system

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a query from a customer; means for analyzing the received query using a generative AI model; means for selecting or generating an appropriate answer from a FAQ database or knowledgebase based on the analyzed result; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; and means for sending a final answer to the customer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Current customer support operations require not only quick responses to standard questions but also detailed responses tailored to individual customer needs. However, conventional systems often have difficulty properly analyzing the content of inquiries and responding quickly and accurately. This results in a decline in customer satisfaction and a decrease in the efficiency of support operations. The purpose of this invention is to solve these problems and improve the efficiency and quality of customer support. [Means for solving the problem]

[0005] The system of the present invention includes the following means: means for receiving an inquiry from a customer, means for analyzing the content of the received inquiry using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for providing the selected or generated answer to a customer support representative, means for the customer support representative to customize and confirm the provided answer, and means for sending the final answer to the customer. In particular, the analysis means evaluates the language, keywords, topic, and urgency of the inquiry, and the generated answer is displayed in a notification and on a dashboard. In this way, the speed and accuracy of inquiry processing are significantly improved, thereby improving customer satisfaction.

[0006] "Means for receiving customer inquiries" refers to an interface or mechanism that digitally inputs the inquiry content entered by the customer into the system.

[0007] "Means of analysis using a generative AI model" refers to the function of using machine learning algorithms, particularly natural language processing technology, to analyze the content of inquiries and perform analyses such as language determination and keyword extraction.

[0008] "Means for selecting from or generating an FAQ database or knowledge base" refers to the ability to search an existing FAQ list or knowledge base and extract appropriate answers or generate new answers as needed.

[0009] "Means provided to customer support agents" refers to a notification system or dashboard used to present generated responses to customer support staff.

[0010] "Means for customization and verification" refers to the interface and functionality that allows customer support staff to modify, add to, or verify the responses provided.

[0011] "Means for sending a final response to the customer" refers to the function that allows the customer support staff to send the confirmed response to the customer via email, chat, or other means of communication.

[0012] "Identifying the language" refers to identifying the language used from the text of the query.

[0013] "Keyword extraction" refers to detecting important words and phrases from the inquiry content.

[0014] "Topic classification" refers to classifying inquiries into specific categories or topics.

[0015] "Evaluating the urgency" refers to determining the importance and urgency of the inquiry.

[0016] "Notification and display on dashboard" refers to the ability to instantly notify and visually display the generated response to the customer support representative. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention includes the following major components for quickly and accurately processing customer inquiries:

[0039] Inquiry Receiving Module

[0040] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0041] Content Analysis Module

[0042] The server passes the received query content to the generative AI model and performs the following analysis:

[0043] Language detection: Automatically identify the language used from the query text.

[0044] Keyword extraction: Identify and extract important words and phrases.

[0045] Topic classification: Categorizing inquiries into specific topics or categories.

[0046] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0047] Answer selection / generation module

[0048] The server then queries the FAQ database or knowledge base based on the analysis results to find the appropriate answer. If the search results are insufficient, a new answer is automatically generated using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0049] Customer Support Delivery Module

[0050] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0051] Customization and Review Module

[0052] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and saved.

[0053] Module for sending answers to customers

[0054] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0055] Specific examples

[0056] For example, a user may send an inquiry saying, "Please tell me about returning a product."

[0057] 1. The server receives the query and stores it in a database.

[0058] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0059] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0060] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0061] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0062] 6. The server sends the final customized answer to the user.

[0063] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[0067] Step 2:

[0068] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[0069] Step 3:

[0070] The server adds the query to a queue and passes it as input to the generative AI model.

[0071] Step 4:

[0072] The generative AI model running on the server performs the following analysis:

[0073] Language detection: Identifying the language used from text.

[0074] Keyword extraction: Extracting important words and phrases from text.

[0075] Topical classification: Classifying content into specific categories or topics.

[0076] Urgency assessment: Assess urgency based on wording and content.

[0077] Step 5:

[0078] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[0079] Step 6:

[0080] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[0081] Step 7:

[0082] The server sends the searched and generated answer to the customer support agent's device, notifies the agent using the notification system, and displays the answer on the dashboard.

[0083] Step 8:

[0084] The customer support representative can review the response on their device and customize it as needed, for example by adding "more information about the return process."

[0085] Step 9:

[0086] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[0087] Step 10:

[0088] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[0089] Step 11:

[0090] The user receives the response and reviews the information that will help them solve the problem.

[0091] Example 1

[0092] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0093] Conventional customer support systems have faced challenges in responding to customer inquiries quickly and accurately. Analyzing inquiries and providing appropriate responses takes a significant amount of time and effort, often resulting in lower customer satisfaction and increased workloads for support staff. Furthermore, the process for customer support staff to find and customize appropriate responses is complex and inefficient.

[0094] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0095] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for notifying a customer support representative of the selected or generated answer and displaying it on a dashboard, means for the customer support representative to customize and confirm the provided answer, and means for sending the final answer to the customer. This significantly improves the speed and accuracy of inquiry processing and makes it possible to increase customer satisfaction.

[0096] "Customer" refers to a person who uses a service or product or makes an inquiry about such a service or product.

[0097] "Enquiry" means a question or request submitted by a Customer seeking information or resolving a question about a product or service.

[0098] A "generative AI model" refers to an artificial intelligence algorithm or system that uses natural language processing to analyze a query and generate an appropriate response.

[0099] An "FAQ database" refers to a database that stores frequently asked questions and their answers, enabling quick responses to customer inquiries.

[0100] A "knowledge base" is a database containing detailed information about a particular field, and is used in expert systems and support systems.

[0101] "Customer Support Representative" means an individual whose job is to receive and provide responses to customer inquiries.

[0102] A "dashboard" is an interface used by customer support staff and is a tool that centrally manages and displays inquiries and responses.

[0103] "Notification system" refers to a mechanism that notifies customer support representatives that a generated response has been received.

[0104] "Urgency" refers to a criterion for assessing the importance of the inquiry and the degree to which a prompt response is required.

[0105] The system of the present invention realizes a fast and accurate response to customer inquiries. The system includes the following main components:

[0106] Inquiry Receiving Module

[0107] The server uses a web form or chatbot as an interface to receive customer inquiries. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a MySQL database.

[0108] Content Analysis Module

[0109] The server passes the received query to a generative AI model (e.g., OpenAI's GPT-3), which performs the following analysis:

[0110] Language detection: Automatically identify the language used from the query text.

[0111] Keyword extraction: Identify and extract important words and phrases.

[0112] Topic classification: Categorizing inquiries into specific topics or categories.

[0113] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0114] Answer selection / generation module

[0115] The server queries a FAQ database or knowledge base (e.g., Elasticsearch) based on the analysis results to find the appropriate answer. If the search results are insufficient, a generative AI model generates a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0116] Customer Support Delivery Module

[0117] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0118] Customization and Review Module

[0119] The customer support representative can review the response displayed on their device and customize it as needed, for example, to add more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and stored.

[0120] Module for sending answers to customers

[0121] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0122] Specific examples

[0123] For example, consider the case where a user sends an inquiry saying, "Please tell me about returning a product."

[0124] 1. The server receives the query and stores it in a database.

[0125] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0126] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0127] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0128] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0129] 6. The server sends the final customized answer to the user.

[0130] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1: Receiving an inquiry

[0133] server

[0134] Input: A user enters their inquiry using a web form or chatbot and clicks submit.

[0135] Processing: The server receives the HTTP POST request.

[0136] Data processing: Analyze the received inquiry content and convert it into an appropriate format (e.g., JSON format).

[0137] Output: Save the transformed query data into a MySQL database.

[0138] Specific behavior: The user enters and submits "Please tell me about returning the product." The server receives this request and stores it in the database.

[0139] Step 2: Content analysis

[0140] server

[0141] Input: Query data stored in the database.

[0142] Processing: Send the data to a generative AI model (e.g., GPT-3) and ask it to analyze:

[0143] Language determination: Identifying the language used from the query text.

[0144] Keyword extraction: Extract important words and phrases.

[0145] Topic classification: Categorizing inquiries into specific topics or categories.

[0146] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0147] Data calculation: The AI ​​model analyzes the query text and extracts relevant information.

[0148] Output: Analysis results (language, keywords, topics, urgency).

[0149] Specific operation: The server sends the text "Please tell me about returning the product" to the AI ​​model, and the model determines that it is in Japanese, contains the keyword "return," and has low urgency.

[0150] Step 3: Answer selection / generation

[0151] server

[0152] Input: Analysis results (language, keywords, topic, urgency).

[0153] Processing: Search for the right answer in a FAQ database or knowledge base (e.g., Elasticsearch).

[0154] Data processing: Querying an FAQ database or knowledge base to retrieve relevant answers.

[0155] Data computation: Generative AI models generate new answers (when search results are insufficient).

[0156] Output: The searched or generated answer.

[0157] Specific operation: The server searches for FAQs related to "returns," but no relevant answer is found, so the generative AI model generates the answer, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0158] Step 4: Providing customer support

[0159] server

[0160] Input: The searched or generated answer.

[0161] Action: Send the response to the customer support representative's device.

[0162] Data processing: Converting response information into a format that can be passed to the notification system and dashboard.

[0163] Output: Notification to customer support representative and response displayed on dashboard.

[0164] Specific operation: The server sends the answer to the customer support representative's device and displays it on the dashboard.

[0165] Step 5: Customize and verify

[0166] Customer Support Representative

[0167] Input: The answer displayed on the dashboard.

[0168] Action: Review the answers and customize them as needed.

[0169] Data processing: Converting data into a format with additional information or corrections.

[0170] Output: A customized final answer.

[0171] Specific actions: The rep adds additional information, such as "The return period is within 30 days of purchase." The customized response is then resubmitted to the server and saved.

[0172] Step 6: Send your response to the customer

[0173] server

[0174] Input: Your customized final answer.

[0175] Processing: Send a response via the method specified by the customer (email, chat, etc.).

[0176] Data processing: Converting customer contact information into a compatible format.

[0177] Output: Sending the final response to the customer.

[0178] Specific operation: The server sends a customized response to the user using the email sending API. The user receives an email with the following response: "Please refer to the link below for the product return procedure. Returns are accepted within 30 days of purchase, and the customer is responsible for the return shipping costs."

[0179] (Application example 1)

[0180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] When responding to customer inquiries, manual response takes time and effort, making it difficult to provide accurate and prompt answers. Furthermore, particularly for online shopping sites, prompt and accurate customer support is required to increase customer satisfaction. Therefore, a system that automatically analyzes the content of inquiries and generates and provides appropriate answers is required.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0183] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for providing the selected or generated answer to a customer support representative, means for the customer support representative to customize and confirm the provided answer, means for sending the final answer to the customer, and means for enhancing customer support functions using a smartphone application to improve the speed and accuracy of inquiry processing, thereby enabling quick and accurate responses to customer inquiries and increasing customer satisfaction.

[0184] The "inquiry receiving means" is a means for receiving inquiries from customers, and transmits the contents of the inquiries to the server through an interface such as a web form or chatbot.

[0185] A "generative AI model" is a model that uses artificial intelligence to analyze and generate natural language, automatically generating appropriate answers based on the content of the inquiry.

[0186] The "analysis means" is a means for analyzing the content of the received inquiry, and performs language identification, keyword extraction, topic classification, and urgency assessment.

[0187] "Answer generation means" refers to a means for selecting an appropriate answer from an FAQ database or knowledge base based on the results obtained by the analysis means, or for generating a new answer using a generative AI model.

[0188] "Answer Providing Means" means a means for providing a selected or generated answer to a customer support representative, and for displaying the answer in real time using a notification system or dashboard.

[0189] "Customization and Verification Means" means a means by which a customer support representative can review the answers provided and add or modify information as needed.

[0190] "Response sending means" refers to the means for sending the final response to the customer, and may be via email, chat, in-app notifications, etc.

[0191] "Smartphone Application" means a software application that operates on a smartphone and is used to receive customer inquiries and generate and provide prompt and accurate responses.

[0192] The present invention is a system for quickly and accurately processing customer inquiries, which uses a server, customer terminals, customer support terminals, and software applications that run on these terminals.

[0193] The server first receives an inquiry from a customer. The customer uses a smartphone application to send the inquiry to the server via a chatbot or inquiry form. The received inquiry is then stored in a database.

[0194] The generative AI model running on the server analyzes the received inquiry. This analysis includes language identification, keyword extraction, topic classification of the inquiry, and urgency assessment. Based on the analysis results, the server searches an FAQ database or knowledge base to select an appropriate answer. If a suitable answer is not found, the generative AI model generates a new answer.

[0195] The generated answer is sent to the customer support representative's device and displayed on their dashboard. The customer support representative reviews the answer and customizes it with additional information as needed. The final customized answer is stored on the server again and sent to the customer. The customer receives the answer through their specified communication channel (email, chat, in-app notification, etc.).

[0196] The system is implemented using the following hardware and software:

[0197] Hardware: Servers (cloud-based or physical), customer smartphones, customer support representative computers

[0198] Software: A web server using the Flask framework, a SQLite or PostgreSQL database, an OpenAI generative model (e.g., GPT-3), and a smartphone application.

[0199] As a concrete example, consider the case where a user sends an inquiry such as "Please tell me the delivery status of my item." The server receives the inquiry and stores it in a database. The generative AI model determines that the inquiry is in Japanese, extracts the keywords "order" and "delivery status," and classifies it as a topic called "delivery." The urgency is assessed as medium. The server searches FAQs related to "delivery," and if no relevant answer is found, the generative AI model generates a new answer. For example, it might say, "You can check the delivery status of your order by clicking this link: <link>."

[0200] An example of a prompt to input to the generative AI model is:

[0201] User's question: "What is the delivery status of my order?"

[0202] Language detection: Japanese

[0203] Keyword extraction: ["order", "shipping status"]

[0204] Topic Category: "Shipping"

[0205] Urgency rating: Medium

[0206] → Generate an answer.

[0207] The system of the present invention enables quick and accurate responses to customer inquiries, thereby increasing customer satisfaction.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] A user inputs and sends an inquiry via a smartphone application. The inquiry is sent from the application to the server as an HTTP POST request, and the server receives it. The input contains the user's inquiry, and the output is the inquiry that is stored in the inquiry database on the server. Specifically, the user inputs "Please tell me the delivery status of my item" and presses the send button.

[0211] Step 2:

[0212] The server passes the received inquiry content to the generative AI model for analysis. The analysis includes language identification, keyword extraction, topic classification of the inquiry content, and urgency assessment. The input is the received inquiry content, and the output is the results of language, keywords, topic classification, and urgency assessment. Specific operations include generating results such as "Japanese," "Order," "Delivery status," "Delivery," and "Medium urgency."

[0213] Step 3:

[0214] Based on the results of the analysis by the generative AI model, the server searches the FAQ database or knowledge base to select an appropriate answer. If a corresponding answer is not found, the generative AI model generates a new answer. The input is the analysis result, and the output is the selected answer or a new generated answer. Specifically, the searched FAQ selects the answer "You can check the delivery status of your order by clicking this link: <link>".

[0215] Step 4:

[0216] The server notifies the customer support representative's terminal of the selected or generated answer and displays it on the dashboard. The input is the selected or generated answer, and the output is the displayed answer. The specific operation is that the customer support representative's dashboard displays "You can check the delivery status of your order by clicking this link: <link>".

[0217] Step 5:

[0218] The customer support representative reviews the displayed answer and adds or modifies information as needed. The input is the provided answer, and the output is the customized final answer. The specific action is to modify the dashboard to read, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[0219] Step 6:

[0220] The server sends a final response to the customer via the communication channel specified by the user (email, chat, in-app notification, etc.). The input is the customized final response, and the output is the response sent to the customer. The specific behavior is that an email is sent to the customer's email address stating, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] The system of the present invention includes the following main components to enable quick and accurate responses to customer inquiries. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions based on the content of the inquiry and provide a more appropriate response.

