system

Abstract

We provide the system. [Solution] A means for the user to input the content of the inquiry, A means by which the server receives the query content and stores the query content in the database, A means by which the server sends the query content to a generation-based AI API, A method for generating an optimal response by using a generative AI to analyze the content of an inquiry, A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface, A system that includes a means for users to receive responses.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional inquiry window, the speed and consistency of response quality in handling inquiries have been major issues. Specifically, responses by human resources are likely to vary depending on the skills and knowledge of the staff, and the time loss in response may have an adverse impact on customer satisfaction. Furthermore, due to insufficient management and analysis of the history of inquiry contents, it is difficult to improve services efficiently. The present invention aims to solve these problems and achieve a quick and consistent high-quality response to inquiries.

Means for Solving the Problems

[0005] This invention relates to a system that includes means for a user to input an inquiry, means for a server to receive the inquiry and store it in a database, means for the server to send the inquiry to a generative AI API, means for the generative AI to analyze the inquiry and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer, and send it to the user interface, and means for the user to receive the answer. This improves the speed and quality of inquiry handling and eliminates variations among staff members. Furthermore, by providing means for storing the inquiry content and generated answers in a database and managing the inquiry history, the system aims to improve efficient service and enhance customer satisfaction.

[0006] A "user" refers to an individual or legal entity that makes an inquiry using the system.

[0007] "Inquiry content" refers to the questions and requests that users enter into the system when seeking support.

[0008] A "server" refers to a computer system that receives inquiries, manages databases, and communicates with generative AI systems.

[0009] A "database" refers to a digital storage system used to store and manage query content and the corresponding responses.

[0010] "Generative AI" refers to an artificial intelligence system that analyzes received inquiries and generates the optimal response using natural language processing technology.

[0011] A "generative AI API" refers to an application programming interface that allows a server to communicate with a generative AI.

[0012] A "user interface (UI)" refers to the interface, such as screens or forms, that users use to input inquiries and receive responses.

[0013] "Formatting" refers to the process of shaping data into a specific format.

[0014] "Inquiry history" refers to the record of past inquiries and the responses stored in the database. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[0037] System Overview

[0038] This system mainly consists of the following components:

[0039] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0040] 2. Server: Receives the query content and communicates with the database and generative AI.

[0041] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0042] 4. Database: Stores and manages inquiry content and its responses.

[0043] Program processing

[0044] Inquiry reception

[0045] Users enter their inquiries via chatbots or email forms. For example, a user might type, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[0046] Receiving and saving inquiry details

[0047] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and inquiry timestamp are recorded. This allows the entire inquiry history to be tracked.

[0048] Sending to a generative AI

[0049] The server formats the received query and sends it to the generative AI API. The generative AI API analyzes the query data sent from the server and performs natural language processing to understand the intent of the query.

[0050] Answer generation

[0051] The generative AI analyzes the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days." This response is sent back to the server in real time.

[0052] Receiving and formatting responses

[0053] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[0054] Submit and display of responses

[0055] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days."

[0056] Specific example

[0057] Case 1: Inquiry via chat

[0058] 1. User enters inquiry: User: "Please explain the return process."

[0059] 2. Server receives and saves query: The query content is saved to the database.

[0060] 3. Analysis of the inquiry: Generative AI analyzes "Please tell me about the return process."

[0061] 4. Response generation: The generation AI generates "For information on the return process, please read the following steps..."

[0062] 5. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0063] 6. The user receives the response: The chatbot displays the response to the user.

[0064] Case 2: Inquiry via email

[0065] 1. User enters inquiry: User: "How do I place an additional order?"

[0066] 2. Server receives and saves query: The query content is saved to the database.

[0067] 3. Analysis of the inquiry: The generative AI analyzes the inquiry "How do I place an additional order?"

[0068] 4. Response generation: The generation AI generates the message, "For instructions on how to place an additional order, please proceed through your My Page on the online store."

[0069] 5. Formatting and sending responses: The server formats the responses and sends them to the email system.

[0070] 6. The user receives the response: The email client displays the response to the user.

[0071] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and responses in a database, it can also be used for future service improvements.

[0072] The following describes the processing flow.

[0073] Step 1:

[0074] The user enters their inquiry.

[0075] Users enter their inquiries into the chatbot or email form on their device. For example, they might type, "What is the delivery date for the product?"

[0076] Step 2:

[0077] The server receives the query and saves it to the database.

[0078] The server receives query data from the user interface.

[0079] The server saves the received query data to a database. The query ID, user ID, timestamp, and query content are recorded.

[0080] Step 3:

[0081] The server prepares to send the query content to the generative AI API.

[0082] The server formats the query content into a format that the generative AI API can understand (for example, JSON format).

[0083] Step 4:

[0084] The server sends the query content to the generative AI API.

[0085] The server sends the formatted query data to the endpoint of the generative AI API.

[0086] Step 5:

[0087] A generative AI analyzes the content of the inquiry.

[0088] Generative AI analyzes received data to extract the intent and keywords of inquiries. For example, generative AI might extract information related to "product delivery dates."

[0089] Step 6:

[0090] The generative AI generates the optimal answer.

[0091] Generative AI generates the optimal answer based on the analysis results. For example, it might generate the answer, "The delivery time for products is usually 3 to 5 business days."

[0092] Step 7:

[0093] The server receives the response generated by the generative AI.

[0094] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[0095] Step 8:

[0096] The server formats the received response for the user interface.

[0097] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[0098] Step 9:

[0099] The server sends the formatted response to the user interface.

[0100] The server sends the formatted response to the chatbot or email system.

[0101] Step 10:

[0102] The user receives the response on their device.

[0103] The response will be displayed on the chatbot screen or email client on the user's device. For example, it might say, "The delivery time for products is usually 3-5 business days."

[0104] In this way, the system ensures that the entire process, from the user submitting an inquiry to receiving a response, is carried out quickly and efficiently.

[0105] (Example 1)

[0106] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] Traditional inquiry handling systems often resulted in long waiting times between user inquiry submission and response, and sometimes generated inconsistent answers. Furthermore, inadequate management of inquiry history prevented the effective utilization of past inquiry information. This led to decreased user satisfaction and hindered the efficiency of corporate response processes.

[0108] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0109] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer, and send it to the user interface, means for the user to receive the answer, means for the inquiry content to be sent to the server in real time, means for the server to store the inquiry ID, user ID, and timestamp for the received inquiry content in a database, means for the server to convert the JSON format data to HTML or plain text after receiving the answer from the generative AI, means for the server to send the formatted answer to the user interface in real time, and means for displaying the formatted answer on the user's terminal. This enables a rapid and consistent response to inquiries, improving user satisfaction and the efficiency of corporate responses.

[0110] A "user" refers to an individual or organization that uses the system to make an inquiry.

[0111] "Inquiry details" refers to information including questions and requests entered by the user into the system.

[0112] A "server" refers to a computer system that receives and processes inquiries.

[0113] A "database" refers to a collection of digital information used to store and manage inquiries and the responses to them.

[0114] "Generative AI" refers to an artificial intelligence system that analyzes user inquiries and generates appropriate responses.

[0115] An "API" refers to an interface for exchanging data between a server and a generative AI.

[0116] "Formatting" refers to the process of converting data or information into a specific format.

[0117] "User interface" refers to the screen or form on which a user makes an inquiry and receives a response.

[0118] A "timestamp" refers to information indicating the date and time the inquiry was made.

[0119] "Real-time" refers to a state where user actions and inquiries are responded to immediately.

[0120] "JSON format" is a type of data exchange format, and is an abbreviation for JavaScript® Object Notation.

[0121] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[0122] System Overview

[0123] This system mainly consists of the following components:

[0124] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0125] 2. Server: Receives the query content and communicates with the database and generative AI.

[0126] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0127] 4. Database: Stores and manages inquiry content and its responses.

[0128] Program processing

[0129] The program processes the information as follows: First, the user enters their inquiry via a chatbot or email form. For example, the user might enter, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[0130] The server saves the received query content to a database. The information saved includes the query ID, user ID, and query timestamp. This makes it possible to track the entire query history. Next, the server formats the received query content and sends it to the generative AI API.

[0131] The generative AI API analyzes inquiry data sent from the server and performs natural language processing to understand the intent of the inquiry. The generative AI analyzes the content of the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3 to 5 business days." This response is sent back to the server in real time.

