according to claim 1, which automates routing to the responsible person.

Images