[0223] Inquiry Receiving Module

[0224] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0225] Content Analysis Module

[0226] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[0227] Language detection: Automatically identify the language used from the query text.

[0228] Keyword extraction: Identify and extract important words and phrases.

[0229] Topic classification: Categorizing inquiries into specific topics or categories.

[0230] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0231] Emotion Recognition: Analyze and evaluate the user's emotions from the query text. Emotion types include joy, anger, sadness, surprise, etc.

[0232] Answer selection / generation module

[0233] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it automatically generates a new answer using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0234] Customer Support Delivery Module

[0235] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[0236] Customization and Review Module

[0237] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[0238] Module for sending answers to customers

[0239] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0240] Specific examples

[0241] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0242] 1. The server receives the query and stores it in a database.

[0243] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0244] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0245] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0246] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0247] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[0248] 7. The server sends the final customized answer to the user.

[0249] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, and can further increase customer satisfaction by taking user emotions into consideration when responding.

[0250] The processing flow will be explained below.

[0251] Step 1:

[0252] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[0253] Step 2:

[0254] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[0255] Step 3:

[0256] The server adds the query to a queue and passes it as input to the generative AI model.

[0257] Step 4:

[0258] The generative AI model running on the server performs the following analysis:

[0259] Language detection: Identifying the language used from text.

[0260] Keyword extraction: Extracting important words and phrases from text.

[0261] Topical classification: Classifying content into specific categories or topics.

[0262] Urgency assessment: Assess urgency based on wording and content.

[0263] Step 5:

[0264] The emotion engine running on the server analyzes and evaluates the user's emotions from the query text, including joy, anger, sadness, surprise, etc.

[0265] Step 6:

[0266] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[0267] Step 7:

[0268] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[0269] Step 8:

[0270] The server sends the generated answer and emotion information to the customer support agent's device, notifies the agent using a notification system, and displays the answer and user emotion on a dashboard.

[0271] Step 9:

[0272] The customer support representative reviews the provided response on their device and customizes it as needed, for example, adding "more information about the return process" or "urgent action required."

[0273] Step 10:

[0274] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[0275] Step 11:

[0276] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[0277] Step 12:

[0278] The user receives the response and reviews the information that will help them solve the problem.

[0279] Specific examples

[0280] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0281] 1. The server receives the query and stores it in a database.

[0282] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0283] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0284] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0285] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0286] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble, and we'll get back to you as soon as possible. Returns are accepted within 30 days of purchase."

[0287] 7. The server sends the final customized answer to the user.

[0288] Example 2

[0289] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0290] Responding quickly and accurately to customer inquiries is important for improving customer satisfaction. However, mechanical responses that ignore customer emotions can make it difficult to resolve customer dissatisfaction and may result in delayed appropriate responses. To improve this situation, it is necessary not only to analyze the content of inquiries, but also to recognize and respond to customer emotions.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0292] In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; means including an emotion engine for recognizing the customer's emotion from the content of the inquiry; and means for providing the emotion information recognized by the emotion engine to the customer support representative. This makes it possible to recognize the customer's emotion while analyzing the content of the inquiry, and to provide an optimal response based on that.

[0293] "Means for receiving inquiries from customers" refers to the interface and protocol for sending the inquiry content entered by customers through a web form or chatbot to a server and receiving it.

[0294] "Means of analysis using a generative AI model" refers to the process of using machine learning and natural language processing techniques to analyze the text data of received inquiries and automatically determine the language, keywords, topics, etc.

[0295] "Means for selecting or generating from an FAQ database or knowledge base" refers to a process for searching an existing FAQ database or knowledge base based on the results of the analysis and selecting appropriate answers or generating new answers as needed.

[0296] "Means provided to customer support representative" refers to a system for transmitting the selected or generated answer to the representative's device and making it visible through notifications and dashboards.

[0297] "Means for customization and review" means the interface and functionality that allows a customer support representative to review the responses provided and make corrections or add additional information as needed.

[0298] "Means for sending the final response to the customer" refers to the mechanism by which the final response that the agent has confirmed and customized is sent to the customer via a communication channel such as an email address or chat system specified by the customer.

[0299] "Means including an emotion engine" refers to software and algorithms for analyzing customer emotions from received inquiries using natural language processing and providing the results in a format that can be used by the system.

[0300] The present invention is a system for responding to customer inquiries quickly and accurately, and includes the following main components: In particular, it incorporates an emotion engine that recognizes customer emotions based on the content of the inquiry, enabling more appropriate responses.

[0301] Inquiry Receiving Module

[0302] The server provides a web form or chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0303] Content Analysis Module

[0304] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[0305] Language detection: Automatically identify the language used from the query text.

[0306] Keyword extraction: Identify and extract important words and phrases.

[0307] Topic classification: Categorizing inquiries into specific topics or categories.

[0308] Urgency assessment: Assess the urgency based on the tone and content of the inquiry.

[0309] Emotion Recognition: Analyze and evaluate the user's emotions from the query text.

[0310] Answer selection / generation module

[0311] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This process uses a multi-layer neural network to provide accurate grammar and appropriate response content.

[0312] Customer Support Delivery Module

[0313] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. In addition, emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[0314] Customization and Review Module

[0315] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return procedure." Once the representative has customized the response, it is sent back to the server and saved.

[0316] Module for sending answers to customers

[0317] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0318] Examples of concrete examples and prompts

[0319] For example, a case will be described in which a user sends an inquiry saying, "Please tell me how to return a product. I would like you to deal with this as soon as possible. I am in a really difficult situation."

[0320] Specific examples

[0321] 1. The server receives the query and stores it in a database.

[0322] 2. The generative AI model running on the server determines that the inquiry is in Japanese and extracts the keyword "return." The urgency is assessed as high.

[0323] 3. The emotion engine determines the user's emotion as "sadness" based on the expression "troubled."

[0324] 4. The server searches the database for FAQs related to "returns." If no relevant FAQ is found, the generative AI model generates an answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0325] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0326] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble and will get back to you as soon as possible."

[0327] 7. The server sends the final customized answer to the user.

[0328] Prompt Sentence Examples

[0329] User query:

[0330] "Please tell me how to return the product. I would like this to be resolved quickly. I am in a very difficult situation."

[0331] Prompt for generative AI model:

[0332] "Generate an appropriate response to the following inquiry: 'Please tell me how to return an item. I'm really struggling and would appreciate a speedy response.' In your response, please include information about the process for returning an item."

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1: Receiving an inquiry

[0335] The server receives inquiries submitted by customers through web forms or chatbots as HTTP POST requests.

[0336] Input: Inquiry data sent by the customer (e.g., question about returning a product)

[0337] Data processing / calculation: Converting received data into a structured format (such as JSON or XML)

[0338] Output: A structured representation of the form data

[0339] Step 2: Save the received data

[0340] The server stores the structured query data in a database, and validates the format and content of the received data to ensure there are no errors.

[0341] Input: Structured inquiry data

[0342] Data processing / calculation: Insertion into database

[0343] Output: Query record stored in the database

[0344] Step 3: Language detection

[0345] The server sends the text data of the received query to a generative AI model, which automatically identifies the language used.

[0346] Input: Text data of the query

[0347] Data processing / computation: Language recognition using generative AI models

[0348] Output: Language (e.g. Japanese)

[0349] Step 4: Keyword extraction

[0350] After language determination is complete, the server runs the text data through a natural language processing algorithm to extract important keywords and phrases.

[0351] Input: Language-determined text data

[0352] Data processing / calculation: Applying keyword extraction algorithms

[0353] Output: Extracted keywords (e.g. "returns")

[0354] Step 5: Create a topic classification

[0355] The server categorizes the query into specific topics and categories based on the extracted keywords.

[0356] Input: Extracted keywords

[0357] Data processing / computation: Topic classification using generative AI models

[0358] Output: Categorized topics (e.g., "Return Procedure")

[0359] Step 6: Conduct an emergency assessment

[0360] The server analyzes the text and tone of the inquiry and assesses its urgency.

[0361] Input: relevant text data and key expressions

[0362] Data processing / computation: Using generative AI models and other algorithms to assess urgency

[0363] Output: Urgency rating (e.g., high urgency)

[0364] Step 7: Emotion Recognition

[0365] The server uses an emotion engine to recognize and evaluate customer emotions.

[0366] Input: Text data of the query

[0367] Data processing / calculation: Emotion analysis using emotion engine

[0368] Output: Recognized emotion (e.g. "sadness")

[0369] Step 8: Query the FAQ database

[0370] Based on the analysis results, the server searches for relevant answers from an FAQ database or knowledge base.

[0371] Input: Keywords and topic classification results

[0372] Data processing / calculation: Database query

[0373] Output: The searched answer (e.g., "Here's how to return the item...")

[0374] Step 9: Generate new answers as needed

[0375] If the server cannot find a suitable answer from the FAQ, it uses a generative AI model to generate a new answer.

[0376] Input: Re-enter data when query results are insufficient

[0377] Data processing / calculation: Answer generation using generative AI models

[0378] Output: The generated answer (e.g., "Please see the link below for return instructions...")

[0379] Step 10: Send your answers and sentiment information

[0380] The server then sends the generated answers and sentiment information to the customer support agent's device, where they are displayed on a dashboard and an alert is sent to the agent via a notification system.

[0381] Input: Generated answers and sentiment information

[0382] Data processing / calculation: Notifications and dashboard display

[0383] Output: Answers and emotion information displayed on the device

[0384] Step 11: Customer support representative customizes response

[0385] A customer support representative will review the response provided and make corrections or add additional information as necessary.

[0386] Input: Answers displayed on the dashboard

[0387] Data manipulation / calculation: customizing and modifying answers

[0388] Output: Customized answer

[0389] Step 12: Send the final response to the customer

[0390] The server then sends the final customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0391] Input: Customized Answer

[0392] Data processing / calculation: Sending answers

[0393] Output: Final response sent to customer

[0394] (Application example 2)

[0395] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0396] While there is an increasing demand for quick and accurate responses to customer inquiries, conventional systems have had the problem of taking time to analyze the content of inquiries and selecting appropriate responses, making it difficult to provide satisfactory customer service. Furthermore, they were unable to respond in a way that took into account the customer's emotions, which could result in a decline in customer satisfaction. It is known that delays in response have a significant negative impact on the customer experience, especially for urgent or emotional inquiries.

[0397] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; and means for responding based on the user's emotions by combining an emotion engine that recognizes the user's emotions based on the content of the inquiry. This eliminates the conventional issues of delays in responding to inquiries and the difficulty of responding while taking customer emotions into consideration, making it possible to improve customer satisfaction.

[0398] "Customer inquiries" refer to questions, requests, and opinions that customers make to a company or store in relation to the purchase of a product or the use of a service.

[0399] "Means for receiving" refers to the interface or process for inputting customer inquiry information into the server.

[0400] A "generative AI model" is an algorithm or software that learns from large amounts of data, uses natural language processing to understand inquiries and sentences, and automatically generates and analyzes them.

[0401] "Means of analysis" refers to the process of analyzing the content of the received inquiry and determining the language of the information, extracting keywords, classifying topics, assessing urgency, recognizing emotions, etc.

[0402] An "FAQ database" is a database that organizes and stores frequently asked questions and their answers collected in the past.

[0403] A "knowledge base" is a collection of information that aggregates and organizes knowledge about a particular topic or field and stores it in a searchable and usable format.

[0404] A "customer support representative" is a specialized staff member or operator who responds appropriately to customer inquiries.

[0405] "Means for providing" refers to a method or system for displaying or notifying a selected or generated answer to a customer support representative.

[0406] "Means for customization and verification" means the processes and tools that allow a customer support representative to modify or add to the provided response as needed and verify its content.

[0407] "Final Response" means the final response sent to Customer after customization and review.

[0408] An "emotion engine" is an algorithm or software that automatically analyzes user emotions from text data and outputs the results as numbers or tags.

[0409] "User emotion" refers to a psychological state such as joy, sadness, anger, or surprise that can be inferred from words and expressions contained in the query text.

[0410] "Response based on user emotions" refers to the process or means of responding to customers in an appropriate manner, taking into account the emotions recognized by the emotion engine.

[0411] The present invention is a system for responding quickly and accurately to customer inquiries, and includes the following main components: The roles of the server, terminal, and user, and the specific processes are as follows:

[0412] System Program

[0413] The server provides an interface for receiving customer inquiries, either through a web form or a chatbot. When a customer enters and submits an inquiry, it is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0414] The server then passes the received query content to a generative AI model for language determination, keyword extraction, topic classification, urgency assessment, and sentiment recognition. This process uses natural language processing (NLP) techniques, such as generative AI models like GPT-3 and BERT, or sentiment engines like Google Cloud Natural Language API and IBM Watson Tone Analyzer.

[0415] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0416] The server then sends the selected or generated answer to the customer support agent's device in real time. The agent is notified via a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the agent, allowing them to respond based on the user's emotions.

[0417] The customer support representative can review the response displayed on their device and customize it as needed. For example, they can add "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[0418] Finally, the server sends a confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0419] Specific examples

[0420] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0421] 1. The server receives the query and stores it in a database.

[0422] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0423] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0424] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0425] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0426] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[0427] 7. The server sends the final customized answer to the user.

[0428] Prompt Sentence Examples

[0429] "A user has submitted an inquiry saying, 'Please tell me how to return an item. I really need help, I want this resolved quickly.' Please generate an example response to this."

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The server receives inquiries from customers. Specifically, when a customer enters and submits an inquiry through a web form or chatbot, the content is sent to the server as an HTTP POST request. The server that receives this request stores the inquiry data in a database.

[0433] Input: Your query as an HTTP POST request.

[0434] Output: Query data stored in a database.

[0435] Step 2:

[0436] The server passes the received query content to a generative AI model and performs content analysis. This involves language determination, keyword extraction, topic classification, urgency assessment, and emotion recognition. Specifically, the server analyzes the text data using a generative AI model (e.g., GPT-3 or BERT) and an emotion engine (e.g., Google Cloud Natural Language API, IBM Watson Tone Analyzer).

[0437] Input: Query data stored in the database.

[0438] Output: Language, keyword, topic, urgency, and sentiment analysis results.

[0439] Step 3:

[0440] The server queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the corresponding answer cannot be found in the database, a new answer is automatically generated using a generative AI model. The model generates an appropriate answer based on the large amount of data learned during training.

[0441] Input: Analysis results (language, keywords, topic, urgency, sentiment).

[0442] Output: Search results from the FAQ database or generated answers.

[0443] Step 4:

[0444] The server sends the selected or generated answer and sentiment information to the customer support agent's device in real time, notifying the agent via a notification system (e.g., Firebase Cloud Messaging), and displaying the answer on a dashboard.

[0445] Input: Search results or generated answers, sentiment information.

[0446] Output: Answers and sentiment information displayed on the customer support representative's device.

[0447] Step 5:

[0448] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding appropriate details or supplementary explanations. Once the representative has customized the response, it is sent back to the server and stored.

[0449] Input: Answers and sentiment information displayed on the dashboard.

[0450] Output: A customized final answer.

[0451] Step 6:

[0452] The server sends a final, customized response to the customer, using email, chat, or other communication channel specified by the customer.

[0453] Input: Your customized final answer.

[0454] Output: The final response sent to the customer.

[0455] In this way, the system automates and streamlines the process of receiving an inquiry, analyzing it, providing an appropriate response, and then having the agent customize and send the final response to the customer.

[0456] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0458] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0462] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0463] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0464] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0465] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0466] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0467] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0468] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0469] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0470] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0471] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0472] The system of the present invention includes the following major components for quickly and accurately processing customer inquiries:

[0473] Inquiry Receiving Module

[0474] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0475] Content Analysis Module

[0476] The server passes the received query content to the generative AI model and performs the following analysis:

[0477] Language detection: Automatically identify the language used from the query text.

[0478] Keyword extraction: Identify and extract important words and phrases.

[0479] Topic classification: Categorizing inquiries into specific topics or categories.