[0132] The server receives responses from the generative AI and formats them for the user interface. For example, it converts JSON data to HTML or plain text. The formatted response is sent from the server to the user interface, and the user's device displays a message such as "Product delivery time is usually 3-5 business days" on the chatbot screen or in their email client.

[0133] Specific example

[0134] Case 1: Inquiry via chat

[0135] 1. User enters inquiry: The user enters "Please explain the return process."

[0136] 2. Server receives and saves query: The server saves the query content to the database.

[0137] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[0138] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to "Please tell me about the return process" (e.g., "For information on the return process, please read the following steps...").

[0139] 5. Server receives and formats the generated response: The server receives the response from the generation AI and formats it in HTML format.

[0140] 6. Server sends response to terminal, user receives: The server sends the formatted response to the chatbot's UI, which is then displayed to the user on the chatbot screen.

[0141] Case 2: Inquiry via email

[0142] 1. User enters inquiry: The user enters "Please tell me how to place an additional order" into the email form.

[0143] 2. Server receives and saves query: The server saves the query content to the database.

[0144] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[0145] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to the question "How do I place an additional order?" (Example: "To place an additional order, please proceed through your My Page on the online store.").

[0146] 5. Server receives and formats the generated response: The server receives the response from the generative AI and formats it in plain text format.

[0147] 6. Server sends response to terminal, user receives: The server sends the formatted response to the email system, and the user's email client displays a message saying, "For instructions on how to place an additional order, please proceed from your online store's My Page."

[0148] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and their responses in a database, it can also be used for future service improvements. This system makes it possible to improve user satisfaction and increase the operational efficiency of companies.

[0149] Example of a prompt

[0150] "When is the product due?"

[0151] "Please tell me about the return process."

[0152] "Please tell me how to place an additional order."

[0153] By entering these prompts, the generative AI will provide the corresponding answer.

[0154] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0155] Step 1:

[0156] The user enters an inquiry.

[0157] The user enters their inquiry using a terminal. For example, the user might enter, "What is the delivery date for the product?" This becomes the input data. The terminal then sends the entered inquiry to the server in real time.

[0158] Step 2:

[0159] The server receives the query.

[0160] The server receives user inquiries in real time. This received data becomes the input data. The server first saves the received inquiry content to a database. When saving, it also records additional information such as the inquiry ID, user ID, and timestamp. This makes it possible to track the inquiry history.

[0161] Step 3:

[0162] The server formats the query content.

[0163] The server retrieves query data stored in the database and converts it into the format necessary for sending it to the generative AI. This format conversion is data processing. For example, the query data is converted into JSON format. The converted JSON data becomes the output data.

[0164] Step 4:

[0165] The server sends the formatted query content to the generation AI API.

[0166] The server sends formatted JSON data to the generative AI API. This becomes the input data. The server performs error checking and data integrity verification during transmission. Once the generative AI receives the data, it begins analyzing the query.

[0167] Step 5:

[0168] The generative AI analyzes the inquiry and generates a response.

[0169] The generative AI analyzes the JSON-formatted query received from the server. This analysis is data processing. The generative AI uses natural language processing techniques to understand the intent of the query and generate an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3-5 business days." This generated response becomes the output data.

[0170] Step 6:

[0171] The server receives the response from the generative AI.

[0172] The server receives the response generated by the generative AI. The received response data in JSON format becomes the input data. The server then performs a verification process on the received data for comparison.

[0173] Step 7:

[0174] The server formats the generated response.

[0175] The server formats the received JSON response for the user interface. Specifically, it converts the JSON data into HTML or plain text. This format conversion is data processing. The converted data becomes the output data.

[0176] Step 8:

[0177] The server sends the formatted response to the user interface.

[0178] The server sends the formatted response data to the user's terminal. The converted data is sent as input data. The server checks the data integrity and confirms delivery upon transmission.

[0179] Step 9:

[0180] The answer will be displayed on the user's device.

[0181] The user's device receives a formatted response sent from the server. This received data becomes the input data. The device then displays the received data appropriately. For example, it might display "Product delivery time is usually 3-5 business days" on the chatbot screen or in the email client.

[0182] Through these steps, users' inquiries will be answered quickly and appropriately.

[0183] (Application Example 1)

[0184] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0185] Electronic payment services require prompt and accurate responses to user inquiries. However, traditional systems often resulted in inconsistent quality in inquiry handling, frequently lowering user satisfaction. Furthermore, there was a lack of efficient methods for managing inquiry content and response history. As a result, inquiry handling took a significant amount of time, negatively impacting user convenience.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0187] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to a user interface, means for the user to receive the answer, means for handling inquiries using an application installed on a smartphone, smart glasses, head-mounted display, or robot, and means for processing inquiries related to electronic payment services. This makes it possible to improve the quality of inquiry handling and enhance user convenience.

[0188] A "server" is a computer system that receives user inquiries, stores them in a database, and sends them to a generative AI API.

[0189] A "user interface" is a means of providing a screen or form for a user to input their inquiry and receive a generated response.

[0190] "Generative AI" refers to artificial intelligence that analyzes inquiries and generates the most appropriate response.

[0191] A "generative AI API" is an application programming interface for sending and receiving query data between a server and a generative AI.

[0192] A "database" is a system for storing and managing query content and generated responses.

[0193] A "smartphone" is a portable computer device used to input inquiries and receive generated responses.

[0194] "Smart glasses" are wearable devices used by users to input inquiries and receive generated responses.

[0195] A "head-mounted display" is a display device worn by the user, used for inputting inquiries and receiving generated responses.

[0196] A "robot" is an automated machine programmed to handle inquiries.

[0197] An "electronic payment service" is a system that allows users to pay electronically for goods and services they purchase online or in physical stores.

[0198] "Inquiry history" refers to a record of user inquiries and the corresponding responses.

[0199] The system for implementing this invention automates the reception, analysis, and response generation of inquiries, thereby improving the efficiency of handling inquiries related to electronic payment services. Specifically, it uses the following hardware and software.

[0200] System Overview

[0201] hardware

[0202] 1. Server: A high-performance computer server receives user inquiries and sends data to the generative AI. It also stores the inquiry content and its response in a database.

[0203] 2. User terminal: This refers to devices such as smartphones, smart glasses, head-mounted displays, and robots. These are used by users to input inquiries and display generated responses.

[0204] software

[0205] 1. User Interface (UI): The screen or form on which a user enters an inquiry and receives a generated response. Frameworks such as React Native or Flutter® are used.

[0206] 2. Server Application: Built using Node.js and Express. It receives, stores, and sends query data to the generation AI, formats the generated responses, and sends them to the user's terminal.

[0207] 3. Generative AI: Using a generative AI model (e.g., GPT-4®), the system analyzes the inquiry content and generates an appropriate response.

[0208] 4. Database: A relational database such as MySQL (registered trademark) is used to manage queries and their responses.

[0209] Program processing

[0210] Receiving and saving inquiries

[0211] The user enters their inquiry through a smartphone application. For example, an inquiry such as, "What should I do about a canceled payment?" The server receives this inquiry and saves it to a database. The inquiry ID, user ID, and timestamp are recorded.

[0212] Sending to a generative AI

[0213] The server sends the received query to a generative AI API. The generative AI analyzes the query and uses natural language processing techniques to understand its intent. It then generates an appropriate response.

[0214] Answer generation and formatting

[0215] The generative AI generates a response such as, "For canceled payments, please follow these instructions..." This response is sent back to the server in real time. The server formats the received response for display to the user. For example, it converts JSON data into plain text.

[0216] Submit and display of responses

[0217] The formatted response is sent from the server to the user interface. The user's device, such as a smartphone or smart glasses screen, displays a response such as, "For canceled payments, please follow these instructions."

[0218] Specific example

[0219] Example 1: Inquiry

[0220] The user typed "What should I do about the canceled payment?" into the smartphone app.

[0221] The server receives the data and saves it to the database.

[0222] Send to a generative AI API.

[0223] The generative AI analyzes the data and generates a response saying, "For canceled payments, please follow these instructions."

[0224] The server formats the file and sends it to the user's terminal.

[0225] The user checks their answer on their smartphone.

[0226] Example of a prompt

[0227] "This is an inquiry regarding electronic payment cancellations. A user has asked about the payment cancellation process. Please provide an appropriate answer."

[0228] "A user is inquiring about a failed payment method. Please generate specific instructions."

[0229] By implementing this invention, the efficiency and quality of handling inquiries are improved, and user convenience is significantly enhanced.