[0480] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0481] Answer selection / generation module

[0482] The server then queries the FAQ database or knowledge base based on the analysis results to find the appropriate answer. If the search results are insufficient, a new answer is automatically generated using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0483] Customer Support Delivery Module

[0484] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0485] Customization and Review Module

[0486] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and saved.

[0487] Module for sending answers to customers

[0488] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0489] Specific examples

[0490] For example, a user may send an inquiry saying, "Please tell me about returning a product."

[0491] 1. The server receives the query and stores it in a database.

[0492] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0493] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0494] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0495] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0496] 6. The server sends the final customized answer to the user.

[0497] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0498] The processing flow will be explained below.

[0499] Step 1:

[0500] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[0501] Step 2:

[0502] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[0503] Step 3:

[0504] The server adds the query to a queue and passes it as input to the generative AI model.

[0505] Step 4:

[0506] The generative AI model running on the server performs the following analysis:

[0507] Language detection: Identifying the language used from text.

[0508] Keyword extraction: Extracting important words and phrases from text.

[0509] Topical classification: Classifying content into specific categories or topics.

[0510] Urgency assessment: Assess urgency based on wording and content.

[0511] Step 5:

[0512] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[0513] Step 6:

[0514] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[0515] Step 7:

[0516] The server sends the searched and generated answer to the customer support agent's device, notifies the agent using the notification system, and displays the answer on the dashboard.

[0517] Step 8:

[0518] The customer support representative can review the response on their device and customize it as needed, for example by adding "more information about the return process."

[0519] Step 9:

[0520] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[0521] Step 10:

[0522] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[0523] Step 11:

[0524] The user receives the response and reviews the information that will help them solve the problem.

[0525] Example 1

[0526] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0527] Conventional customer support systems have faced challenges in responding to customer inquiries quickly and accurately. Analyzing inquiries and providing appropriate responses takes a significant amount of time and effort, often resulting in lower customer satisfaction and increased workloads for support staff. Furthermore, the process for customer support staff to find and customize appropriate responses is complex and inefficient.

[0528] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0529] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for notifying a customer support representative of the selected or generated answer and displaying it on a dashboard, means for the customer support representative to customize and confirm the provided answer, and means for sending the final answer to the customer. This significantly improves the speed and accuracy of inquiry processing and makes it possible to increase customer satisfaction.

[0530] "Customer" refers to a person who uses a service or product or makes an inquiry about such a service or product.

[0531] "Enquiry" means a question or request submitted by a Customer seeking information or resolving a question about a product or service.

[0532] A "generative AI model" refers to an artificial intelligence algorithm or system that uses natural language processing to analyze a query and generate an appropriate response.

[0533] An "FAQ database" refers to a database that stores frequently asked questions and their answers, enabling quick responses to customer inquiries.

[0534] A "knowledge base" is a database containing detailed information about a particular field, and is used in expert systems and support systems.

[0535] "Customer Support Representative" means an individual whose job is to receive and provide responses to customer inquiries.

[0536] A "dashboard" is an interface used by customer support staff and is a tool that centrally manages and displays inquiries and responses.

[0537] "Notification system" refers to a mechanism that notifies customer support representatives that a generated response has been received.

[0538] "Urgency" refers to a criterion for assessing the importance of the inquiry and the degree to which a prompt response is required.

[0539] The system of the present invention realizes a fast and accurate response to customer inquiries. The system includes the following main components:

[0540] Inquiry Receiving Module

[0541] The server uses a web form or chatbot as an interface to receive customer inquiries. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a MySQL database.

[0542] Content Analysis Module

[0543] The server passes the received query to a generative AI model (e.g., OpenAI's GPT-3), which performs the following analysis:

[0544] Language detection: Automatically identify the language used from the query text.

[0545] Keyword extraction: Identify and extract important words and phrases.

[0546] Topic classification: Categorizing inquiries into specific topics or categories.

[0547] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0548] Answer selection / generation module

[0549] The server queries a FAQ database or knowledge base (e.g., Elasticsearch) based on the analysis results to find the appropriate answer. If the search results are insufficient, a generative AI model generates a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0550] Customer Support Delivery Module

[0551] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0552] Customization and Review Module

[0553] The customer support representative can review the response displayed on their device and customize it as needed, for example, to add more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and stored.

[0554] Module for sending answers to customers

[0555] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0556] Specific examples

[0557] For example, consider the case where a user sends an inquiry saying, "Please tell me about returning a product."

[0558] 1. The server receives the query and stores it in a database.

[0559] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0560] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0561] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0562] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0563] 6. The server sends the final customized answer to the user.

[0564] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0566] Step 1: Receiving an inquiry

[0567] server

[0568] Input: A user enters their inquiry using a web form or chatbot and clicks submit.

[0569] Processing: The server receives the HTTP POST request.

[0570] Data processing: Analyze the received inquiry content and convert it into an appropriate format (e.g., JSON format).

[0571] Output: Save the transformed query data into a MySQL database.

[0572] Specific behavior: The user enters and submits "Please tell me about returning the product." The server receives this request and stores it in the database.

[0573] Step 2: Content analysis

[0574] server

[0575] Input: Query data stored in the database.

[0576] Processing: Send the data to a generative AI model (e.g., GPT-3) and ask it to analyze:

[0577] Language determination: Identifying the language used from the query text.

[0578] Keyword extraction: Extract important words and phrases.

[0579] Topic classification: Categorizing inquiries into specific topics or categories.

[0580] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0581] Data calculation: The AI ​​model analyzes the query text and extracts relevant information.

[0582] Output: Analysis results (language, keywords, topics, urgency).

[0583] Specific operation: The server sends the text "Please tell me about returning the product" to the AI ​​model, and the model determines that it is in Japanese, contains the keyword "return," and has low urgency.

[0584] Step 3: Answer selection / generation

[0585] server

[0586] Input: Analysis results (language, keywords, topic, urgency).

[0587] Processing: Search for the right answer in a FAQ database or knowledge base (e.g., Elasticsearch).

[0588] Data processing: Querying an FAQ database or knowledge base to retrieve relevant answers.

[0589] Data computation: Generative AI models generate new answers (when search results are insufficient).

[0590] Output: The searched or generated answer.

[0591] Specific operation: The server searches for FAQs related to "returns," but no relevant answer is found, so the generative AI model generates the answer, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0592] Step 4: Providing customer support

[0593] server

[0594] Input: The searched or generated answer.

[0595] Action: Send the response to the customer support representative's device.

[0596] Data processing: Converting response information into a format that can be passed to the notification system and dashboard.

[0597] Output: Notification to customer support representative and response displayed on dashboard.

[0598] Specific operation: The server sends the answer to the customer support representative's device and displays it on the dashboard.

[0599] Step 5: Customize and verify

[0600] Customer Support Representative

[0601] Input: The answer displayed on the dashboard.

[0602] Action: Review the answers and customize them as needed.

[0603] Data processing: Converting data into a format with additional information or corrections.

[0604] Output: A customized final answer.

[0605] Specific actions: The rep adds additional information, such as "The return period is within 30 days of purchase." The customized response is then resubmitted to the server and saved.

[0606] Step 6: Send your response to the customer

[0607] server

[0608] Input: Your customized final answer.

[0609] Processing: Send a response via the method specified by the customer (email, chat, etc.).

[0610] Data processing: Converting customer contact information into a compatible format.

[0611] Output: Sending the final response to the customer.

[0612] Specific operation: The server sends a customized response to the user using the email sending API. The user receives an email with the following response: "Please refer to the link below for the product return procedure. Returns are accepted within 30 days of purchase, and the customer is responsible for the return shipping costs."

[0613] (Application example 1)

[0614] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0615] When responding to customer inquiries, manual response takes time and effort, making it difficult to provide accurate and prompt answers. Furthermore, particularly for online shopping sites, prompt and accurate customer support is required to increase customer satisfaction. Therefore, a system that automatically analyzes the content of inquiries and generates and provides appropriate answers is required.

[0616] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0617] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for providing the selected or generated answer to a customer support representative, means for the customer support representative to customize and confirm the provided answer, means for sending the final answer to the customer, and means for enhancing customer support functions using a smartphone application to improve the speed and accuracy of inquiry processing, thereby enabling quick and accurate responses to customer inquiries and increasing customer satisfaction.

[0618] The "inquiry receiving means" is a means for receiving inquiries from customers, and transmits the contents of the inquiries to the server through an interface such as a web form or chatbot.

[0619] A "generative AI model" is a model that uses artificial intelligence to analyze and generate natural language, automatically generating appropriate answers based on the content of the inquiry.

[0620] The "analysis means" is a means for analyzing the content of the received inquiry, and performs language identification, keyword extraction, topic classification, and urgency assessment.

[0621] "Answer generation means" refers to a means for selecting an appropriate answer from an FAQ database or knowledge base based on the results obtained by the analysis means, or for generating a new answer using a generative AI model.

[0622] "Answer Providing Means" means a means for providing a selected or generated answer to a customer support representative, and for displaying the answer in real time using a notification system or dashboard.

[0623] "Customization and Verification Means" means a means by which a customer support representative can review the answers provided and add or modify information as needed.

[0624] "Response sending means" refers to the means for sending the final response to the customer, and may be via email, chat, in-app notifications, etc.

[0625] "Smartphone Application" means a software application that operates on a smartphone and is used to receive customer inquiries and generate and provide prompt and accurate responses.

[0626] The present invention is a system for quickly and accurately processing customer inquiries, which uses a server, customer terminals, customer support terminals, and software applications that run on these terminals.

[0627] The server first receives an inquiry from a customer. The customer uses a smartphone application to send the inquiry to the server via a chatbot or inquiry form. The received inquiry is then stored in a database.

[0628] The generative AI model running on the server analyzes the received inquiry. This analysis includes language identification, keyword extraction, topic classification of the inquiry, and urgency assessment. Based on the analysis results, the server searches an FAQ database or knowledge base to select an appropriate answer. If a suitable answer is not found, the generative AI model generates a new answer.

[0629] The generated answer is sent to the customer support representative's device and displayed on their dashboard. The customer support representative reviews the answer and customizes it with additional information as needed. The final customized answer is stored on the server again and sent to the customer. The customer receives the answer through their specified communication channel (email, chat, in-app notification, etc.).

[0630] The system is implemented using the following hardware and software:

[0631] Hardware: Servers (cloud-based or physical), customer smartphones, customer support representative computers

[0632] Software: A web server using the Flask framework, a SQLite or PostgreSQL database, an OpenAI generative model (e.g., GPT-3), and a smartphone application.

[0633] As a concrete example, consider the case where a user sends an inquiry such as "Please tell me the delivery status of my item." The server receives the inquiry and stores it in a database. The generative AI model determines that the inquiry is in Japanese, extracts the keywords "order" and "delivery status," and classifies it as a topic called "delivery." The urgency is assessed as medium. The server searches FAQs related to "delivery," and if no relevant answer is found, the generative AI model generates a new answer. For example, it might say, "You can check the delivery status of your order by clicking this link: <link>."

[0634] An example of a prompt to input to the generative AI model is:

[0635] User's question: "What is the delivery status of my order?"

[0636] Language detection: Japanese

[0637] Keyword extraction: ["order", "shipping status"]

[0638] Topic Category: "Shipping"

[0639] Urgency rating: Medium

[0640] → Generate an answer.

[0641] The system of the present invention enables quick and accurate responses to customer inquiries, thereby increasing customer satisfaction.

[0642] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0643] Step 1:

[0644] A user inputs and sends an inquiry via a smartphone application. The inquiry is sent from the application to the server as an HTTP POST request, and the server receives it. The input contains the user's inquiry, and the output is the inquiry that is stored in the inquiry database on the server. Specifically, the user inputs "Please tell me the delivery status of my item" and presses the send button.

[0645] Step 2:

[0646] The server passes the received inquiry content to the generative AI model for analysis. The analysis includes language identification, keyword extraction, topic classification of the inquiry content, and urgency assessment. The input is the received inquiry content, and the output is the results of language, keywords, topic classification, and urgency assessment. Specific operations include generating results such as "Japanese," "Order," "Delivery status," "Delivery," and "Medium urgency."

[0647] Step 3:

[0648] Based on the results of the analysis by the generative AI model, the server searches the FAQ database or knowledge base to select an appropriate answer. If a corresponding answer is not found, the generative AI model generates a new answer. The input is the analysis result, and the output is the selected answer or a new generated answer. Specifically, the searched FAQ selects the answer "You can check the delivery status of your order by clicking this link: <link>".

[0649] Step 4:

[0650] The server notifies the customer support representative's terminal of the selected or generated answer and displays it on the dashboard. The input is the selected or generated answer, and the output is the displayed answer. The specific operation is that the customer support representative's dashboard displays "You can check the delivery status of your order by clicking this link: <link>".

[0651] Step 5:

[0652] The customer support representative reviews the displayed answer and adds or modifies information as needed. The input is the provided answer, and the output is the customized final answer. The specific action is to modify the dashboard to read, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[0653] Step 6:

[0654] The server sends a final response to the customer via the communication channel specified by the user (email, chat, in-app notification, etc.). The input is the customized final response, and the output is the response sent to the customer. The specific behavior is that an email is sent to the customer's email address stating, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[0655] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0656] The system of the present invention includes the following main components to enable quick and accurate responses to customer inquiries. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions based on the content of the inquiry and provide a more appropriate response.

[0657] Inquiry Receiving Module

[0658] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0659] Content Analysis Module

[0660] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[0661] Language detection: Automatically identify the language used from the query text.

[0662] Keyword extraction: Identify and extract important words and phrases.

[0663] Topic classification: Categorizing inquiries into specific topics or categories.

[0664] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0665] Emotion Recognition: Analyze and evaluate the user's emotions from the query text. Emotion types include joy, anger, sadness, surprise, etc.

[0666] Answer selection / generation module

[0667] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it automatically generates a new answer using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0668] Customer Support Delivery Module

[0669] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[0670] Customization and Review Module

[0671] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[0672] Module for sending answers to customers

[0673] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0674] Specific examples

[0675] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0676] 1. The server receives the query and stores it in a database.

[0677] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0678] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0679] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0680] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0681] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[0682] 7. The server sends the final customized answer to the user.

[0683] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, and can further increase customer satisfaction by taking user emotions into consideration when responding.

[0684] The processing flow will be explained below.

[0685] Step 1:

[0686] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[0687] Step 2:

[0688] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[0689] Step 3:

[0690] The server adds the query to a queue and passes it as input to the generative AI model.

[0691] Step 4:

[0692] The generative AI model running on the server performs the following analysis:

[0693] Language detection: Identifying the language used from text.

[0694] Keyword extraction: Extracting important words and phrases from text.

[0695] Topical classification: Classifying content into specific categories or topics.

[0696] Urgency assessment: Assess urgency based on wording and content.

[0697] Step 5:

[0698] The emotion engine running on the server analyzes and evaluates the user's emotions from the query text, including joy, anger, sadness, surprise, etc.

[0699] Step 6:

[0700] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[0701] Step 7:

[0702] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[0703] Step 8:

[0704] The server sends the generated answer and emotion information to the customer support agent's device, notifies the agent using a notification system, and displays the answer and user emotion on a dashboard.

[0705] Step 9:

[0706] The customer support representative reviews the provided response on their device and customizes it as needed, for example, adding "more information about the return process" or "urgent action required."

[0707] Step 10:

[0708] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[0709] Step 11:

[0710] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[0711] Step 12:

[0712] The user receives the response and reviews the information that will help them solve the problem.

[0713] Specific examples

[0714] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0715] 1. The server receives the query and stores it in a database.

[0716] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0717] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0718] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0719] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0720] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble, and we'll get back to you as soon as possible. Returns are accepted within 30 days of purchase."

[0721] 7. The server sends the final customized answer to the user.

[0722] Example 2

[0723] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0724] Responding quickly and accurately to customer inquiries is important for improving customer satisfaction. However, mechanical responses that ignore customer emotions can make it difficult to resolve customer dissatisfaction and may result in delayed appropriate responses. To improve this situation, it is necessary not only to analyze the content of inquiries, but also to recognize and respond to customer emotions.

[0725] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0726] In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; means including an emotion engine for recognizing the customer's emotion from the content of the inquiry; and means for providing the emotion information recognized by the emotion engine to the customer support representative. This makes it possible to recognize the customer's emotion while analyzing the content of the inquiry, and to provide an optimal response based on that.

[0727] "Means for receiving inquiries from customers" refers to the interface and protocol for sending the inquiry content entered by customers through a web form or chatbot to a server and receiving it.

[0728] "Means of analysis using a generative AI model" refers to the process of using machine learning and natural language processing techniques to analyze the text data of received inquiries and automatically determine the language, keywords, topics, etc.

[0729] "Means for selecting or generating from an FAQ database or knowledge base" refers to a process for searching an existing FAQ database or knowledge base based on the results of the analysis and selecting appropriate answers or generating new answers as needed.

[0730] "Means provided to customer support representative" refers to a system for transmitting the selected or generated answer to the representative's device and making it visible through notifications and dashboards.

[0731] "Means for customization and review" means the interface and functionality that allows a customer support representative to review the responses provided and make corrections or add additional information as needed.

[0732] "Means for sending the final response to the customer" refers to the mechanism by which the final response that the agent has confirmed and customized is sent to the customer via a communication channel such as an email address or chat system specified by the customer.

[0733] "Means including an emotion engine" refers to software and algorithms for analyzing customer emotions from received inquiries using natural language processing and providing the results in a format that can be used by the system.

[0734] The present invention is a system for responding to customer inquiries quickly and accurately, and includes the following main components: In particular, it incorporates an emotion engine that recognizes customer emotions based on the content of the inquiry, enabling more appropriate responses.

[0735] Inquiry Receiving Module

[0736] The server provides a web form or chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0737] Content Analysis Module

[0738] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[0739] Language detection: Automatically identify the language used from the query text.

[0740] Keyword extraction: Identify and extract important words and phrases.

[0741] Topic classification: Categorizing inquiries into specific topics or categories.

[0742] Urgency assessment: Assess the urgency based on the tone and content of the inquiry.

[0743] Emotion Recognition: Analyze and evaluate the user's emotions from the query text.

[0744] Answer selection / generation module

[0745] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This process uses a multi-layer neural network to provide accurate grammar and appropriate response content.

[0746] Customer Support Delivery Module

[0747] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. In addition, emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[0748] Customization and Review Module

[0749] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return procedure." Once the representative has customized the response, it is sent back to the server and saved.

[0750] Module for sending answers to customers

[0751] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0752] Examples of concrete examples and prompts

[0753] For example, a case will be described in which a user sends an inquiry saying, "Please tell me how to return a product. I would like you to deal with this as soon as possible. I am in a really difficult situation."

[0754] Specific examples

[0755] 1. The server receives the query and stores it in a database.

[0756] 2. The generative AI model running on the server determines that the inquiry is in Japanese and extracts the keyword "return." The urgency is assessed as high.

[0757] 3. The emotion engine determines the user's emotion as "sadness" based on the expression "troubled."

[0758] 4. The server searches the database for FAQs related to "returns." If no relevant FAQ is found, the generative AI model generates an answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0759] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0760] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble and will get back to you as soon as possible."

[0761] 7. The server sends the final customized answer to the user.

[0762] Prompt Sentence Examples

[0763] User query:

[0764] "Please tell me how to return the product. I would like this to be resolved quickly. I am in a very difficult situation."

[0765] Prompt for generative AI model:

[0766] "Generate an appropriate response to the following inquiry: 'Please tell me how to return an item. I'm really struggling and would appreciate a speedy response.' In your response, please include information about the process for returning an item."

[0767] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0768] Step 1: Receiving an inquiry

[0769] The server receives inquiries submitted by customers through web forms or chatbots as HTTP POST requests.

[0770] Input: Inquiry data sent by the customer (e.g., question about returning a product)

[0771] Data processing / calculation: Converting received data into a structured format (such as JSON or XML)

[0772] Output: A structured representation of the form data

[0773] Step 2: Save the received data

[0774] The server stores the structured query data in a database, and validates the format and content of the received data to ensure there are no errors.

[0775] Input: Structured inquiry data

[0776] Data processing / calculation: Insertion into database

[0777] Output: Query record stored in the database

[0778] Step 3: Language detection

[0779] The server sends the text data of the received query to a generative AI model, which automatically identifies the language used.

[0780] Input: Text data of the query

[0781] Data processing / computation: Language recognition using generative AI models

[0782] Output: Language (e.g. Japanese)

[0783] Step 4: Keyword extraction

[0784] After language determination is complete, the server runs the text data through a natural language processing algorithm to extract important keywords and phrases.

[0785] Input: Language-determined text data

[0786] Data processing / calculation: Applying keyword extraction algorithms

[0787] Output: Extracted keywords (e.g. "returns")

[0788] Step 5: Create a topic classification

[0789] The server categorizes the query into specific topics and categories based on the extracted keywords.

[0790] Input: Extracted keywords

[0791] Data processing / computation: Topic classification using generative AI models

[0792] Output: Categorized topics (e.g., "Return Procedure")

[0793] Step 6: Conduct an emergency assessment

[0794] The server analyzes the text and tone of the inquiry and assesses its urgency.

[0795] Input: relevant text data and key expressions

[0796] Data processing / computation: Using generative AI models and other algorithms to assess urgency

[0797] Output: Urgency rating (e.g., high urgency)

[0798] Step 7: Emotion Recognition

[0799] The server uses an emotion engine to recognize and evaluate customer emotions.

[0800] Input: Text data of the query

[0801] Data processing / calculation: Emotion analysis using emotion engine

[0802] Output: Recognized emotion (e.g. "sadness")

[0803] Step 8: Query the FAQ database

[0804] Based on the analysis results, the server searches for relevant answers from an FAQ database or knowledge base.

[0805] Input: Keywords and topic classification results

[0806] Data processing / calculation: Database query

[0807] Output: The searched answer (e.g., "Here's how to return the item...")

[0808] Step 9: Generate new answers as needed

[0809] If the server cannot find a suitable answer from the FAQ, it uses a generative AI model to generate a new answer.

[0810] Input: Re-enter data when query results are insufficient

[0811] Data processing / calculation: Answer generation using generative AI models

[0812] Output: The generated answer (e.g., "Please see the link below for return instructions...")

[0813] Step 10: Send your answers and sentiment information

[0814] The server then sends the generated answers and sentiment information to the customer support agent's device, where they are displayed on a dashboard and an alert is sent to the agent via a notification system.

[0815] Input: Generated answers and sentiment information

[0816] Data processing / calculation: Notifications and dashboard display

[0817] Output: Answers and emotion information displayed on the device

[0818] Step 11: Customer support representative customizes response

[0819] A customer support representative will review the response provided and make corrections or add additional information as necessary.

[0820] Input: Answers displayed on the dashboard

[0821] Data manipulation / calculation: customizing and modifying answers

[0822] Output: Customized answer

[0823] Step 12: Send the final response to the customer

[0824] The server then sends the final customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0825] Input: Customized Answer

[0826] Data processing / calculation: Sending answers

[0827] Output: Final response sent to customer

[0828] (Application example 2)

[0829] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0830] While there is an increasing demand for quick and accurate responses to customer inquiries, conventional systems have had the problem of taking time to analyze the content of inquiries and selecting appropriate responses, making it difficult to provide satisfactory customer service. Furthermore, they were unable to respond in a way that took into account the customer's emotions, which could result in a decline in customer satisfaction. It is known that delays in response have a significant negative impact on the customer experience, especially for urgent or emotional inquiries.

[0831] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; and means for responding based on the user's emotions by combining an emotion engine that recognizes the user's emotions based on the content of the inquiry. This eliminates the conventional issues of delays in responding to inquiries and the difficulty of responding while taking customer emotions into consideration, making it possible to improve customer satisfaction.

[0832] "Customer inquiries" refer to questions, requests, and opinions that customers make to a company or store in relation to the purchase of a product or the use of a service.

[0833] "Means for receiving" refers to the interface or process for inputting customer inquiry information into the server.

[0834] A "generative AI model" is an algorithm or software that learns from large amounts of data, uses natural language processing to understand inquiries and sentences, and automatically generates and analyzes them.

[0835] "Means of analysis" refers to the process of analyzing the content of the received inquiry and determining the language of the information, extracting keywords, classifying topics, assessing urgency, recognizing emotions, etc.

[0836] An "FAQ database" is a database that organizes and stores frequently asked questions and their answers collected in the past.

[0837] A "knowledge base" is a collection of information that aggregates and organizes knowledge about a particular topic or field and stores it in a searchable and usable format.

[0838] A "customer support representative" is a specialized staff member or operator who responds appropriately to customer inquiries.

[0839] "Means for providing" refers to a method or system for displaying or notifying a selected or generated answer to a customer support representative.

[0840] "Means for customization and verification" means the processes and tools that allow a customer support representative to modify or add to the provided response as needed and verify its content.

[0841] "Final Response" means the final response sent to Customer after customization and review.

[0842] An "emotion engine" is an algorithm or software that automatically analyzes user emotions from text data and outputs the results as numbers or tags.

[0843] "User emotion" refers to a psychological state such as joy, sadness, anger, or surprise that can be inferred from words and expressions contained in the query text.

[0844] "Response based on user emotions" refers to the process or means of responding to customers in an appropriate manner, taking into account the emotions recognized by the emotion engine.

[0845] The present invention is a system for responding quickly and accurately to customer inquiries, and includes the following main components: The roles of the server, terminal, and user, and the specific processes are as follows:

[0846] System Program

[0847] The server provides an interface for receiving customer inquiries, either through a web form or a chatbot. When a customer enters and submits an inquiry, it is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0848] The server then passes the received query content to a generative AI model for language determination, keyword extraction, topic classification, urgency assessment, and sentiment recognition. This process uses natural language processing (NLP) techniques, such as generative AI models like GPT-3 and BERT, or sentiment engines like Google Cloud Natural Language API and IBM Watson Tone Analyzer.

[0849] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0850] The server then sends the selected or generated answer to the customer support agent's device in real time. The agent is notified via a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the agent, allowing them to respond based on the user's emotions.

[0851] The customer support representative can review the response displayed on their device and customize it as needed. For example, they can add "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[0852] Finally, the server sends a confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0853] Specific examples

[0854] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[0855] 1. The server receives the query and stores it in a database.

[0856] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[0857] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[0858] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0859] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[0860] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[0861] 7. The server sends the final customized answer to the user.

[0862] Prompt Sentence Examples

[0863] "A user has submitted an inquiry saying, 'Please tell me how to return an item. I really need help, I want this resolved quickly.' Please generate an example response to this."

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Step 1:

[0866] The server receives inquiries from customers. Specifically, when a customer enters and submits an inquiry through a web form or chatbot, the content is sent to the server as an HTTP POST request. The server that receives this request stores the inquiry data in a database.

[0867] Input: Your query as an HTTP POST request.

[0868] Output: Query data stored in a database.

[0869] Step 2:

[0870] The server passes the received query content to a generative AI model and performs content analysis. This involves language determination, keyword extraction, topic classification, urgency assessment, and emotion recognition. Specifically, the server analyzes the text data using a generative AI model (e.g., GPT-3 or BERT) and an emotion engine (e.g., Google Cloud Natural Language API, IBM Watson Tone Analyzer).

[0871] Input: Query data stored in the database.

[0872] Output: Language, keyword, topic, urgency, and sentiment analysis results.

[0873] Step 3:

[0874] The server queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the corresponding answer cannot be found in the database, a new answer is automatically generated using a generative AI model. The model generates an appropriate answer based on the large amount of data learned during training.

[0875] Input: Analysis results (language, keywords, topic, urgency, sentiment).

[0876] Output: Search results from the FAQ database or generated answers.

[0877] Step 4:

[0878] The server sends the selected or generated answer and sentiment information to the customer support agent's device in real time, notifying the agent via a notification system (e.g., Firebase Cloud Messaging), and displaying the answer on a dashboard.

[0879] Input: Search results or generated answers, sentiment information.

[0880] Output: Answers and sentiment information displayed on the customer support representative's device.

[0881] Step 5:

[0882] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding appropriate details or supplementary explanations. Once the representative has customized the response, it is sent back to the server and stored.

[0883] Input: Answers and sentiment information displayed on the dashboard.

[0884] Output: A customized final answer.

[0885] Step 6:

[0886] The server sends a final, customized response to the customer, using email, chat, or other communication channel specified by the customer.

[0887] Input: Your customized final answer.

[0888] Output: The final response sent to the customer.

[0889] In this way, the system automates and streamlines the process of receiving an inquiry, analyzing it, providing an appropriate response, and then having the agent customize and send the final response to the customer.

[0890] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0891] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0892] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0893] [Third embodiment]

[0894] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0895] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0896] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0897] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0898] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0899] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0900] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0901] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0902] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0903] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0904] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0905] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0906] The system of the present invention includes the following major components for quickly and accurately processing customer inquiries:

[0907] Inquiry Receiving Module

[0908] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[0909] Content Analysis Module

[0910] The server passes the received query content to the generative AI model and performs the following analysis:

[0911] Language detection: Automatically identify the language used from the query text.

[0912] Keyword extraction: Identify and extract important words and phrases.

[0913] Topic classification: Categorizing inquiries into specific topics or categories.

[0914] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0915] Answer selection / generation module

[0916] The server then queries the FAQ database or knowledge base based on the analysis results to find the appropriate answer. If the search results are insufficient, a new answer is automatically generated using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0917] Customer Support Delivery Module

[0918] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0919] Customization and Review Module

[0920] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and saved.

[0921] Module for sending answers to customers

[0922] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0923] Specific examples

[0924] For example, a user may send an inquiry saying, "Please tell me about returning a product."

[0925] 1. The server receives the query and stores it in a database.

[0926] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0927] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0928] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0929] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0930] 6. The server sends the final customized answer to the user.

[0931] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0932] The processing flow will be explained below.

[0933] Step 1:

[0934] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[0935] Step 2:

[0936] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[0937] Step 3:

[0938] The server adds the query to a queue and passes it as input to the generative AI model.

[0939] Step 4:

[0940] The generative AI model running on the server performs the following analysis:

[0941] Language detection: Identifying the language used from text.

[0942] Keyword extraction: Extracting important words and phrases from text.

[0943] Topical classification: Classifying content into specific categories or topics.

[0944] Urgency assessment: Assess urgency based on wording and content.

[0945] Step 5:

[0946] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[0947] Step 6:

[0948] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[0949] Step 7:

[0950] The server sends the searched and generated answer to the customer support agent's device, notifies the agent using the notification system, and displays the answer on the dashboard.

[0951] Step 8:

[0952] The customer support representative can review the response on their device and customize it as needed, for example by adding "more information about the return process."

[0953] Step 9:

[0954] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[0955] Step 10:

[0956] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[0957] Step 11:

[0958] The user receives the response and reviews the information that will help them solve the problem.

[0959] Example 1

[0960] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0961] Conventional customer support systems have faced challenges in responding to customer inquiries quickly and accurately. Analyzing inquiries and providing appropriate responses takes a significant amount of time and effort, often resulting in lower customer satisfaction and increased workloads for support staff. Furthermore, the process for customer support staff to find and customize appropriate responses is complex and inefficient.

[0962] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0963] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for notifying a customer support representative of the selected or generated answer and displaying it on a dashboard, means for the customer support representative to customize and confirm the provided answer, and means for sending the final answer to the customer. This significantly improves the speed and accuracy of inquiry processing and makes it possible to increase customer satisfaction.

[0964] "Customer" refers to a person who uses a service or product or makes an inquiry about such a service or product.

[0965] "Enquiry" means a question or request submitted by a Customer seeking information or resolving a question about a product or service.