[0230] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0231] Step 1:

[0232] The user enters their inquiry using a device (e.g., a smartphone). For example, they might enter an inquiry such as "What should I do about a canceled payment?" into the application screen. This input is sent to the server in real time through the UI component.

[0233] Step 2:

[0234] The server receives the query content sent from the terminal. The received content is stored in the database. Metadata such as the query ID, user ID, and timestamp is also stored here. The input is the query content, and the output is the record stored in the database.

[0235] Step 3:

[0236] The server formats the received query and sends it to the generative AI API. For example, it prepares the query as JSON data and sends a request to the API endpoint. The input is the formatted query, and the output is the request to the generative AI.

[0237] Step 4:

[0238] The generative AI analyzes the inquiry content and performs natural language processing to understand its intent. It then generates an appropriate response. For example, it might generate the prompt "For canceled payments, please follow these steps." The input is the received inquiry, and the output is the generated response.

[0239] Step 5:

[0240] The server receives the responses generated by the generative AI. The server then formats the received responses for the user interface. For example, it might convert JSON data to plain text. The input is the generated response, and the output is the formatted response.

[0241] Step 6:

[0242] The server sends a formatted response to the user interface. It converts the response to a format that can be displayed on the application's chat screen and sends it to the user's device. The input is the formatted response, and the output is the display of the response on the user's device.

[0243] Step 7:

[0244] The user's device displays the response received from the server. The user sees a specific response on their smartphone screen, such as "For canceled payments, please follow these instructions." The input is the formatted response received from the server, and the output is the display on the user's screen.

[0245] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0246] This invention relates to a system that achieves more accurate responses by combining a system that uses generative AI to streamline customer service responses with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0247] System Overview

[0248] This system mainly consists of the following components:

[0249] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0250] 2. Server: Receives the query content and communicates with the database and generative AI.

[0251] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0252] 4. Emotion Engine: Analyzes user emotions from the content of their inquiries and the writing style used during input.

[0253] 5. Database: Stores and manages inquiry content, responses, and sentiment analysis results.

[0254] Program processing

[0255] Inquiry reception

[0256] Users enter their inquiries via chatbots or email forms. For example, a user might type, "When is the delivery date for the product? Is it too late?" This inquiry is sent to the server in real time.

[0257] Receiving and saving inquiry details

[0258] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and timestamp are recorded. This allows the entire inquiry history to be tracked.

[0259] Analysis using an emotion engine

[0260] The server sends the received inquiry to the sentiment engine. The sentiment engine analyzes the user's emotions based on the style and keywords of the inquiry. For example, from the sentence "Is it too late?", the sentiment engine might determine that the user is irritated.

[0261] Sending to a generative AI

[0262] The server sends the inquiry details, including the sentiment analysis results obtained from the sentiment engine, to the generative AI API. The generative AI API then generates the optimal response based on the inquiry data and sentiment analysis results.

[0263] Answer generation

[0264] The generative AI generates the optimal response based on the analysis results. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions." This response is sent back to the server in real time.

[0265] Receiving and formatting responses

[0266] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[0267] Submit and display of responses

[0268] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0269] Specific example

[0270] Case 1: How to calm frustration in a chat

[0271] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[0272] 2. Server receives and saves query: The query content is saved to the database.

[0273] 3. Emotional Engine Analysis: Detecting frustration from "Is it too late?"

[0274] 4. Sending to the Generative AI: Send the content of your inquiry and your frustration to the Generative AI.

[0275] 5. Generate response: Generate the response: "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0276] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0277] 7. The user receives the response: The chatbot displays the response.

[0278] Case Study 2: Responding to a thank-you message via email

[0279] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[0280] 2. Server receives and saves inquiries: Save the inquiry content in the database

[0281] 3. Analysis by the emotion engine: Detect the feeling of gratitude from "Thank you very much."

[0282] 4. Send to generative AI: Send the inquiry content and the fact that there is a feeling of gratitude to the generative AI

[0283] 5. Generate a response: Generate a response such as "Thank you for always using our service. The next sale is scheduled for early next month."

[0284] 6. Format and send the response: The server formats the response and sends it to the mail system

[0285] 7. User receives the response: The mail client displays the response

[0286] In this way, by recognizing the user's emotions and responding accordingly, a system is realized that improves user satisfaction and efficiently handles inquiries. The emotion analysis results are saved in the database and can also be used for future service improvement.

[0287] The processing flow will be described below.

[0288] Step 1:

[0289] The user inputs the inquiry content.

[0290] The user inputs "When is the delivery date of the product? Is it already late?" into the chatbot or mail form of the terminal.

[0291] Step 2:

[0292] The server receives the inquiry content and saves the inquiry content in the database.

[0293] The server receives the inquiry details from the user interface.

[0294] The server saves the received query data (query ID, user ID, timestamp, and query content) to the database.

[0295] Step 3:

[0296] The server prepares to send the query content to the emotion engine.

[0297] The server formats the query content into a format that the sentiment engine can analyze (for example, text format).

[0298] Step 4:

[0299] The server sends the query to the emotion engine.

[0300] The server sends the formatted query data to the sentiment engine.

[0301] Step 5:

[0302] The emotion engine analyzes the content of the inquiry.

[0303] The emotion engine analyzes the received data and detects the user's emotions from the style and keywords of the inquiry. For example, it might determine that the user is feeling frustrated from the phrase, "Is it too late?"

[0304] Step 6:

[0305] The server receives the emotion analysis results from the emotion engine.

[0306] The server receives the emotion analysis results sent from the emotion engine.

[0307] The server stores the query data and sentiment analysis results in a database.

[0308] Step 7:

[0309] The server prepares to send the inquiry content and the sentiment analysis result to the generative AI API.

[0310] The server formats the inquiry content and the sentiment analysis result into a format (e.g., JSON format) that can be understood by the generative AI API.

[0311] Step 8:

[0312] The server sends the inquiry content and the sentiment analysis result to the generative AI API.

[0313] The server sends the formatted inquiry content and the sentiment analysis result to the endpoint of the generative AI API.

[0314] Step 9:

[0315] The generative AI analyzes the inquiry content and the sentiment analysis result.

[0316] The generative AI analyzes the received data and generates an optimal response according to the user's intention and sentiment situation. For example, a response such as "The delivery time of the product is usually 3 to 5 business days, but there may be a delay. If you have any questions, we will provide further support." is generated.

[0317] Step 10:

[0318] The server receives the response generated by the generative AI.

[0319] The server receives the response data sent from the generative AI. The received data is in a format such as JSON.

[0320] [[ID='49']] Step 11:

[0321] [[ID='53']] The server formats the received response for the user interface.

[0322] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[0323] Step 12:

[0324] The server sends the formatted response to the user interface.

[0325] The server sends the formatted response to the chatbot or email system.

[0326] Step 13:

[0327] The user receives the response on their device.

[0328] The user's device will display a message via chatbot or email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us for further assistance if you have any questions."

[0329] In this way, this system enables the analysis of user emotions and the response accordingly, thereby improving user satisfaction.

[0330] (Example 2)

[0331] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0332] Traditional customer service systems often use canned responses without considering user emotions, resulting in decreased user satisfaction. Furthermore, managing inquiry content while incorporating sentiment analysis results was difficult. This led to problems with the quality and efficiency of responses.

[0333] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0334] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to an emotion analysis engine and analyze the user's emotions, means for the server to send the inquiry content and emotion analysis results to a generative AI API, means for the generative AI to generate an optimal answer based on the inquiry content and emotion analysis results, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for the user to receive the answer, and means for storing the inquiry content, generated answer, and emotion analysis results in a database and managing the inquiry history. This makes it possible to quickly provide the optimal answer while taking the user's emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[0335] A "user" is a person or group that accesses the system and enters their inquiry.

[0336] "Inquiry details" refer to information such as questions and requests that users enter and send to the system.

[0337] A "server" is a computer system that receives queries, performs necessary processing, and interacts with databases and other components.

[0338] A "database" is an information storage system that stores and manages inquiry content, responses, and sentiment analysis results.

[0339] A "sentiment analysis engine" is software and algorithms that analyze the content of inquiries and determine the user's emotions.

[0340] A "generative AI API" is an application programming interface for artificial intelligence that operates based on the content of an inquiry and the results of sentiment analysis in order to provide an appropriate generated response.

[0341] "Formatting" refers to the process of shaping the response obtained from a generative AI for use in a user interface.