[0966] A "generative AI model" refers to an artificial intelligence algorithm or system that uses natural language processing to analyze a query and generate an appropriate response.

[0967] An "FAQ database" refers to a database that stores frequently asked questions and their answers, enabling quick responses to customer inquiries.

[0968] A "knowledge base" is a database containing detailed information about a particular field, and is used in expert systems and support systems.

[0969] "Customer Support Representative" means an individual whose job is to receive and provide responses to customer inquiries.

[0970] A "dashboard" is an interface used by customer support staff and is a tool that centrally manages and displays inquiries and responses.

[0971] "Notification system" refers to a mechanism that notifies customer support representatives that a generated response has been received.

[0972] "Urgency" refers to a criterion for assessing the importance of the inquiry and the degree to which a prompt response is required.

[0973] The system of the present invention realizes a fast and accurate response to customer inquiries. The system includes the following main components:

[0974] Inquiry Receiving Module

[0975] The server uses a web form or chatbot as an interface to receive customer inquiries. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a MySQL database.

[0976] Content Analysis Module

[0977] The server passes the received query to a generative AI model (e.g., OpenAI's GPT-3), which performs the following analysis:

[0978] Language detection: Automatically identify the language used from the query text.

[0979] Keyword extraction: Identify and extract important words and phrases.

[0980] Topic classification: Categorizing inquiries into specific topics or categories.

[0981] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[0982] Answer selection / generation module

[0983] The server queries a FAQ database or knowledge base (e.g., Elasticsearch) based on the analysis results to find the appropriate answer. If the search results are insufficient, a generative AI model generates a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[0984] Customer Support Delivery Module

[0985] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[0986] Customization and Review Module

[0987] The customer support representative can review the response displayed on their device and customize it as needed, for example, to add more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and stored.

[0988] Module for sending answers to customers

[0989] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[0990] Specific examples

[0991] For example, consider the case where a user sends an inquiry saying, "Please tell me about returning a product."

[0992] 1. The server receives the query and stores it in a database.

[0993] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[0994] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[0995] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[0996] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[0997] 6. The server sends the final customized answer to the user.

[0998] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[0999] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1000] Step 1: Receiving an inquiry

[1001] server

[1002] Input: A user enters their inquiry using a web form or chatbot and clicks submit.

[1003] Processing: The server receives the HTTP POST request.

[1004] Data processing: Analyze the received inquiry content and convert it into an appropriate format (e.g., JSON format).

[1005] Output: Save the transformed query data into a MySQL database.

[1006] Specific behavior: The user enters and submits "Please tell me about returning the product." The server receives this request and stores it in the database.

[1007] Step 2: Content analysis

[1008] server

[1009] Input: Query data stored in the database.

[1010] Processing: Send the data to a generative AI model (e.g., GPT-3) and ask it to analyze:

[1011] Language determination: Identifying the language used from the query text.

[1012] Keyword extraction: Extract important words and phrases.

[1013] Topic classification: Categorizing inquiries into specific topics or categories.

[1014] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1015] Data calculation: The AI ​​model analyzes the query text and extracts relevant information.

[1016] Output: Analysis results (language, keywords, topics, urgency).

[1017] Specific operation: The server sends the text "Please tell me about returning the product" to the AI ​​model, and the model determines that it is in Japanese, contains the keyword "return," and has low urgency.

[1018] Step 3: Answer selection / generation

[1019] server

[1020] Input: Analysis results (language, keywords, topic, urgency).

[1021] Processing: Search for the right answer in a FAQ database or knowledge base (e.g., Elasticsearch).

[1022] Data processing: Querying an FAQ database or knowledge base to retrieve relevant answers.

[1023] Data computation: Generative AI models generate new answers (when search results are insufficient).

[1024] Output: The searched or generated answer.

[1025] Specific operation: The server searches for FAQs related to "returns," but no relevant answer is found, so the generative AI model generates the answer, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1026] Step 4: Providing customer support

[1027] server

[1028] Input: The searched or generated answer.

[1029] Action: Send the response to the customer support representative's device.

[1030] Data processing: Converting response information into a format that can be passed to the notification system and dashboard.

[1031] Output: Notification to customer support representative and response displayed on dashboard.

[1032] Specific operation: The server sends the answer to the customer support representative's device and displays it on the dashboard.

[1033] Step 5: Customize and verify

[1034] Customer Support Representative

[1035] Input: The answer displayed on the dashboard.

[1036] Action: Review the answers and customize them as needed.

[1037] Data processing: Converting data into a format with additional information or corrections.

[1038] Output: A customized final answer.

[1039] Specific actions: The rep adds additional information, such as "The return period is within 30 days of purchase." The customized response is then resubmitted to the server and saved.

[1040] Step 6: Send your response to the customer

[1041] server

[1042] Input: Your customized final answer.

[1043] Processing: Send a response via the method specified by the customer (email, chat, etc.).

[1044] Data processing: Converting customer contact information into a compatible format.

[1045] Output: Sending the final response to the customer.

[1046] Specific operation: The server sends a customized response to the user using the email sending API. The user receives an email with the following response: "Please refer to the link below for the product return procedure. Returns are accepted within 30 days of purchase, and the customer is responsible for the return shipping costs."

[1047] (Application example 1)

[1048] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1049] When responding to customer inquiries, manual response takes time and effort, making it difficult to provide accurate and prompt answers. Furthermore, particularly for online shopping sites, prompt and accurate customer support is required to increase customer satisfaction. Therefore, a system that automatically analyzes the content of inquiries and generates and provides appropriate answers is required.

[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1051] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for providing the selected or generated answer to a customer support representative, means for the customer support representative to customize and confirm the provided answer, means for sending the final answer to the customer, and means for enhancing customer support functions using a smartphone application to improve the speed and accuracy of inquiry processing, thereby enabling quick and accurate responses to customer inquiries and increasing customer satisfaction.

[1052] The "inquiry receiving means" is a means for receiving inquiries from customers, and transmits the contents of the inquiries to the server through an interface such as a web form or chatbot.

[1053] A "generative AI model" is a model that uses artificial intelligence to analyze and generate natural language, automatically generating appropriate answers based on the content of the inquiry.

[1054] The "analysis means" is a means for analyzing the content of the received inquiry, and performs language identification, keyword extraction, topic classification, and urgency assessment.

[1055] "Answer generation means" refers to a means for selecting an appropriate answer from an FAQ database or knowledge base based on the results obtained by the analysis means, or for generating a new answer using a generative AI model.

[1056] "Answer Providing Means" means a means for providing a selected or generated answer to a customer support representative, and for displaying the answer in real time using a notification system or dashboard.

[1057] "Customization and Verification Means" means a means by which a customer support representative can review the answers provided and add or modify information as needed.

[1058] "Response sending means" refers to the means for sending the final response to the customer, and may be via email, chat, in-app notifications, etc.

[1059] "Smartphone Application" means a software application that operates on a smartphone and is used to receive customer inquiries and generate and provide prompt and accurate responses.

[1060] The present invention is a system for quickly and accurately processing customer inquiries, which uses a server, customer terminals, customer support terminals, and software applications that run on these terminals.

[1061] The server first receives an inquiry from a customer. The customer uses a smartphone application to send the inquiry to the server via a chatbot or inquiry form. The received inquiry is then stored in a database.

[1062] The generative AI model running on the server analyzes the received inquiry. This analysis includes language identification, keyword extraction, topic classification of the inquiry, and urgency assessment. Based on the analysis results, the server searches an FAQ database or knowledge base to select an appropriate answer. If a suitable answer is not found, the generative AI model generates a new answer.

[1063] The generated answer is sent to the customer support representative's device and displayed on their dashboard. The customer support representative reviews the answer and customizes it with additional information as needed. The final customized answer is stored on the server again and sent to the customer. The customer receives the answer through their specified communication channel (email, chat, in-app notification, etc.).

[1064] The system is implemented using the following hardware and software:

[1065] Hardware: Servers (cloud-based or physical), customer smartphones, customer support representative computers

[1066] Software: A web server using the Flask framework, a SQLite or PostgreSQL database, an OpenAI generative model (e.g., GPT-3), and a smartphone application.

[1067] As a concrete example, consider the case where a user sends an inquiry such as "Please tell me the delivery status of my item." The server receives the inquiry and stores it in a database. The generative AI model determines that the inquiry is in Japanese, extracts the keywords "order" and "delivery status," and classifies it as a topic called "delivery." The urgency is assessed as medium. The server searches FAQs related to "delivery," and if no relevant answer is found, the generative AI model generates a new answer. For example, it might say, "You can check the delivery status of your order by clicking this link: <link>."

[1068] An example of a prompt to input to the generative AI model is:

[1069] User's question: "What is the delivery status of my order?"

[1070] Language detection: Japanese

[1071] Keyword extraction: ["order", "shipping status"]

[1072] Topic Category: "Shipping"

[1073] Urgency rating: Medium

[1074] → Generate an answer.

[1075] The system of the present invention enables quick and accurate responses to customer inquiries, thereby increasing customer satisfaction.

[1076] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1077] Step 1:

[1078] A user inputs and sends an inquiry via a smartphone application. The inquiry is sent from the application to the server as an HTTP POST request, and the server receives it. The input contains the user's inquiry, and the output is the inquiry that is stored in the inquiry database on the server. Specifically, the user inputs "Please tell me the delivery status of my item" and presses the send button.

[1079] Step 2:

[1080] The server passes the received inquiry content to the generative AI model for analysis. The analysis includes language identification, keyword extraction, topic classification of the inquiry content, and urgency assessment. The input is the received inquiry content, and the output is the results of language, keywords, topic classification, and urgency assessment. Specific operations include generating results such as "Japanese," "Order," "Delivery status," "Delivery," and "Medium urgency."

[1081] Step 3:

[1082] Based on the results of the analysis by the generative AI model, the server searches the FAQ database or knowledge base to select an appropriate answer. If a corresponding answer is not found, the generative AI model generates a new answer. The input is the analysis result, and the output is the selected answer or a new generated answer. Specifically, the searched FAQ selects the answer "You can check the delivery status of your order by clicking this link: <link>".

[1083] Step 4:

[1084] The server notifies the customer support representative's terminal of the selected or generated answer and displays it on the dashboard. The input is the selected or generated answer, and the output is the displayed answer. The specific operation is that the customer support representative's dashboard displays "You can check the delivery status of your order by clicking this link: <link>".

[1085] Step 5:

[1086] The customer support representative reviews the displayed answer and adds or modifies information as needed. The input is the provided answer, and the output is the customized final answer. The specific action is to modify the dashboard to read, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[1087] Step 6:

[1088] The server sends a final response to the customer via the communication channel specified by the user (email, chat, in-app notification, etc.). The input is the customized final response, and the output is the response sent to the customer. The specific behavior is that an email is sent to the customer's email address stating, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[1089] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1090] The system of the present invention includes the following main components to enable quick and accurate responses to customer inquiries. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions based on the content of the inquiry and provide a more appropriate response.

[1091] Inquiry Receiving Module

[1092] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1093] Content Analysis Module

[1094] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[1095] Language detection: Automatically identify the language used from the query text.

[1096] Keyword extraction: Identify and extract important words and phrases.

[1097] Topic classification: Categorizing inquiries into specific topics or categories.

[1098] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1099] Emotion Recognition: Analyze and evaluate the user's emotions from the query text. Emotion types include joy, anger, sadness, surprise, etc.

[1100] Answer selection / generation module

[1101] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it automatically generates a new answer using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1102] Customer Support Delivery Module

[1103] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[1104] Customization and Review Module

[1105] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[1106] Module for sending answers to customers

[1107] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1108] Specific examples

[1109] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1110] 1. The server receives the query and stores it in a database.

[1111] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1112] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1113] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1114] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1115] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[1116] 7. The server sends the final customized answer to the user.

[1117] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, and can further increase customer satisfaction by taking user emotions into consideration when responding.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[1121] Step 2:

[1122] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[1123] Step 3:

[1124] The server adds the query to a queue and passes it as input to the generative AI model.

[1125] Step 4:

[1126] The generative AI model running on the server performs the following analysis:

[1127] Language detection: Identifying the language used from text.

[1128] Keyword extraction: Extracting important words and phrases from text.

[1129] Topical classification: Classifying content into specific categories or topics.

[1130] Urgency assessment: Assess urgency based on wording and content.

[1131] Step 5:

[1132] The emotion engine running on the server analyzes and evaluates the user's emotions from the query text, including joy, anger, sadness, surprise, etc.

[1133] Step 6:

[1134] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[1135] Step 7:

[1136] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[1137] Step 8:

[1138] The server sends the generated answer and emotion information to the customer support agent's device, notifies the agent using a notification system, and displays the answer and user emotion on a dashboard.

[1139] Step 9:

[1140] The customer support representative reviews the provided response on their device and customizes it as needed, for example, adding "more information about the return process" or "urgent action required."

[1141] Step 10:

[1142] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[1143] Step 11:

[1144] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[1145] Step 12:

[1146] The user receives the response and reviews the information that will help them solve the problem.

[1147] Specific examples

[1148] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1149] 1. The server receives the query and stores it in a database.

[1150] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1151] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1152] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1153] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1154] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble, and we'll get back to you as soon as possible. Returns are accepted within 30 days of purchase."

[1155] 7. The server sends the final customized answer to the user.

[1156] Example 2

[1157] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1158] Responding quickly and accurately to customer inquiries is important for improving customer satisfaction. However, mechanical responses that ignore customer emotions can make it difficult to resolve customer dissatisfaction and may result in delayed appropriate responses. To improve this situation, it is necessary not only to analyze the content of inquiries, but also to recognize and respond to customer emotions.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1160] In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; means including an emotion engine for recognizing the customer's emotion from the content of the inquiry; and means for providing the emotion information recognized by the emotion engine to the customer support representative. This makes it possible to recognize the customer's emotion while analyzing the content of the inquiry, and to provide an optimal response based on that.

[1161] "Means for receiving inquiries from customers" refers to the interface and protocol for sending the inquiry content entered by customers through a web form or chatbot to a server and receiving it.

[1162] "Means of analysis using a generative AI model" refers to the process of using machine learning and natural language processing techniques to analyze the text data of received inquiries and automatically determine the language, keywords, topics, etc.

[1163] "Means for selecting or generating from an FAQ database or knowledge base" refers to a process for searching an existing FAQ database or knowledge base based on the results of the analysis and selecting appropriate answers or generating new answers as needed.

[1164] "Means provided to customer support representative" refers to a system for transmitting the selected or generated answer to the representative's device and making it visible through notifications and dashboards.

[1165] "Means for customization and review" means the interface and functionality that allows a customer support representative to review the responses provided and make corrections or add additional information as needed.

[1166] "Means for sending the final response to the customer" refers to the mechanism by which the final response that the agent has confirmed and customized is sent to the customer via a communication channel such as an email address or chat system specified by the customer.

[1167] "Means including an emotion engine" refers to software and algorithms for analyzing customer emotions from received inquiries using natural language processing and providing the results in a format that can be used by the system.

[1168] The present invention is a system for responding to customer inquiries quickly and accurately, and includes the following main components: In particular, it incorporates an emotion engine that recognizes customer emotions based on the content of the inquiry, enabling more appropriate responses.

[1169] Inquiry Receiving Module

[1170] The server provides a web form or chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1171] Content Analysis Module

[1172] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[1173] Language detection: Automatically identify the language used from the query text.

[1174] Keyword extraction: Identify and extract important words and phrases.

[1175] Topic classification: Categorizing inquiries into specific topics or categories.

[1176] Urgency assessment: Assess the urgency based on the tone and content of the inquiry.

[1177] Emotion Recognition: Analyze and evaluate the user's emotions from the query text.

[1178] Answer selection / generation module

[1179] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This process uses a multi-layer neural network to provide accurate grammar and appropriate response content.