[0342] A "user interface" refers to the elements of interaction, including screens and forms, that allow a user to input inquiries into a system and receive generated responses.

[0343] "Inquiry history" refers to a record of all past inquiries, the responses to those inquiries, and data including sentiment analysis results.

[0344] This invention relates to a system that improves user satisfaction by streamlining customer service response using generative AI and an emotion analysis engine. Specific embodiments of this invention are described below.

[0345] Hardware and software to be used

[0346] To implement the invention, the following hardware and software are used.

[0347] Hardware:

[0348] Server: Receives, stores, and communicates with the AI ​​API for generating queries.

[0349] Terminal: A device (such as a PC or smartphone) used by the user to enter their inquiry and receive a response.

[0350] software:

[0351] Database: A system for storing and managing inquiry content, responses, and sentiment analysis results.

[0352] Sentiment analysis engine: Software that analyzes inquiry content and determines the user's emotions.

[0353] Generative AI API: An API for generating the optimal response based on the content of the inquiry and the results of sentiment analysis.

[0354] User interface: A screen or form on which a user enters their inquiry and receives a response.

[0355] Data processing and calculation

[0356] server

[0357] 1. The server receives data from forms or chatbots where users enter their inquiries.

[0358] 2. Save the received inquiry details to the database. At this time, metadata such as the inquiry ID, user ID, and timestamp will also be recorded.

[0359] 3. The server sends the saved query content to the sentiment analysis engine. The sentiment analysis engine analyzes the writing style and keywords to determine the user's emotions.

[0360] 4. The server that receives the sentiment analysis results sends the inquiry content and sentiment analysis results to the generative AI API.

[0361] 5. The generative AI generates the optimal response based on the inquiry content and sentiment analysis results, and returns the result to the server.

[0362] 6. The server formats the generated response for the user interface and sends the response to the terminal.

[0363] terminal

[0364] 1. Users enter their inquiries using their devices. For example, they might use a website's chatbot screen or email form.

[0365] 2. The user receives the response sent from the server on their device. They then review the formatted response using a chatbot or email app.

[0366] Examples of specific cases and prompt statements

[0367] Example 1: Handling inquiries via chat

[0368] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[0369] 2. Server receives and stores query: The server stores the query content in the database.

[0370] 3. Emotional analysis: The emotional analysis engine detects frustration from the phrase "Is it too late?"

[0371] 4. Sending to the Generative AI: The server sends the query content and the frustration to the Generative AI.

[0372] 5. Response Generation: The generation AI generates the response: "The delivery time for products is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0373] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0374] 7. The user receives the response: The user confirms the response via the chatbot.

[0375] Example 2: Responding to inquiries via email

[0376] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[0377] 2. Server receives and stores query: The server stores the query content in the database.

[0378] 3. Analysis by the emotion engine: The emotion analysis engine detects gratitude from "Thank you."

[0379] 4. Sending to the Generative AI: The server sends the inquiry details and a message of thanks to the Generative AI.

[0380] 5. Response generation: The generation AI generates the response, "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[0381] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[0382] 7. The user receives the response: The user confirms the response via their email client.

[0383] Example of a prompt

[0384] 1. A prompt to calm frustration during a chat: "When is the product due? Is it too late?"

[0385] 2. Prompt response to a thank-you email: "Thank you as always. Please let me know about your next sale."

[0386] This embodiment makes it possible to quickly provide the optimal answer while taking user emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The user enters an inquiry.

[0390] Input: The user enters their inquiry into a chatbot or email form.

[0391] Processing: The user enters, for example, "When is the delivery date for the product? Is it too late?"

[0392] Operation: The entered inquiry content is displayed in the terminal's input field, and when the submit button is pressed, that content is sent to the server.

[0393] Output: The user's inquiry is sent to the server.

[0394] Step 2:

[0395] The server receives and stores the query.

[0396] Input: The content of the inquiry submitted by the user.

[0397] Processing: The server receives the query in real time. The received content is analyzed and saved to the database along with the relevant metadata (query ID, user ID, timestamp, etc.).

[0398] Operation: The server adds the query content to the database as a new record. This makes the query content traceable within the system.

[0399] Output: The query details are saved in the database.

[0400] Step 3:

[0401] The server sends the inquiry details to the sentiment analysis engine.

[0402] Input: The query content stored in the database.

[0403] Processing: The server sends the inquiry content as an API request to the sentiment analysis engine. The sentiment analysis engine analyzes the user's emotions using the writing style and keywords.

[0404] Operation: The server sends data to the sentiment analysis engine using an HTTP POST request and receives the analysis results.

[0405] Output: Sentiment analysis results from the emotion analysis engine.

[0406] Step 4:

[0407] The server sends the sentiment analysis results and inquiry content to a generative AI API.

[0408] Input: Inquiry details and sentiment analysis results.

[0409] Processing: The server sends the inquiry details and sentiment analysis results to a generative AI API. The generative AI API generates the optimal response based on the received information.

[0410] Operation: The server sends data to a generative AI API and sets prompts to generate the optimal response.

[0411] Output: Response data from a generative AI.

[0412] Step 5:

[0413] Generative AI generates the optimal answer.

[0414] Input: Prompts based on the inquiry content and sentiment analysis results.

[0415] Processing: The generative AI analyzes the input prompt and generates an appropriate response to the inquiry. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0416] Operation: Generative AI uses internal algorithms to analyze the content and sentiment of inquiries and construct responses.

[0417] Output: Generated response data.

[0418] Step 6:

[0419] The server formats the generated response.

[0420] Input: Response data generated by a generative AI.

[0421] Processing: The server formats the received response data for the user interface. This process includes converting JSON data to HTML or plain text.

[0422] Operation: The server converts the received data into an appropriate format and displays it in a way that is easy for the user to read.

[0423] Output: Formatted response data.

[0424] Step 7:

[0425] The server sends the formatted response to the user interface.

[0426] Input: Formatted response data.

[0427] Processing: The server sends the formatted response to the user interface, such as a chatbot screen or email system.

[0428] Operation: Data is sent from the server to the user interface and displayed on the terminal in real time.

[0429] Output: Response data displayed on the user's device.

[0430] Step 8:

[0431] The user receives the response.

[0432] Input: Formatted response data submitted from the user interface.

[0433] Processing: The user's device receives the response data and displays it on the screen.

[0434] Operation: Users review the responses via the chatbot screen or email client and decide on their next action.

[0435] Output: The user reviews the displayed answer.

[0436] (Application Example 2)

[0437] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0438] Traditional customer service systems often provide formulaic responses without considering user emotions, leading to decreased customer satisfaction. Furthermore, staff in physical stores lacked the means to provide appropriate answers and responses in real time, making efficient and effective customer service difficult.

[0439] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for sending the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate the optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for using an emotion engine to analyze the user's emotions, means for sending the emotion information analyzed by the emotion engine to the generative AI, and means for the generative AI to generate a more accurate answer based on the emotion information. This makes it possible for staff in physical stores to provide the optimal response in real time according to the customer's emotions.

[0440] The "user interface" is the part of a system that provides an interactive screen or form for users to input inquiry details and view the generated response.

[0441] A "server" is a central computer that receives user inquiries and manages and processes communication with databases, generative AI APIs, and emotion engines.

[0442] A "database" is a data management system used to store and manage information such as inquiry content, generated responses, and sentiment analysis results.

[0443] "Generative AI" refers to a system that uses artificial intelligence technology to analyze the content of an input inquiry and generate the most appropriate response.

[0444] A "generative AI API" is a programmatic interface for sending inquiries to a generative AI and obtaining the most appropriate response.

[0445] An "emotion engine" is a system that analyzes user emotions based on the content of their inquiries and the writing style they use.

[0446] "Formatting" refers to the process of converting the generated response into a format suitable for the user interface.

[0447] "Inquiry content" refers to questions or requests that users enter into the system.

[0448] "Answer" refers to the optimal response generated by a generative AI in response to an inquiry that has been analyzed.

[0449] This invention is a system that utilizes generative AI and an emotion engine to streamline user support at inquiry desks. Specific embodiments for carrying out this invention are described below.

[0450] System Configuration

[0451] This system consists of multiple components, including a user interface, server, generative AI API, emotion engine, and database.

[0452] User Interface (UI)

[0453] The user interface provides interactive screens and forms for users to input inquiries and review generated responses. Specifically, it is implemented as a smartphone or tablet application.