[1180] Customer Support Delivery Module

[1181] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. In addition, emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[1182] Customization and Review Module

[1183] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return procedure." Once the representative has customized the response, it is sent back to the server and saved.

[1184] Module for sending answers to customers

[1185] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1186] Examples of concrete examples and prompts

[1187] For example, a case will be described in which a user sends an inquiry saying, "Please tell me how to return a product. I would like you to deal with this as soon as possible. I am in a really difficult situation."

[1188] Specific examples

[1189] 1. The server receives the query and stores it in a database.

[1190] 2. The generative AI model running on the server determines that the inquiry is in Japanese and extracts the keyword "return." The urgency is assessed as high.

[1191] 3. The emotion engine determines the user's emotion as "sadness" based on the expression "troubled."

[1192] 4. The server searches the database for FAQs related to "returns." If no relevant FAQ is found, the generative AI model generates an answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1193] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1194] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble and will get back to you as soon as possible."

[1195] 7. The server sends the final customized answer to the user.

[1196] Prompt Sentence Examples

[1197] User query:

[1198] "Please tell me how to return the product. I would like this to be resolved quickly. I am in a very difficult situation."

[1199] Prompt for generative AI model:

[1200] "Generate an appropriate response to the following inquiry: 'Please tell me how to return an item. I'm really struggling and would appreciate a speedy response.' In your response, please include information about the process for returning an item."

[1201] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1202] Step 1: Receiving an inquiry

[1203] The server receives inquiries submitted by customers through web forms or chatbots as HTTP POST requests.

[1204] Input: Inquiry data sent by the customer (e.g., question about returning a product)

[1205] Data processing / calculation: Converting received data into a structured format (such as JSON or XML)

[1206] Output: A structured representation of the form data

[1207] Step 2: Save the received data

[1208] The server stores the structured query data in a database, and validates the format and content of the received data to ensure there are no errors.

[1209] Input: Structured inquiry data

[1210] Data processing / calculation: Insertion into database

[1211] Output: Query record stored in the database

[1212] Step 3: Language detection

[1213] The server sends the text data of the received query to a generative AI model, which automatically identifies the language used.

[1214] Input: Text data of the query

[1215] Data processing / computation: Language recognition using generative AI models

[1216] Output: Language (e.g. Japanese)

[1217] Step 4: Keyword extraction

[1218] After language determination is complete, the server runs the text data through a natural language processing algorithm to extract important keywords and phrases.

[1219] Input: Language-determined text data

[1220] Data processing / calculation: Applying keyword extraction algorithms

[1221] Output: Extracted keywords (e.g. "returns")

[1222] Step 5: Create a topic classification

[1223] The server categorizes the query into specific topics and categories based on the extracted keywords.

[1224] Input: Extracted keywords

[1225] Data processing / computation: Topic classification using generative AI models

[1226] Output: Categorized topics (e.g., "Return Procedure")

[1227] Step 6: Conduct an emergency assessment

[1228] The server analyzes the text and tone of the inquiry and assesses its urgency.

[1229] Input: relevant text data and key expressions

[1230] Data processing / computation: Using generative AI models and other algorithms to assess urgency

[1231] Output: Urgency rating (e.g., high urgency)

[1232] Step 7: Emotion Recognition

[1233] The server uses an emotion engine to recognize and evaluate customer emotions.

[1234] Input: Text data of the query

[1235] Data processing / calculation: Emotion analysis using emotion engine

[1236] Output: Recognized emotion (e.g. "sadness")

[1237] Step 8: Query the FAQ database

[1238] Based on the analysis results, the server searches for relevant answers from an FAQ database or knowledge base.

[1239] Input: Keywords and topic classification results

[1240] Data processing / calculation: Database query

[1241] Output: The searched answer (e.g., "Here's how to return the item...")

[1242] Step 9: Generate new answers as needed

[1243] If the server cannot find a suitable answer from the FAQ, it uses a generative AI model to generate a new answer.

[1244] Input: Re-enter data when query results are insufficient

[1245] Data processing / calculation: Answer generation using generative AI models

[1246] Output: The generated answer (e.g., "Please see the link below for return instructions...")

[1247] Step 10: Send your answers and sentiment information

[1248] The server then sends the generated answers and sentiment information to the customer support agent's device, where they are displayed on a dashboard and an alert is sent to the agent via a notification system.

[1249] Input: Generated answers and sentiment information

[1250] Data processing / calculation: Notifications and dashboard display

[1251] Output: Answers and emotion information displayed on the device

[1252] Step 11: Customer support representative customizes response

[1253] A customer support representative will review the response provided and make corrections or add additional information as necessary.

[1254] Input: Answers displayed on the dashboard

[1255] Data manipulation / calculation: customizing and modifying answers

[1256] Output: Customized answer

[1257] Step 12: Send the final response to the customer

[1258] The server then sends the final customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1259] Input: Customized Answer

[1260] Data processing / calculation: Sending answers

[1261] Output: Final response sent to customer

[1262] (Application example 2)

[1263] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1264] While there is an increasing demand for quick and accurate responses to customer inquiries, conventional systems have had the problem of taking time to analyze the content of inquiries and selecting appropriate responses, making it difficult to provide satisfactory customer service. Furthermore, they were unable to respond in a way that took into account the customer's emotions, which could result in a decline in customer satisfaction. It is known that delays in response have a significant negative impact on the customer experience, especially for urgent or emotional inquiries.

[1265] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; and means for responding based on the user's emotions by combining an emotion engine that recognizes the user's emotions based on the content of the inquiry. This eliminates the conventional issues of delays in responding to inquiries and the difficulty of responding while taking customer emotions into consideration, making it possible to improve customer satisfaction.

[1266] "Customer inquiries" refer to questions, requests, and opinions that customers make to a company or store in relation to the purchase of a product or the use of a service.

[1267] "Means for receiving" refers to the interface or process for inputting customer inquiry information into the server.

[1268] A "generative AI model" is an algorithm or software that learns from large amounts of data, uses natural language processing to understand inquiries and sentences, and automatically generates and analyzes them.

[1269] "Means of analysis" refers to the process of analyzing the content of the received inquiry and determining the language of the information, extracting keywords, classifying topics, assessing urgency, recognizing emotions, etc.

[1270] An "FAQ database" is a database that organizes and stores frequently asked questions and their answers collected in the past.

[1271] A "knowledge base" is a collection of information that aggregates and organizes knowledge about a particular topic or field and stores it in a searchable and usable format.

[1272] A "customer support representative" is a specialized staff member or operator who responds appropriately to customer inquiries.

[1273] "Means for providing" refers to a method or system for displaying or notifying a selected or generated answer to a customer support representative.

[1274] "Means for customization and verification" means the processes and tools that allow a customer support representative to modify or add to the provided response as needed and verify its content.

[1275] "Final Response" means the final response sent to Customer after customization and review.

[1276] An "emotion engine" is an algorithm or software that automatically analyzes user emotions from text data and outputs the results as numbers or tags.

[1277] "User emotion" refers to a psychological state such as joy, sadness, anger, or surprise that can be inferred from words and expressions contained in the query text.

[1278] "Response based on user emotions" refers to the process or means of responding to customers in an appropriate manner, taking into account the emotions recognized by the emotion engine.

[1279] The present invention is a system for responding quickly and accurately to customer inquiries, and includes the following main components: The roles of the server, terminal, and user, and the specific processes are as follows:

[1280] System Program

[1281] The server provides an interface for receiving customer inquiries, either through a web form or a chatbot. When a customer enters and submits an inquiry, it is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1282] The server then passes the received query content to a generative AI model for language determination, keyword extraction, topic classification, urgency assessment, and sentiment recognition. This process uses natural language processing (NLP) techniques, such as generative AI models like GPT-3 and BERT, or sentiment engines like Google Cloud Natural Language API and IBM Watson Tone Analyzer.

[1283] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1284] The server then sends the selected or generated answer to the customer support agent's device in real time. The agent is notified via a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the agent, allowing them to respond based on the user's emotions.

[1285] The customer support representative can review the response displayed on their device and customize it as needed. For example, they can add "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[1286] Finally, the server sends a confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1287] Specific examples

[1288] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1289] 1. The server receives the query and stores it in a database.

[1290] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1291] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1292] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1293] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1294] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[1295] 7. The server sends the final customized answer to the user.

[1296] Prompt Sentence Examples

[1297] "A user has submitted an inquiry saying, 'Please tell me how to return an item. I really need help, I want this resolved quickly.' Please generate an example response to this."

[1298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1299] Step 1:

[1300] The server receives inquiries from customers. Specifically, when a customer enters and submits an inquiry through a web form or chatbot, the content is sent to the server as an HTTP POST request. The server that receives this request stores the inquiry data in a database.

[1301] Input: Your query as an HTTP POST request.

[1302] Output: Query data stored in a database.

[1303] Step 2:

[1304] The server passes the received query content to a generative AI model and performs content analysis. This involves language determination, keyword extraction, topic classification, urgency assessment, and emotion recognition. Specifically, the server analyzes the text data using a generative AI model (e.g., GPT-3 or BERT) and an emotion engine (e.g., Google Cloud Natural Language API, IBM Watson Tone Analyzer).

[1305] Input: Query data stored in the database.

[1306] Output: Language, keyword, topic, urgency, and sentiment analysis results.

[1307] Step 3:

[1308] The server queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the corresponding answer cannot be found in the database, a new answer is automatically generated using a generative AI model. The model generates an appropriate answer based on the large amount of data learned during training.

[1309] Input: Analysis results (language, keywords, topic, urgency, sentiment).

[1310] Output: Search results from the FAQ database or generated answers.

[1311] Step 4:

[1312] The server sends the selected or generated answer and sentiment information to the customer support agent's device in real time, notifying the agent via a notification system (e.g., Firebase Cloud Messaging), and displaying the answer on a dashboard.

[1313] Input: Search results or generated answers, sentiment information.

[1314] Output: Answers and sentiment information displayed on the customer support representative's device.

[1315] Step 5:

[1316] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding appropriate details or supplementary explanations. Once the representative has customized the response, it is sent back to the server and stored.

[1317] Input: Answers and sentiment information displayed on the dashboard.

[1318] Output: A customized final answer.

[1319] Step 6:

[1320] The server sends a final, customized response to the customer, using email, chat, or other communication channel specified by the customer.

[1321] Input: Your customized final answer.

[1322] Output: The final response sent to the customer.

[1323] In this way, the system automates and streamlines the process of receiving an inquiry, analyzing it, providing an appropriate response, and then having the agent customize and send the final response to the customer.

[1324] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1325] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1326] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1327] [Fourth embodiment]

[1328] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1329] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1330] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1331] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1332] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1333] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1334] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1335] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1336] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1337] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1338] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1339] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1340] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1341] The system of the present invention includes the following major components for quickly and accurately processing customer inquiries:

[1342] Inquiry Receiving Module

[1343] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1344] Content Analysis Module

[1345] The server passes the received query content to the generative AI model and performs the following analysis:

[1346] Language detection: Automatically identify the language used from the query text.

[1347] Keyword extraction: Identify and extract important words and phrases.

[1348] Topic classification: Categorizing inquiries into specific topics or categories.

[1349] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1350] Answer selection / generation module

[1351] The server then queries the FAQ database or knowledge base based on the analysis results to find the appropriate answer. If the search results are insufficient, a new answer is automatically generated using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1352] Customer Support Delivery Module

[1353] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[1354] Customization and Review Module

[1355] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and saved.

[1356] Module for sending answers to customers

[1357] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1358] Specific examples

[1359] For example, a user may send an inquiry saying, "Please tell me about returning a product."

[1360] 1. The server receives the query and stores it in a database.

[1361] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[1362] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1363] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[1364] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[1365] 6. The server sends the final customized answer to the user.

[1366] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[1367] The processing flow will be explained below.

[1368] Step 1:

[1369] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[1370] Step 2:

[1371] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[1372] Step 3:

[1373] The server adds the query to a queue and passes it as input to the generative AI model.

[1374] Step 4:

[1375] The generative AI model running on the server performs the following analysis:

[1376] Language detection: Identifying the language used from text.

[1377] Keyword extraction: Extracting important words and phrases from text.

[1378] Topical classification: Classifying content into specific categories or topics.

[1379] Urgency assessment: Assess urgency based on wording and content.

[1380] Step 5:

[1381] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[1382] Step 6:

[1383] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[1384] Step 7:

[1385] The server sends the searched and generated answer to the customer support agent's device, notifies the agent using the notification system, and displays the answer on the dashboard.

[1386] Step 8:

[1387] The customer support representative can review the response on their device and customize it as needed, for example by adding "more information about the return process."

[1388] Step 9:

[1389] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[1390] Step 10:

[1391] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[1392] Step 11:

[1393] The user receives the response and reviews the information that will help them solve the problem.

[1394] Example 1

[1395] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1396] Conventional customer support systems have faced challenges in responding to customer inquiries quickly and accurately. Analyzing inquiries and providing appropriate responses takes a significant amount of time and effort, often resulting in lower customer satisfaction and increased workloads for support staff. Furthermore, the process for customer support staff to find and customize appropriate responses is complex and inefficient.

[1397] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1398] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for notifying a customer support representative of the selected or generated answer and displaying it on a dashboard, means for the customer support representative to customize and confirm the provided answer, and means for sending the final answer to the customer. This significantly improves the speed and accuracy of inquiry processing and makes it possible to increase customer satisfaction.

[1399] "Customer" refers to a person who uses a service or product or makes an inquiry about such a service or product.

[1400] "Enquiry" means a question or request submitted by a Customer seeking information or resolving a question about a product or service.

[1401] A "generative AI model" refers to an artificial intelligence algorithm or system that uses natural language processing to analyze a query and generate an appropriate response.

[1402] An "FAQ database" refers to a database that stores frequently asked questions and their answers, enabling quick responses to customer inquiries.

[1403] A "knowledge base" is a database containing detailed information about a particular field, and is used in expert systems and support systems.

[1404] "Customer Support Representative" means an individual whose job is to receive and provide responses to customer inquiries.

[1405] A "dashboard" is an interface used by customer support staff and is a tool that centrally manages and displays inquiries and responses.

[1406] "Notification system" refers to a mechanism that notifies customer support representatives that a generated response has been received.

[1407] "Urgency" refers to a criterion for assessing the importance of the inquiry and the degree to which a prompt response is required.

[1408] The system of the present invention realizes a fast and accurate response to customer inquiries. The system includes the following main components:

[1409] Inquiry Receiving Module

[1410] The server uses a web form or chatbot as an interface to receive customer inquiries. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a MySQL database.

[1411] Content Analysis Module

[1412] The server passes the received query to a generative AI model (e.g., OpenAI's GPT-3), which performs the following analysis:

[1413] Language detection: Automatically identify the language used from the query text.

[1414] Keyword extraction: Identify and extract important words and phrases.

[1415] Topic classification: Categorizing inquiries into specific topics or categories.

[1416] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1417] Answer selection / generation module

[1418] The server queries a FAQ database or knowledge base (e.g., Elasticsearch) based on the analysis results to find the appropriate answer. If the search results are insufficient, a generative AI model generates a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1419] Customer Support Delivery Module

[1420] The server sends the selected or generated answer in real time to the customer support representative's device, notifies the representative via a notification system, and displays the answer on a dashboard.

[1421] Customization and Review Module

[1422] The customer support representative can review the response displayed on their device and customize it as needed, for example, to add more detailed return procedure information. Once the representative has customized the response, it is sent back to the server and stored.

[1423] Module for sending answers to customers

[1424] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1425] Specific examples

[1426] For example, consider the case where a user sends an inquiry saying, "Please tell me about returning a product."

[1427] 1. The server receives the query and stores it in a database.

[1428] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is assessed as low.

[1429] 3. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1430] 4. The server sends the response to the customer support representative's terminal and displays it on the dashboard.

[1431] 5. The customer support representative reviews the response and adds additional information, such as "Returns are accepted within 30 days of purchase."

[1432] 6. The server sends the final customized answer to the user.