[0454] server

[0455] The server receives user inquiries and stores them in a database. It also sends the inquiry content to a generative AI API, formats the generated response, and sends it to the user interface. The server handles the main central processing and manages the coordination with the emotion engine and generative AI API.

[0456] Emotional Engine

[0457] The emotion engine analyzes user inquiries and interprets their emotions based on their writing style and keywords. The analyzed emotion information is sent to the generative AI via the server and used to improve the accuracy of the generated responses.

[0458] Generative AI API

[0459] The generative AI API generates the optimal response based on the user's inquiry and sentiment analysis results. The generated response is sent to the server and formatted for display in the user interface.

[0460] database

[0461] The database stores and manages information such as inquiry content, generated responses, and sentiment analysis results. This makes it possible to track the entire inquiry history.

[0462] Flow of operations

[0463] When a user enters an inquiry using a smartphone or tablet, that information is sent to the server. The server stores the received inquiry in a database and sends it to an emotion engine for sentiment analysis. The emotion information obtained from the emotion engine is sent to a generative AI to generate the optimal response. The generated response is returned to the server, formatted in a way that can be displayed to the user, and then sent to the user interface.

[0464] Specific example

[0465] For example, imagine a staff member at a physical store receiving a customer inquiry via smartphone asking, "Do you have this item in stock?" If the emotion engine analyzes the customer's emotion to be "anxiety," the generative AI uses this information to generate a response such as, "We have it in stock. However, it may take some time for the next shipment to arrive." This allows the staff member to respond quickly and appropriately.

[0466] Example of a prompt

[0467] Enter the following as the prompt:

[0468] Prompt: A customer in a store asks, "Do you have this item in stock?" Generate the best response using a generative AI model, incorporating the emotion analyzed as "anxiety" by the emotion engine.

[0469] The above describes the "mode for carrying out the invention." A system following this mode can improve the efficiency of user support and enhance customer satisfaction.

[0470] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0471] Step 1:

[0472] The user enters their inquiry.

[0473] Input: User input from smartphones or tablets (e.g., "Is this product in stock?").

[0474] Output: The entered query content is sent to the server.

[0475] Specific operation: When a user enters their inquiry into a text box on the user interface (UI) and presses the submit button, that text data is sent from the terminal to the server.

[0476] Step 2:

[0477] The server receives the query and saves it to the database.

[0478] Input: The content of the inquiry submitted by the user.

[0479] Output: The query details are saved in the database and registered along with the query ID and timestamp.

[0480] Specific operation: The server temporarily stores the received query in memory, establishes a database connection, and permanently stores the query. Metadata such as ID, user ID, and timestamp is attached to the query.

[0481] Step 3:

[0482] The server sends the query to the emotion engine, which then analyzes the emotions.

[0483] Input: The query content stored in the database.

[0484] Output: Emotional information analyzed by the emotion engine (e.g., "anxiety").

[0485] Specific operation: The server sends the stored query content to the sentiment engine's API, and the sentiment engine analyzes the writing style and keywords to return sentiment information. The server receives this sentiment information.

[0486] Step 4:

[0487] The server sends the inquiry content and sentiment information to a generative AI API, which then generates the optimal response.

[0488] Input: Inquiry content and sentiment information returned by the sentiment engine.

[0489] Output: Response generated from a generative AI API (e.g., "We have stock. However, it may take some time before the next shipment arrives.").

[0490] Specific operation: The server combines the inquiry content and sentiment information and sends it to a generative AI API. The generative AI then performs natural language processing based on this information, generates the optimal response, and sends it to the server.

[0491] Step 5:

[0492] The server receives the generated response and formats it for the user interface.

[0493] Input: Response received from a generative AI.

[0494] Output: Formatted response data.

[0495] Specific operation: The server converts the received response from JSON format to HTML or plain text format and formats it so that it can be displayed in the user interface.

[0496] Step 6:

[0497] The server sends the formatted response to the user interface, and the user receives the response.

[0498] Input: Formatted response data.

[0499] Output: The answer displayed on the user interface.

[0500] Specific operation: The server sends the formatted response to the terminal and visualizes it in the user interface. The user can view the response on their smartphone or tablet screen.

[0501] This allows users to receive optimal responses tailored to their emotions in real time, streamlining customer service in physical stores.

[0502] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0503] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0504] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0505] [Second Embodiment]

[0506] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0507] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0508] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0509] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0510] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0511] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0512] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0513] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0514] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0515] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0516] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0517] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0518] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[0519] System Overview

[0520] This system mainly consists of the following components:

[0521] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0522] 2. Server: Receives the query content and communicates with the database and generative AI.

[0523] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0524] 4. Database: Stores and manages inquiry content and its responses.

[0525] Program processing

[0526] Inquiry reception

[0527] Users enter their inquiries via chatbots or email forms. For example, a user might type, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[0528] Receiving and saving inquiry details

[0529] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and inquiry timestamp are recorded. This allows the entire inquiry history to be tracked.

[0530] Sending to a generative AI

[0531] The server formats the received query and sends it to the generative AI API. The generative AI API analyzes the query data sent from the server and performs natural language processing to understand the intent of the query.

[0532] Answer generation

[0533] The generative AI analyzes the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days." This response is sent back to the server in real time.

[0534] Receiving and formatting responses

[0535] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[0536] Submit and display of responses

[0537] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days."

[0538] Specific example

[0539] Case 1: Inquiry via chat

[0540] 1. User enters inquiry: User: "Please explain the return process."

[0541] 2. Server receives and saves query: The query content is saved to the database.

[0542] 3. Analysis of the inquiry: Generative AI analyzes "Please tell me about the return process."

[0543] 4. Response generation: The generation AI generates "For information on the return process, please read the following steps..."

[0544] 5. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0545] 6. The user receives the response: The chatbot displays the response to the user.

[0546] Case 2: Inquiry via email

[0547] 1. User enters inquiry: User: "How do I place an additional order?"

[0548] 2. Server receives and saves query: The query content is saved to the database.

[0549] 3. Analysis of the inquiry: The generative AI analyzes the inquiry "How do I place an additional order?"

[0550] 4. Response generation: The generation AI generates the message, "For instructions on how to place an additional order, please proceed through your My Page on the online store."

[0551] 5. Formatting and sending responses: The server formats the responses and sends them to the email system.

[0552] 6. The user receives the response: The email client displays the response to the user.

[0553] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and responses in a database, it can also be used for future service improvements.

[0554] The following describes the processing flow.

[0555] Step 1:

[0556] The user enters their inquiry.

[0557] Users enter their inquiries into the chatbot or email form on their device. For example, they might type, "What is the delivery date for the product?"

[0558] Step 2:

[0559] The server receives the query and saves it to the database.

[0560] The server receives query data from the user interface.

[0561] The server saves the received query data to a database. The query ID, user ID, timestamp, and query content are recorded.

[0562] Step 3:

[0563] The server prepares to send the query content to the generative AI API.

[0564] The server formats the query content into a format that the generative AI API can understand (for example, JSON format).

[0565] Step 4:

[0566] The server sends the query content to the generative AI API.

[0567] The server sends the formatted query data to the endpoint of the generative AI API.

[0568] Step 5:

[0569] A generative AI analyzes the content of the inquiry.

[0570] Generative AI analyzes received data to extract the intent and keywords of inquiries. For example, generative AI might extract information related to "product delivery dates."

[0571] Step 6:

[0572] The generative AI generates the optimal answer.

[0573] Generative AI generates the optimal answer based on the analysis results. For example, it might generate the answer, "The delivery time for products is usually 3 to 5 business days."

[0574] Step 7:

[0575] The server receives the response generated by the generative AI.

[0576] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[0577] Step 8:

[0578] The server formats the received response for the user interface.

[0579] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[0580] Step 9:

[0581] The server sends the formatted response to the user interface.

[0582] The server sends the formatted response to the chatbot or email system.

[0583] Step 10:

[0584] The user receives the response on their device.

[0585] The response will be displayed on the chatbot screen or email client on the user's device. For example, it might say, "The delivery time for products is usually 3-5 business days."

[0586] In this way, the system ensures that the entire process, from the user submitting an inquiry to receiving a response, is carried out quickly and efficiently.

[0587] (Example 1)

[0588] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0589] Traditional inquiry handling systems often resulted in long waiting times between user inquiry submission and response, and sometimes generated inconsistent answers. Furthermore, inadequate management of inquiry history prevented the effective utilization of past inquiry information. This led to decreased user satisfaction and hindered the efficiency of corporate response processes.