[1433] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, thereby increasing customer satisfaction.

[1434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1435] Step 1: Receiving an inquiry

[1436] server

[1437] Input: A user enters their inquiry using a web form or chatbot and clicks submit.

[1438] Processing: The server receives the HTTP POST request.

[1439] Data processing: Analyze the received inquiry content and convert it into an appropriate format (e.g., JSON format).

[1440] Output: Save the transformed query data into a MySQL database.

[1441] Specific behavior: The user enters and submits "Please tell me about returning the product." The server receives this request and stores it in the database.

[1442] Step 2: Content analysis

[1443] server

[1444] Input: Query data stored in the database.

[1445] Processing: Send the data to a generative AI model (e.g., GPT-3) and ask it to analyze:

[1446] Language determination: Identifying the language used from the query text.

[1447] Keyword extraction: Extract important words and phrases.

[1448] Topic classification: Categorizing inquiries into specific topics or categories.

[1449] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1450] Data calculation: The AI ​​model analyzes the query text and extracts relevant information.

[1451] Output: Analysis results (language, keywords, topics, urgency).

[1452] Specific operation: The server sends the text "Please tell me about returning the product" to the AI ​​model, and the model determines that it is in Japanese, contains the keyword "return," and has low urgency.

[1453] Step 3: Answer selection / generation

[1454] server

[1455] Input: Analysis results (language, keywords, topic, urgency).

[1456] Processing: Search for the right answer in a FAQ database or knowledge base (e.g., Elasticsearch).

[1457] Data processing: Querying an FAQ database or knowledge base to retrieve relevant answers.

[1458] Data computation: Generative AI models generate new answers (when search results are insufficient).

[1459] Output: The searched or generated answer.

[1460] Specific operation: The server searches for FAQs related to "returns," but no relevant answer is found, so the generative AI model generates the answer, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1461] Step 4: Providing customer support

[1462] server

[1463] Input: The searched or generated answer.

[1464] Action: Send the response to the customer support representative's device.

[1465] Data processing: Converting response information into a format that can be passed to the notification system and dashboard.

[1466] Output: Notification to customer support representative and response displayed on dashboard.

[1467] Specific operation: The server sends the answer to the customer support representative's device and displays it on the dashboard.

[1468] Step 5: Customize and verify

[1469] Customer Support Representative

[1470] Input: The answer displayed on the dashboard.

[1471] Action: Review the answers and customize them as needed.

[1472] Data processing: Converting data into a format with additional information or corrections.

[1473] Output: A customized final answer.

[1474] Specific actions: The rep adds additional information, such as "The return period is within 30 days of purchase." The customized response is then resubmitted to the server and saved.

[1475] Step 6: Send your response to the customer

[1476] server

[1477] Input: Your customized final answer.

[1478] Processing: Send a response via the method specified by the customer (email, chat, etc.).

[1479] Data processing: Converting customer contact information into a compatible format.

[1480] Output: Sending the final response to the customer.

[1481] Specific operation: The server sends a customized response to the user using the email sending API. The user receives an email with the following response: "Please refer to the link below for the product return procedure. Returns are accepted within 30 days of purchase, and the customer is responsible for the return shipping costs."

[1482] (Application example 1)

[1483] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1484] When responding to customer inquiries, manual response takes time and effort, making it difficult to provide accurate and prompt answers. Furthermore, particularly for online shopping sites, prompt and accurate customer support is required to increase customer satisfaction. Therefore, a system that automatically analyzes the content of inquiries and generates and provides appropriate answers is required.

[1485] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1486] In this invention, the server includes means for receiving inquiries from customers, means for analyzing the received inquiries using a generative AI model, means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results, means for providing the selected or generated answer to a customer support representative, means for the customer support representative to customize and confirm the provided answer, means for sending the final answer to the customer, and means for enhancing customer support functions using a smartphone application to improve the speed and accuracy of inquiry processing, thereby enabling quick and accurate responses to customer inquiries and increasing customer satisfaction.

[1487] The "inquiry receiving means" is a means for receiving inquiries from customers, and transmits the contents of the inquiries to the server through an interface such as a web form or chatbot.

[1488] A "generative AI model" is a model that uses artificial intelligence to analyze and generate natural language, automatically generating appropriate answers based on the content of the inquiry.

[1489] The "analysis means" is a means for analyzing the content of the received inquiry, and performs language identification, keyword extraction, topic classification, and urgency assessment.

[1490] "Answer generation means" refers to a means for selecting an appropriate answer from an FAQ database or knowledge base based on the results obtained by the analysis means, or for generating a new answer using a generative AI model.

[1491] "Answer Providing Means" means a means for providing a selected or generated answer to a customer support representative, and for displaying the answer in real time using a notification system or dashboard.

[1492] "Customization and Verification Means" means a means by which a customer support representative can review the answers provided and add or modify information as needed.

[1493] "Response sending means" refers to the means for sending the final response to the customer, and may be via email, chat, in-app notifications, etc.

[1494] "Smartphone Application" means a software application that operates on a smartphone and is used to receive customer inquiries and generate and provide prompt and accurate responses.

[1495] The present invention is a system for quickly and accurately processing customer inquiries, which uses a server, customer terminals, customer support terminals, and software applications that run on these terminals.

[1496] The server first receives an inquiry from a customer. The customer uses a smartphone application to send the inquiry to the server via a chatbot or inquiry form. The received inquiry is then stored in a database.

[1497] The generative AI model running on the server analyzes the received inquiry. This analysis includes language identification, keyword extraction, topic classification of the inquiry, and urgency assessment. Based on the analysis results, the server searches an FAQ database or knowledge base to select an appropriate answer. If a suitable answer is not found, the generative AI model generates a new answer.

[1498] The generated answer is sent to the customer support representative's device and displayed on their dashboard. The customer support representative reviews the answer and customizes it with additional information as needed. The final customized answer is stored on the server again and sent to the customer. The customer receives the answer through their specified communication channel (email, chat, in-app notification, etc.).

[1499] The system is implemented using the following hardware and software:

[1500] Hardware: Servers (cloud-based or physical), customer smartphones, customer support representative computers

[1501] Software: A web server using the Flask framework, a SQLite or PostgreSQL database, an OpenAI generative model (e.g., GPT-3), and a smartphone application.

[1502] As a concrete example, consider the case where a user sends an inquiry such as "Please tell me the delivery status of my item." The server receives the inquiry and stores it in a database. The generative AI model determines that the inquiry is in Japanese, extracts the keywords "order" and "delivery status," and classifies it as a topic called "delivery." The urgency is assessed as medium. The server searches FAQs related to "delivery," and if no relevant answer is found, the generative AI model generates a new answer. For example, it might say, "You can check the delivery status of your order by clicking this link: <link>."

[1503] An example of a prompt to input to the generative AI model is:

[1504] User's question: "What is the delivery status of my order?"

[1505] Language detection: Japanese

[1506] Keyword extraction: ["order", "shipping status"]

[1507] Topic Category: "Shipping"

[1508] Urgency rating: Medium

[1509] → Generate an answer.

[1510] The system of the present invention enables quick and accurate responses to customer inquiries, thereby increasing customer satisfaction.

[1511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1512] Step 1:

[1513] A user inputs and sends an inquiry via a smartphone application. The inquiry is sent from the application to the server as an HTTP POST request, and the server receives it. The input contains the user's inquiry, and the output is the inquiry that is stored in the inquiry database on the server. Specifically, the user inputs "Please tell me the delivery status of my item" and presses the send button.

[1514] Step 2:

[1515] The server passes the received inquiry content to the generative AI model for analysis. The analysis includes language identification, keyword extraction, topic classification of the inquiry content, and urgency assessment. The input is the received inquiry content, and the output is the results of language, keywords, topic classification, and urgency assessment. Specific operations include generating results such as "Japanese," "Order," "Delivery status," "Delivery," and "Medium urgency."

[1516] Step 3:

[1517] Based on the results of the analysis by the generative AI model, the server searches the FAQ database or knowledge base to select an appropriate answer. If a corresponding answer is not found, the generative AI model generates a new answer. The input is the analysis result, and the output is the selected answer or a new generated answer. Specifically, the searched FAQ selects the answer "You can check the delivery status of your order by clicking this link: <link>".

[1518] Step 4:

[1519] The server notifies the customer support representative's terminal of the selected or generated answer and displays it on the dashboard. The input is the selected or generated answer, and the output is the displayed answer. The specific operation is that the customer support representative's dashboard displays "You can check the delivery status of your order by clicking this link: <link>".

[1520] Step 5:

[1521] The customer support representative reviews the displayed answer and adds or modifies information as needed. The input is the provided answer, and the output is the customized final answer. The specific action is to modify the dashboard to read, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[1522] Step 6:

[1523] The server sends a final response to the customer via the communication channel specified by the user (email, chat, in-app notification, etc.). The input is the customized final response, and the output is the response sent to the customer. The specific behavior is that an email is sent to the customer's email address stating, "You can check the delivery status of your order by clicking this link: <link>. Delivery usually takes 2-3 days."

[1524] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1525] The system of the present invention includes the following main components to enable quick and accurate responses to customer inquiries. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions based on the content of the inquiry and provide a more appropriate response.

[1526] Inquiry Receiving Module

[1527] The server provides a web form and chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1528] Content Analysis Module

[1529] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[1530] Language detection: Automatically identify the language used from the query text.

[1531] Keyword extraction: Identify and extract important words and phrases.

[1532] Topic classification: Categorizing inquiries into specific topics or categories.

[1533] Urgency assessment: Assess the urgency of the inquiry based on its tone and content.

[1534] Emotion Recognition: Analyze and evaluate the user's emotions from the query text. Emotion types include joy, anger, sadness, surprise, etc.

[1535] Answer selection / generation module

[1536] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it automatically generates a new answer using a generative AI model. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1537] Customer Support Delivery Module

[1538] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[1539] Customization and Review Module

[1540] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[1541] Module for sending answers to customers

[1542] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1543] Specific examples

[1544] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1545] 1. The server receives the query and stores it in a database.

[1546] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1547] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1548] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1549] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1550] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[1551] 7. The server sends the final customized answer to the user.

[1552] In this way, the system of the present invention can significantly improve the speed and accuracy of inquiry processing, and can further increase customer satisfaction by taking user emotions into consideration when responding.

[1553] The processing flow will be explained below.

[1554] Step 1:

[1555] The user enters their inquiry into the customer support system interface (web form or chatbot) and presses the send button.

[1556] Step 2:

[1557] The server receives the query as an HTTP POST request and stores it in a database, including metadata such as the query content, timestamp, and user ID.

[1558] Step 3:

[1559] The server adds the query to a queue and passes it as input to the generative AI model.

[1560] Step 4:

[1561] The generative AI model running on the server performs the following analysis:

[1562] Language detection: Identifying the language used from text.

[1563] Keyword extraction: Extracting important words and phrases from text.

[1564] Topical classification: Classifying content into specific categories or topics.

[1565] Urgency assessment: Assess urgency based on wording and content.

[1566] Step 5:

[1567] The emotion engine running on the server analyzes and evaluates the user's emotions from the query text, including joy, anger, sadness, surprise, etc.

[1568] Step 6:

[1569] The server then queries a FAQ database or knowledge base based on the analysis results to find relevant answers.

[1570] Step 7:

[1571] If the server doesn't find a result, it uses a generative AI model to generate a new answer, using multiple neural networks to ensure grammatical accuracy and content appropriateness.

[1572] Step 8:

[1573] The server sends the generated answer and emotion information to the customer support agent's device, notifies the agent using a notification system, and displays the answer and user emotion on a dashboard.

[1574] Step 9:

[1575] The customer support representative reviews the provided response on their device and customizes it as needed, for example, adding "more information about the return process" or "urgent action required."

[1576] Step 10:

[1577] Answers customized on the device are sent back to the server when the save button is pressed, where they are saved and managed again.

[1578] Step 11:

[1579] The server then sends a final confirmation and customized response to the user via email, chat, or other communication method selected by the user.

[1580] Step 12:

[1581] The user receives the response and reviews the information that will help them solve the problem.

[1582] Specific examples

[1583] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1584] 1. The server receives the query and stores it in a database.

[1585] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1586] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1587] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1588] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1589] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble, and we'll get back to you as soon as possible. Returns are accepted within 30 days of purchase."

[1590] 7. The server sends the final customized answer to the user.

[1591] Example 2

[1592] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1593] Responding quickly and accurately to customer inquiries is important for improving customer satisfaction. However, mechanical responses that ignore customer emotions can make it difficult to resolve customer dissatisfaction and may result in delayed appropriate responses. To improve this situation, it is necessary not only to analyze the content of inquiries, but also to recognize and respond to customer emotions.

[1594] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1595] In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; means including an emotion engine for recognizing the customer's emotion from the content of the inquiry; and means for providing the emotion information recognized by the emotion engine to the customer support representative. This makes it possible to recognize the customer's emotion while analyzing the content of the inquiry, and to provide an optimal response based on that.

[1596] "Means for receiving inquiries from customers" refers to the interface and protocol for sending the inquiry content entered by customers through a web form or chatbot to a server and receiving it.

[1597] "Means of analysis using a generative AI model" refers to the process of using machine learning and natural language processing techniques to analyze the text data of received inquiries and automatically determine the language, keywords, topics, etc.

[1598] "Means for selecting or generating from an FAQ database or knowledge base" refers to a process for searching an existing FAQ database or knowledge base based on the results of the analysis and selecting appropriate answers or generating new answers as needed.

[1599] "Means provided to customer support representative" refers to a system for transmitting the selected or generated answer to the representative's device and making it visible through notifications and dashboards.

[1600] "Means for customization and review" means the interface and functionality that allows a customer support representative to review the responses provided and make corrections or add additional information as needed.

[1601] "Means for sending the final response to the customer" refers to the mechanism by which the final response that the agent has confirmed and customized is sent to the customer via a communication channel such as an email address or chat system specified by the customer.

[1602] "Means including an emotion engine" refers to software and algorithms for analyzing customer emotions from received inquiries using natural language processing and providing the results in a format that can be used by the system.

[1603] The present invention is a system for responding to customer inquiries quickly and accurately, and includes the following main components: In particular, it incorporates an emotion engine that recognizes customer emotions based on the content of the inquiry, enabling more appropriate responses.

[1604] Inquiry Receiving Module

[1605] The server provides a web form or chatbot as an interface for receiving inquiries from customers. When a customer enters and submits an inquiry, the content is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1606] Content Analysis Module

[1607] The server passes the received query content to the generative AI model and emotion engine, and performs the following analysis:

[1608] Language detection: Automatically identify the language used from the query text.

[1609] Keyword extraction: Identify and extract important words and phrases.

[1610] Topic classification: Categorizing inquiries into specific topics or categories.

[1611] Urgency assessment: Assess the urgency based on the tone and content of the inquiry.

[1612] Emotion Recognition: Analyze and evaluate the user's emotions from the query text.

[1613] Answer selection / generation module

[1614] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This process uses a multi-layer neural network to provide accurate grammar and appropriate response content.

[1615] Customer Support Delivery Module

[1616] The server sends the selected or generated answer to the customer support representative's device in real time. The representative is notified by a notification system and the answer is displayed on a dashboard. In addition, emotion information from the emotion engine is also provided to the representative, allowing them to respond based on the user's emotions.

[1617] Customization and Review Module

[1618] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding "detailed information about the return procedure." Once the representative has customized the response, it is sent back to the server and saved.

[1619] Module for sending answers to customers

[1620] The server then sends a final confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1621] Examples of concrete examples and prompts

[1622] For example, a case will be described in which a user sends an inquiry saying, "Please tell me how to return a product. I would like you to deal with this as soon as possible. I am in a really difficult situation."

[1623] Specific examples

[1624] 1. The server receives the query and stores it in a database.

[1625] 2. The generative AI model running on the server determines that the inquiry is in Japanese and extracts the keyword "return." The urgency is assessed as high.