[0590] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0591] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer, and send it to the user interface, means for the user to receive the answer, means for the inquiry content to be sent to the server in real time, means for the server to store the inquiry ID, user ID, and timestamp for the received inquiry content in a database, means for the server to convert the JSON format data to HTML or plain text after receiving the answer from the generative AI, means for the server to send the formatted answer to the user interface in real time, and means for displaying the formatted answer on the user's terminal. This enables a rapid and consistent response to inquiries, improving user satisfaction and the efficiency of corporate responses.

[0592] A "user" refers to an individual or organization that uses the system to make an inquiry.

[0593] "Inquiry details" refers to information including questions and requests entered by the user into the system.

[0594] A "server" refers to a computer system that receives and processes inquiries.

[0595] A "database" refers to a collection of digital information used to store and manage inquiries and the responses to them.

[0596] "Generative AI" refers to an artificial intelligence system that analyzes user inquiries and generates appropriate responses.

[0597] An "API" refers to an interface for exchanging data between a server and a generative AI.

[0598] "Formatting" refers to the process of converting data or information into a specific format.

[0599] "User interface" refers to the screen or form on which a user makes an inquiry and receives a response.

[0600] A "timestamp" refers to information indicating the date and time the inquiry was made.

[0601] "Real-time" refers to a state where user actions and inquiries are responded to immediately.

[0602] "JSON format" is a type of data exchange format, and is an abbreviation for JavaScript Object Notation.

[0603] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[0604] System Overview

[0605] This system mainly consists of the following components:

[0606] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0607] 2. Server: Receives the query content and communicates with the database and generative AI.

[0608] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0609] 4. Database: Stores and manages inquiry content and its responses.

[0610] Program processing

[0611] The program processes the information as follows: First, the user enters their inquiry via a chatbot or email form. For example, the user might enter, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[0612] The server saves the received query content to a database. The information saved includes the query ID, user ID, and query timestamp. This makes it possible to track the entire query history. Next, the server formats the received query content and sends it to the generative AI API.

[0613] The generative AI API analyzes inquiry data sent from the server and performs natural language processing to understand the intent of the inquiry. The generative AI analyzes the content of the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3 to 5 business days." This response is sent back to the server in real time.

[0614] The server receives responses from the generative AI and formats them for the user interface. For example, it converts JSON data to HTML or plain text. The formatted response is sent from the server to the user interface, and the user's device displays a message such as "Product delivery time is usually 3-5 business days" on the chatbot screen or in their email client.

[0615] Specific example

[0616] Case 1: Inquiry via chat

[0617] 1. User enters inquiry: The user enters "Please explain the return process."

[0618] 2. Server receives and saves query: The server saves the query content to the database.

[0619] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[0620] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to "Please tell me about the return process" (e.g., "For information on the return process, please read the following steps...").

[0621] 5. Server receives and formats the generated response: The server receives the response from the generation AI and formats it in HTML format.

[0622] 6. Server sends response to terminal, user receives: The server sends the formatted response to the chatbot's UI, which is then displayed to the user on the chatbot screen.

[0623] Case 2: Inquiry via email

[0624] 1. User enters inquiry: The user enters "Please tell me how to place an additional order" into the email form.

[0625] 2. Server receives and saves query: The server saves the query content to the database.

[0626] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[0627] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to the question "How do I place an additional order?" (Example: "To place an additional order, please proceed through your My Page on the online store.").

[0628] 5. Server receives and formats the generated response: The server receives the response from the generative AI and formats it in plain text format.

[0629] 6. Server sends response to terminal, user receives: The server sends the formatted response to the email system, and the user's email client displays a message saying, "For instructions on how to place an additional order, please proceed from your online store's My Page."

[0630] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and their responses in a database, it can also be used for future service improvements. This system makes it possible to improve user satisfaction and increase the operational efficiency of companies.

[0631] Example of a prompt

[0632] "When is the product due?"

[0633] "Please tell me about the return process."

[0634] "Please tell me how to place an additional order."

[0635] By entering these prompts, the generative AI will provide the corresponding answer.

[0636] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0637] Step 1:

[0638] The user enters an inquiry.

[0639] The user enters their inquiry using a terminal. For example, the user might enter, "What is the delivery date for the product?" This becomes the input data. The terminal then sends the entered inquiry to the server in real time.

[0640] Step 2:

[0641] The server receives the query.

[0642] The server receives user inquiries in real time. This received data becomes the input data. The server first saves the received inquiry content to a database. When saving, it also records additional information such as the inquiry ID, user ID, and timestamp. This makes it possible to track the inquiry history.

[0643] Step 3:

[0644] The server formats the query content.

[0645] The server retrieves query data stored in the database and converts it into the format necessary for sending it to the generative AI. This format conversion is data processing. For example, the query data is converted into JSON format. The converted JSON data becomes the output data.

[0646] Step 4:

[0647] The server sends the formatted query content to the generation AI API.

[0648] The server sends formatted JSON data to the generative AI API. This becomes the input data. The server performs error checking and data integrity verification during transmission. Once the generative AI receives the data, it begins analyzing the query.

[0649] Step 5:

[0650] The generative AI analyzes the inquiry and generates a response.

[0651] The generative AI analyzes the JSON-formatted query received from the server. This analysis is data processing. The generative AI uses natural language processing techniques to understand the intent of the query and generate an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3-5 business days." This generated response becomes the output data.

[0652] Step 6:

[0653] The server receives the response from the generative AI.

[0654] The server receives the response generated by the generative AI. The received response data in JSON format becomes the input data. The server then performs a verification process on the received data for comparison.

[0655] Step 7:

[0656] The server formats the generated response.

[0657] The server formats the received JSON response for the user interface. Specifically, it converts the JSON data into HTML or plain text. This format conversion is data processing. The converted data becomes the output data.

[0658] Step 8:

[0659] The server sends the formatted response to the user interface.

[0660] The server sends the formatted response data to the user's terminal. The converted data is sent as input data. The server checks the data integrity and confirms delivery upon transmission.

[0661] Step 9:

[0662] The answer will be displayed on the user's device.

[0663] The user's device receives a formatted response sent from the server. This received data becomes the input data. The device then displays the received data appropriately. For example, it might display "Product delivery time is usually 3-5 business days" on the chatbot screen or in the email client.

[0664] Through these steps, users' inquiries will be answered quickly and appropriately.

[0665] (Application Example 1)

[0666] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0667] Electronic payment services require prompt and accurate responses to user inquiries. However, traditional systems often resulted in inconsistent quality in inquiry handling, frequently lowering user satisfaction. Furthermore, there was a lack of efficient methods for managing inquiry content and response history. As a result, inquiry handling took a significant amount of time, negatively impacting user convenience.

[0668] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0669] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to a user interface, means for the user to receive the answer, means for handling inquiries using an application installed on a smartphone, smart glasses, head-mounted display, or robot, and means for processing inquiries related to electronic payment services. This makes it possible to improve the quality of inquiry handling and enhance user convenience.

[0670] A "server" is a computer system that receives user inquiries, stores them in a database, and sends them to a generative AI API.

[0671] A "user interface" is a means of providing a screen or form for a user to input their inquiry and receive a generated response.

[0672] "Generative AI" refers to artificial intelligence that analyzes inquiries and generates the most appropriate response.

[0673] A "generative AI API" is an application programming interface for sending and receiving query data between a server and a generative AI.

[0674] A "database" is a system for storing and managing query content and generated responses.

[0675] A "smartphone" is a portable computer device used to input inquiries and receive generated responses.

[0676] "Smart glasses" are wearable devices used by users to input inquiries and receive generated responses.

[0677] A "head-mounted display" is a display device worn by the user, used for inputting inquiries and receiving generated responses.

[0678] A "robot" is an automated machine programmed to handle inquiries.

[0679] An "electronic payment service" is a system that allows users to pay electronically for goods and services they purchase online or in physical stores.

[0680] "Inquiry history" refers to a record of user inquiries and the corresponding responses.

[0681] The system for implementing this invention automates the reception, analysis, and response generation of inquiries, thereby improving the efficiency of handling inquiries related to electronic payment services. Specifically, it uses the following hardware and software.

[0682] System Overview

[0683] hardware

[0684] 1. Server: A high-performance computer server receives user inquiries and sends data to the generative AI. It also stores the inquiry content and its response in a database.

[0685] 2. User terminal: This refers to devices such as smartphones, smart glasses, head-mounted displays, and robots. These are used by users to input inquiries and display generated responses.

[0686] software

[0687] 1. User Interface (UI): The screen or form on which a user enters an inquiry and receives a generated response. Frameworks such as React Native or Flutter are used.

[0688] 2. Server Application: Built using Node.js and Express. It receives, stores, and sends query data to the generation AI, formats the generated responses, and sends them to the user's terminal.

[0689] 3. Generative AI: A generative AI model (e.g., GPT-4) is used to analyze the inquiry content and generate an appropriate response.

[0690] 4. Database: Use a relational database such as MySQL to manage queries and their responses.

[0691] Program processing

[0692] Receiving and saving inquiries

[0693] The user enters their inquiry through a smartphone application. For example, an inquiry such as, "What should I do about a canceled payment?" The server receives this inquiry and saves it to a database. The inquiry ID, user ID, and timestamp are recorded.

[0694] Sending to a generative AI

[0695] The server sends the received query to a generative AI API. The generative AI analyzes the query and uses natural language processing techniques to understand its intent. It then generates an appropriate response.

[0696] Answer generation and formatting

[0697] The generative AI generates a response such as, "For canceled payments, please follow these instructions..." This response is sent back to the server in real time. The server formats the received response for display to the user. For example, it converts JSON data into plain text.

[0698] Submit and display of responses

[0699] The formatted response is sent from the server to the user interface. The user's device, such as a smartphone or smart glasses screen, displays a response such as, "For canceled payments, please follow these instructions."

[0700] Specific example

[0701] Example 1: Inquiry

[0702] The user typed "What should I do about the canceled payment?" into the smartphone app.

[0703] The server receives the data and saves it to the database.

[0704] Send to a generative AI API.

[0705] The generative AI analyzes the data and generates a response saying, "For canceled payments, please follow these instructions."

[0706] The server formats the file and sends it to the user's terminal.

[0707] The user checks their answer on their smartphone.

[0708] Example of a prompt

[0709] "This is an inquiry regarding electronic payment cancellations. A user has asked about the payment cancellation process. Please provide an appropriate answer."

[0710] "A user is inquiring about a failed payment method. Please generate specific instructions."

[0711] By implementing this invention, the efficiency and quality of handling inquiries are improved, and user convenience is significantly enhanced.

[0712] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0713] Step 1:

[0714] The user enters their inquiry using a device (e.g., a smartphone). For example, they might enter an inquiry such as "What should I do about a canceled payment?" into the application screen. This input is sent to the server in real time through the UI component.

[0715] Step 2:

[0716] The server receives the query content sent from the terminal. The received content is stored in the database. Metadata such as the query ID, user ID, and timestamp is also stored here. The input is the query content, and the output is the record stored in the database.

[0717] Step 3:

[0718] The server formats the received query and sends it to the generative AI API. For example, it prepares the query as JSON data and sends a request to the API endpoint. The input is the formatted query, and the output is the request to the generative AI.

[0719] Step 4:

[0720] The generative AI analyzes the inquiry content and performs natural language processing to understand its intent. It then generates an appropriate response. For example, it might generate the prompt "For canceled payments, please follow these steps." The input is the received inquiry, and the output is the generated response.

[0721] Step 5:

[0722] The server receives the responses generated by the generative AI. The server then formats the received responses for the user interface. For example, it might convert JSON data to plain text. The input is the generated response, and the output is the formatted response.

[0723] Step 6:

[0724] The server sends a formatted response to the user interface. It converts the response to a format that can be displayed on the application's chat screen and sends it to the user's device. The input is the formatted response, and the output is the display of the response on the user's device.

[0725] Step 7:

[0726] The user's device displays the response received from the server. The user sees a specific response on their smartphone screen, such as "For canceled payments, please follow these instructions." The input is the formatted response received from the server, and the output is the display on the user's screen.

[0727] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0728] This invention relates to a system that achieves more accurate responses by combining a system that uses generative AI to streamline customer service responses with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0729] System Overview

[0730] This system mainly consists of the following components:

[0731] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[0732] 2. Server: Receives the query content and communicates with the database and generative AI.

[0733] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[0734] 4. Emotion Engine: Analyzes user emotions from the content of their inquiries and the writing style used during input.

[0735] 5. Database: Stores and manages inquiry content, responses, and sentiment analysis results.

[0736] Program processing

[0737] Inquiry reception

[0738] Users enter their inquiries via chatbots or email forms. For example, a user might type, "When is the delivery date for the product? Is it too late?" This inquiry is sent to the server in real time.

[0739] Receiving and saving inquiry details

[0740] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and timestamp are recorded. This allows the entire inquiry history to be tracked.

[0741] Analysis using an emotion engine

[0742] The server sends the received inquiry to the sentiment engine. The sentiment engine analyzes the user's emotions based on the style and keywords of the inquiry. For example, from the sentence "Is it too late?", the sentiment engine might determine that the user is irritated.

[0743] Sending to a generative AI

[0744] The server sends the inquiry details, including the sentiment analysis results obtained from the sentiment engine, to the generative AI API. The generative AI API then generates the optimal response based on the inquiry data and sentiment analysis results.

[0745] Answer generation

[0746] The generative AI generates the optimal response based on the analysis results. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions." This response is sent back to the server in real time.

[0747] Receiving and formatting responses

[0748] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[0749] Submit and display of responses

[0750] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0751] Specific example

[0752] Case 1: How to calm frustration in a chat

[0753] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[0754] 2. Server receives and saves query: The query content is saved to the database.

[0755] 3. Emotional Engine Analysis: Detecting frustration from "Is it too late?"

[0756] 4. Sending to the Generative AI: Send the content of your inquiry and your frustration to the Generative AI.

[0757] 5. Generate response: Generate the response: "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0758] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0759] 7. The user receives the response: The chatbot displays the response.

[0760] Case Study 2: Responding to a thank-you message via email

[0761] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[0762] 2. Server receives and saves query: The query content is saved to the database.

[0763] 3. Analysis using an emotion engine: Detecting gratitude from "Thank you."

[0764] 4. Sending to the Generative AI: Send the inquiry details and your thanks to the Generative AI.

[0765] 5. Generating the response: Generate the response: "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[0766] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[0767] 7. The user receives the response: The email client displays the response.

[0768] This system recognizes user emotions and responds accordingly, thereby improving user satisfaction and enabling efficient inquiry handling. The emotion analysis results are stored in a database and can be used for future service improvements.

[0769] The following describes the processing flow.

[0770] Step 1:

[0771] The user enters their inquiry.

[0772] Users type "When is the product due? Is it too late?" into the chatbot or email form on their device.

[0773] Step 2:

[0774] The server receives the query and saves the query details to the database.

[0775] The server receives the inquiry details from the user interface.

[0776] The server saves the received query data (query ID, user ID, timestamp, and query content) to the database.

[0777] Step 3:

[0778] The server prepares to send the query content to the emotion engine.

[0779] The server formats the query content into a format that the sentiment engine can analyze (for example, text format).

[0780] Step 4:

[0781] The server sends the query to the emotion engine.

[0782] The server sends the formatted query data to the sentiment engine.

[0783] Step 5:

[0784] The emotion engine analyzes the content of the inquiry.

[0785] The emotion engine analyzes the received data and detects the user's emotions from the style and keywords of the inquiry. For example, it might determine that the user is feeling frustrated from the phrase, "Is it too late?"

[0786] Step 6:

[0787] The server receives the emotion analysis results from the emotion engine.

[0788] The server receives the emotion analysis results sent from the emotion engine.

[0789] The server stores the query data and sentiment analysis results in a database.

[0790] Step 7:

[0791] The server prepares to send the inquiry details and sentiment analysis results to the generative AI API.

[0792] The server formats the inquiry content and sentiment analysis results into a format that the generative AI API can understand (for example, JSON format).

[0793] Step 8:

[0794] The server sends the query content and sentiment analysis results to the generative AI API.

[0795] The server sends the formatted query content and sentiment analysis results to the generative AI API endpoint.

[0796] Step 9:

[0797] A generative AI analyzes the content of the inquiry and the results of the sentiment analysis.

[0798] Generative AI analyzes received data and generates the most appropriate response tailored to the user's intent and emotional state. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0799] Step 10:

[0800] The server receives the response generated by the generative AI.

[0801] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[0802] Step 11:

[0803] The server formats the received response for the user interface.

[0804] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[0805] Step 12:

[0806] The server sends the formatted response to the user interface.

[0807] The server sends the formatted response to the chatbot or email system.