[1626] 3. The emotion engine determines the user's emotion as "sadness" based on the expression "troubled."

[1627] 4. The server searches the database for FAQs related to "returns." If no relevant FAQ is found, the generative AI model generates an answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1628] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1629] 6. The customer support representative reviews the response and adds additional information, such as, "We understand you're having trouble and will get back to you as soon as possible."

[1630] 7. The server sends the final customized answer to the user.

[1631] Prompt Sentence Examples

[1632] User query:

[1633] "Please tell me how to return the product. I would like this to be resolved quickly. I am in a very difficult situation."

[1634] Prompt for generative AI model:

[1635] "Generate an appropriate response to the following inquiry: 'Please tell me how to return an item. I'm really struggling and would appreciate a speedy response.' In your response, please include information about the process for returning an item."

[1636] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1637] Step 1: Receiving an inquiry

[1638] The server receives inquiries submitted by customers through web forms or chatbots as HTTP POST requests.

[1639] Input: Inquiry data sent by the customer (e.g., question about returning a product)

[1640] Data processing / calculation: Converting received data into a structured format (such as JSON or XML)

[1641] Output: A structured representation of the form data

[1642] Step 2: Save the received data

[1643] The server stores the structured query data in a database, and validates the format and content of the received data to ensure there are no errors.

[1644] Input: Structured inquiry data

[1645] Data processing / calculation: Insertion into database

[1646] Output: Query record stored in the database

[1647] Step 3: Language detection

[1648] The server sends the text data of the received query to a generative AI model, which automatically identifies the language used.

[1649] Input: Text data of the query

[1650] Data processing / computation: Language recognition using generative AI models

[1651] Output: Language (e.g. Japanese)

[1652] Step 4: Keyword extraction

[1653] After language determination is complete, the server runs the text data through a natural language processing algorithm to extract important keywords and phrases.

[1654] Input: Language-determined text data

[1655] Data processing / calculation: Applying keyword extraction algorithms

[1656] Output: Extracted keywords (e.g. "returns")

[1657] Step 5: Create a topic classification

[1658] The server categorizes the query into specific topics and categories based on the extracted keywords.

[1659] Input: Extracted keywords

[1660] Data processing / computation: Topic classification using generative AI models

[1661] Output: Categorized topics (e.g., "Return Procedure")

[1662] Step 6: Conduct an emergency assessment

[1663] The server analyzes the text and tone of the inquiry and assesses its urgency.

[1664] Input: relevant text data and key expressions

[1665] Data processing / computation: Using generative AI models and other algorithms to assess urgency

[1666] Output: Urgency rating (e.g., high urgency)

[1667] Step 7: Emotion Recognition

[1668] The server uses an emotion engine to recognize and evaluate customer emotions.

[1669] Input: Text data of the query

[1670] Data processing / calculation: Emotion analysis using emotion engine

[1671] Output: Recognized emotion (e.g. "sadness")

[1672] Step 8: Query the FAQ database

[1673] Based on the analysis results, the server searches for relevant answers from an FAQ database or knowledge base.

[1674] Input: Keywords and topic classification results

[1675] Data processing / calculation: Database query

[1676] Output: The searched answer (e.g., "Here's how to return the item...")

[1677] Step 9: Generate new answers as needed

[1678] If the server cannot find a suitable answer from the FAQ, it uses a generative AI model to generate a new answer.

[1679] Input: Re-enter data when query results are insufficient

[1680] Data processing / calculation: Answer generation using generative AI models

[1681] Output: The generated answer (e.g., "Please see the link below for return instructions...")

[1682] Step 10: Send your answers and sentiment information

[1683] The server then sends the generated answers and sentiment information to the customer support agent's device, where they are displayed on a dashboard and an alert is sent to the agent via a notification system.

[1684] Input: Generated answers and sentiment information

[1685] Data processing / calculation: Notifications and dashboard display

[1686] Output: Answers and emotion information displayed on the device

[1687] Step 11: Customer support representative customizes response

[1688] A customer support representative will review the response provided and make corrections or add additional information as necessary.

[1689] Input: Answers displayed on the dashboard

[1690] Data manipulation / calculation: customizing and modifying answers

[1691] Output: Customized answer

[1692] Step 12: Send the final response to the customer

[1693] The server then sends the final customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1694] Input: Customized Answer

[1695] Data processing / calculation: Sending answers

[1696] Output: Final response sent to customer

[1697] (Application example 2)

[1698] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1699] While there is an increasing demand for quick and accurate responses to customer inquiries, conventional systems have had the problem of taking time to analyze the content of inquiries and selecting appropriate responses, making it difficult to provide satisfactory customer service. Furthermore, they were unable to respond in a way that took into account the customer's emotions, which could result in a decline in customer satisfaction. It is known that delays in response have a significant negative impact on the customer experience, especially for urgent or emotional inquiries.

[1700] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving an inquiry from a customer; means for analyzing the content of the received inquiry using a generative AI model; means for selecting or generating an appropriate answer from an FAQ database or knowledge base based on the analysis results; means for providing the selected or generated answer to a customer support representative; means for the customer support representative to customize and confirm the provided answer; means for sending the final answer to the customer; and means for responding based on the user's emotions by combining an emotion engine that recognizes the user's emotions based on the content of the inquiry. This eliminates the conventional issues of delays in responding to inquiries and the difficulty of responding while taking customer emotions into consideration, making it possible to improve customer satisfaction.

[1701] "Customer inquiries" refer to questions, requests, and opinions that customers make to a company or store in relation to the purchase of a product or the use of a service.

[1702] "Means for receiving" refers to the interface or process for inputting customer inquiry information into the server.

[1703] A "generative AI model" is an algorithm or software that learns from large amounts of data, uses natural language processing to understand inquiries and sentences, and automatically generates and analyzes them.

[1704] "Means of analysis" refers to the process of analyzing the content of the received inquiry and determining the language of the information, extracting keywords, classifying topics, assessing urgency, recognizing emotions, etc.

[1705] An "FAQ database" is a database that organizes and stores frequently asked questions and their answers collected in the past.

[1706] A "knowledge base" is a collection of information that aggregates and organizes knowledge about a particular topic or field and stores it in a searchable and usable format.

[1707] A "customer support representative" is a specialized staff member or operator who responds appropriately to customer inquiries.

[1708] "Means for providing" refers to a method or system for displaying or notifying a selected or generated answer to a customer support representative.

[1709] "Means for customization and verification" means the processes and tools that allow a customer support representative to modify or add to the provided response as needed and verify its content.

[1710] "Final Response" means the final response sent to Customer after customization and review.

[1711] An "emotion engine" is an algorithm or software that automatically analyzes user emotions from text data and outputs the results as numbers or tags.

[1712] "User emotion" refers to a psychological state such as joy, sadness, anger, or surprise that can be inferred from words and expressions contained in the query text.

[1713] "Response based on user emotions" refers to the process or means of responding to customers in an appropriate manner, taking into account the emotions recognized by the emotion engine.

[1714] The present invention is a system for responding quickly and accurately to customer inquiries, and includes the following main components: The roles of the server, terminal, and user, and the specific processes are as follows:

[1715] System Program

[1716] The server provides an interface for receiving customer inquiries, either through a web form or a chatbot. When a customer enters and submits an inquiry, it is sent to the server as an HTTP POST request. The server stores the received data in a database.

[1717] The server then passes the received query content to a generative AI model for language determination, keyword extraction, topic classification, urgency assessment, and sentiment recognition. This process uses natural language processing (NLP) techniques, such as generative AI models like GPT-3 and BERT, or sentiment engines like Google Cloud Natural Language API and IBM Watson Tone Analyzer.

[1718] The server then queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the search results are insufficient, it uses a generative AI model to automatically generate a new answer. This generation process uses a multi-layer neural network to ensure accurate grammar and appropriate response content.

[1719] The server then sends the selected or generated answer to the customer support agent's device in real time. The agent is notified via a notification system and the answer is displayed on a dashboard. Emotion information from the emotion engine is also provided to the agent, allowing them to respond based on the user's emotions.

[1720] The customer support representative can review the response displayed on their device and customize it as needed. For example, they can add "detailed information about the return process." Once the representative has customized the response, it is sent back to the server and saved.

[1721] Finally, the server sends a confirmation and customized response to the customer via email, chat, or any other communication channel specified by the customer.

[1722] Specific examples

[1723] For example, a user may send an inquiry saying, "Please tell me how to return a product. I would like this dealt with quickly; I am in a really difficult situation."

[1724] 1. The server receives the query and stores it in a database.

[1725] 2. The generative AI model running on the server determines that the language of the inquiry is Japanese and extracts the keyword "return." The urgency is evaluated as high.

[1726] 3. The emotion engine evaluates the user's emotion as sadness based on the expression "I'm in trouble."

[1727] 4. The server searches the database for FAQs related to "returns," but if no relevant FAQ is found, the generative AI model generates a new answer such as, "For product return procedures, please refer to the link below. Return shipping fees are the customer's responsibility."

[1728] 5. The server sends the response and emotional information to the customer support representative's device and displays it on a dashboard.

[1729] 6. The customer support representative reviews the response and, based on the emotional information, adds additional information such as, "We understand you are having trouble, and we will assist you as soon as possible. Returns are accepted within 30 days of purchase."

[1730] 7. The server sends the final customized answer to the user.

[1731] Prompt Sentence Examples

[1732] "A user has submitted an inquiry saying, 'Please tell me how to return an item. I really need help, I want this resolved quickly.' Please generate an example response to this."

[1733] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1734] Step 1:

[1735] The server receives inquiries from customers. Specifically, when a customer enters and submits an inquiry through a web form or chatbot, the content is sent to the server as an HTTP POST request. The server that receives this request stores the inquiry data in a database.

[1736] Input: Your query as an HTTP POST request.

[1737] Output: Query data stored in a database.

[1738] Step 2:

[1739] The server passes the received query content to a generative AI model and performs content analysis. This involves language determination, keyword extraction, topic classification, urgency assessment, and emotion recognition. Specifically, the server analyzes the text data using a generative AI model (e.g., GPT-3 or BERT) and an emotion engine (e.g., Google Cloud Natural Language API, IBM Watson Tone Analyzer).

[1740] Input: Query data stored in the database.

[1741] Output: Language, keyword, topic, urgency, and sentiment analysis results.

[1742] Step 3:

[1743] The server queries the FAQ database or knowledge base based on the analysis results to find relevant answers. If the corresponding answer cannot be found in the database, a new answer is automatically generated using a generative AI model. The model generates an appropriate answer based on the large amount of data learned during training.

[1744] Input: Analysis results (language, keywords, topic, urgency, sentiment).

[1745] Output: Search results from the FAQ database or generated answers.

[1746] Step 4:

[1747] The server sends the selected or generated answer and sentiment information to the customer support agent's device in real time, notifying the agent via a notification system (e.g., Firebase Cloud Messaging), and displaying the answer on a dashboard.

[1748] Input: Search results or generated answers, sentiment information.

[1749] Output: Answers and sentiment information displayed on the customer support representative's device.

[1750] Step 5:

[1751] The customer support representative can review the response displayed on their device and customize it as needed, for example by adding appropriate details or supplementary explanations. Once the representative has customized the response, it is sent back to the server and stored.

[1752] Input: Answers and sentiment information displayed on the dashboard.

[1753] Output: A customized final answer.

[1754] Step 6:

[1755] The server sends a final, customized response to the customer, using email, chat, or other communication channel specified by the customer.

[1756] Input: Your customized final answer.

[1757] Output: The final response sent to the customer.

[1758] In this way, the system automates and streamlines the process of receiving an inquiry, analyzing it, providing an appropriate response, and then having the agent customize and send the final response to the customer.

[1759] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1760] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1761] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1762] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1763] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1764] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1765] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1766] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1767] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1768] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1769] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1770] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1771] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1772] 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.

[1773] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1774] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1775] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1776] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1777] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1778] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1779] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1780] The following is further disclosed regarding the above embodiment.

[1781] (Claim 1)

[1782] a means for receiving customer inquiries;

[1783] A means for analyzing the received inquiry content using a generative AI model;

[1784] a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results;

[1785] a means for providing the selected or generated answer to a customer support representative;

[1786] A means for customer support representatives to customize and review the answers provided;

[1787] a means of sending the final response to the customer;

[1788] A system including:

[1789] (Claim 2)

[1790] 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query.

[1791] (Claim 3)

[1792] 10. The system of claim 1, further comprising means for notifying a customer support representative of the generated answer and displaying the answer on a dashboard.

[1793] "Example 1"

[1794] (Claim 1)

[1795] a means for receiving customer inquiries;

[1796] A means for analyzing the received inquiry content using a generative AI model;

[1797] a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results;

[1798] a means for notifying the customer support representative of the selected or generated answer and displaying the answer on a dashboard;

[1799] A means for customer support representatives to customize and review the answers provided;

[1800] a means of sending the final response to the customer;

[1801] A system including:

[1802] (Claim 2)

[1803] 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query.

[1804] (Claim 3)

[1805] 10. The system of claim 1, further comprising a notification system for transmitting the generated answer to a terminal of a customer support representative.

[1806] "Application Example 1"

[1807] (Claim 1)

[1808] a means for receiving customer inquiries;

[1809] A means for analyzing the received inquiry content using a generative AI model;

[1810] a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results;

[1811] a means for providing the selected or generated answer to a customer support representative;

[1812] A means for customer support representatives to customize and review the answers provided;

[1813] a means of sending the final response to the customer;

[1814] A means of enhancing customer support capabilities using a smartphone application to improve the speed and accuracy of inquiry processing;

[1815] A system including:

[1816] (Claim 2)

[1817] 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query.

[1818] (Claim 3)

[1819] 10. The system of claim 1, further comprising means for notifying a customer support representative of the generated answer and displaying the answer on a dashboard.

[1820] "Example 2: Combining Emotion Engines"

[1821] (Claim 1)

[1822] a means for receiving customer inquiries;

[1823] A means for analyzing the received inquiry content using a generative AI model;

[1824] a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results;

[1825] a means for providing the selected or generated answer to a customer support representative;

[1826] A means for customer support representatives to customize and review the answers provided;

[1827] a means of sending the final response to the customer;

[1828] a means including an emotion engine for recognizing customer emotions from the content of an inquiry;

[1829] a means for providing the emotion information recognized by the emotion engine to a customer support representative;

[1830] A system including:

[1831] (Claim 2)

[1832] 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query.

[1833] (Claim 3)

[1834] 10. The system of claim 1, further comprising means for notifying a customer support representative of the generated answer and displaying the answer on a dashboard.

[1835] "Application example 2 when combining emotion engines"

[1836] (Claim 1)

[1837] a means for receiving customer inquiries;

[1838] A means for analyzing the received inquiry content using a generative AI model;

[1839] a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results;

[1840] a means for providing the selected or generated answer to a customer support representative;

[1841] A means for customer support representatives to customize and review the answers provided;

[1842] a means of sending the final response to the customer;

[1843] A means for responding based on the user's emotions by combining with an emotion engine that recognizes the user's emotions based on the content of the inquiry;

[1844] A system including:

[1845] (Claim 2)

[1846] 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query, and further identifies and evaluates sentiment.

[1847] (Claim 3)

[1848] 10. The system of claim 1, further comprising means for notifying and displaying the generated answer to the customer support representative on a dashboard, and also providing sentiment information. [Explanation of symbols]

[1849] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for receiving customer inquiries; A means for analyzing the received inquiry content using a generative AI model; a means for selecting or generating appropriate answers from a FAQ database or knowledge base based on the analysis results; a means for providing the selected or generated answer to a customer support representative; A means for customer support representatives to customize and review the answers provided; a means of sending the final response to the customer; A system including:

2. 10. The system of claim 1, wherein the analysis means evaluates the language, keywords, topic, and urgency of the query.

3. 10. The system of claim 1, further comprising means for notifying a customer support representative of the generated answer and displaying the answer on a dashboard.

Images