[0808] Step 13:

[0809] The user receives the response on their device.

[0810] The user's device will display a message via chatbot or email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us for further assistance if you have any questions."

[0811] In this way, this system enables the analysis of user emotions and the response accordingly, thereby improving user satisfaction.

[0812] (Example 2)

[0813] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0814] Traditional customer service systems often use canned responses without considering user emotions, resulting in decreased user satisfaction. Furthermore, managing inquiry content while incorporating sentiment analysis results was difficult. This led to problems with the quality and efficiency of responses.

[0815] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0816] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to an emotion analysis engine and analyze the user's emotions, means for the server to send the inquiry content and emotion analysis results to a generative AI API, means for the generative AI to generate an optimal answer based on the inquiry content and emotion analysis results, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for the user to receive the answer, and means for storing the inquiry content, generated answer, and emotion analysis results in a database and managing the inquiry history. This makes it possible to quickly provide the optimal answer while taking the user's emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[0817] A "user" is a person or group that accesses the system and enters their inquiry.

[0818] "Inquiry details" refer to information such as questions and requests that users enter and send to the system.

[0819] A "server" is a computer system that receives queries, performs necessary processing, and interacts with databases and other components.

[0820] A "database" is an information storage system that stores and manages inquiry content, responses, and sentiment analysis results.

[0821] A "sentiment analysis engine" is software and algorithms that analyze the content of inquiries and determine the user's emotions.

[0822] A "generative AI API" is an application programming interface for artificial intelligence that operates based on the content of an inquiry and the results of sentiment analysis in order to provide an appropriate generated response.

[0823] "Formatting" refers to the process of shaping the response obtained from a generative AI for use in a user interface.

[0824] A "user interface" refers to the elements of interaction, including screens and forms, that allow a user to input inquiries into a system and receive generated responses.

[0825] "Inquiry history" refers to a record of all past inquiries, the responses to those inquiries, and data including sentiment analysis results.

[0826] This invention relates to a system that improves user satisfaction by streamlining customer service response using generative AI and an emotion analysis engine. Specific embodiments of this invention are described below.

[0827] Hardware and software to be used

[0828] To implement the invention, the following hardware and software are used.

[0829] Hardware:

[0830] Server: Receives, stores, and communicates with the AI ​​API for generating queries.

[0831] Terminal: A device (such as a PC or smartphone) used by the user to enter their inquiry and receive a response.

[0832] software:

[0833] Database: A system for storing and managing inquiry content, responses, and sentiment analysis results.

[0834] Sentiment analysis engine: Software that analyzes inquiry content and determines the user's emotions.

[0835] Generative AI API: An API for generating the optimal response based on the content of the inquiry and the results of sentiment analysis.

[0836] User interface: A screen or form on which a user enters their inquiry and receives a response.

[0837] Data processing and calculation

[0838] server

[0839] 1. The server receives data from forms or chatbots where users enter their inquiries.

[0840] 2. Save the received inquiry details to the database. At this time, metadata such as the inquiry ID, user ID, and timestamp will also be recorded.

[0841] 3. The server sends the saved query content to the sentiment analysis engine. The sentiment analysis engine analyzes the writing style and keywords to determine the user's emotions.

[0842] 4. The server that receives the sentiment analysis results sends the inquiry content and sentiment analysis results to the generative AI API.

[0843] 5. The generative AI generates the optimal response based on the inquiry content and sentiment analysis results, and returns the result to the server.

[0844] 6. The server formats the generated response for the user interface and sends the response to the terminal.

[0845] terminal

[0846] 1. Users enter their inquiries using their devices. For example, they might use a website's chatbot screen or email form.

[0847] 2. The user receives the response sent from the server on their device. They then review the formatted response using a chatbot or email app.

[0848] Examples of specific cases and prompt statements

[0849] Example 1: Handling inquiries via chat

[0850] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[0851] 2. Server receives and stores query: The server stores the query content in the database.

[0852] 3. Emotional analysis: The emotional analysis engine detects frustration from the phrase "Is it too late?"

[0853] 4. Sending to the Generative AI: The server sends the query content and the frustration to the Generative AI.

[0854] 5. Response Generation: The generation AI generates the response: "The delivery time for products is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0855] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[0856] 7. The user receives the response: The user confirms the response via the chatbot.

[0857] Example 2: Responding to inquiries via email

[0858] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[0859] 2. Server receives and stores query: The server stores the query content in the database.

[0860] 3. Analysis by the emotion engine: The emotion analysis engine detects gratitude from "Thank you."

[0861] 4. Sending to the Generative AI: The server sends the inquiry details and a message of thanks to the Generative AI.

[0862] 5. Response generation: The generation AI generates the response, "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[0863] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[0864] 7. The user receives the response: The user confirms the response via their email client.

[0865] Example of a prompt

[0866] 1. A prompt to calm frustration during a chat: "When is the product due? Is it too late?"

[0867] 2. Prompt response to a thank-you email: "Thank you as always. Please let me know about your next sale."

[0868] This embodiment makes it possible to quickly provide the optimal answer while taking user emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[0869] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0870] Step 1:

[0871] The user enters an inquiry.

[0872] Input: The user enters their inquiry into a chatbot or email form.

[0873] Processing: The user enters, for example, "When is the delivery date for the product? Is it too late?"

[0874] Operation: The entered inquiry content is displayed in the terminal's input field, and when the submit button is pressed, that content is sent to the server.

[0875] Output: The user's inquiry is sent to the server.

[0876] Step 2:

[0877] The server receives and stores the query.

[0878] Input: The content of the inquiry submitted by the user.

[0879] Processing: The server receives the query in real time. The received content is analyzed and saved to the database along with the relevant metadata (query ID, user ID, timestamp, etc.).

[0880] Operation: The server adds the query content to the database as a new record. This makes the query content traceable within the system.

[0881] Output: The query details are saved in the database.

[0882] Step 3:

[0883] The server sends the inquiry details to the sentiment analysis engine.

[0884] Input: The query content stored in the database.

[0885] Processing: The server sends the inquiry content as an API request to the sentiment analysis engine. The sentiment analysis engine analyzes the user's emotions using the writing style and keywords.

[0886] Operation: The server sends data to the sentiment analysis engine using an HTTP POST request and receives the analysis results.

[0887] Output: Sentiment analysis results from the emotion analysis engine.

[0888] Step 4:

[0889] The server sends the sentiment analysis results and inquiry content to a generative AI API.

[0890] Input: Inquiry details and sentiment analysis results.

[0891] Processing: The server sends the inquiry details and sentiment analysis results to a generative AI API. The generative AI API generates the optimal response based on the received information.

[0892] Operation: The server sends data to a generative AI API and sets prompts to generate the optimal response.

[0893] Output: Response data from a generative AI.

[0894] Step 5:

[0895] Generative AI generates the optimal answer.

[0896] Input: Prompts based on the inquiry content and sentiment analysis results.

[0897] Processing: The generative AI analyzes the input prompt and generates an appropriate response to the inquiry. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[0898] Operation: Generative AI uses internal algorithms to analyze the content and sentiment of inquiries and construct responses.

[0899] Output: Generated response data.

[0900] Step 6:

[0901] The server formats the generated response.

[0902] Input: Response data generated by a generative AI.

[0903] Processing: The server formats the received response data for the user interface. This process includes converting JSON data to HTML or plain text.

[0904] Operation: The server converts the received data into an appropriate format and displays it in a way that is easy for the user to read.

[0905] Output: Formatted response data.

[0906] Step 7:

[0907] The server sends the formatted response to the user interface.

[0908] Input: Formatted response data.

[0909] Processing: The server sends the formatted response to the user interface, such as a chatbot screen or email system.

[0910] Operation: Data is sent from the server to the user interface and displayed on the terminal in real time.

[0911] Output: Response data displayed on the user's device.

[0912] Step 8:

[0913] The user receives the response.

[0914] Input: Formatted response data submitted from the user interface.

[0915] Processing: The user's device receives the response data and displays it on the screen.

[0916] Operation: Users review the responses via the chatbot screen or email client and decide on their next action.

[0917] Output: The user reviews the displayed answer.

[0918] (Application Example 2)

[0919] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0920] Traditional customer service systems often provide formulaic responses without considering user emotions, leading to decreased customer satisfaction. Furthermore, staff in physical stores lacked the means to provide appropriate answers and responses in real time, making efficient and effective customer service difficult.

[0921] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for sending the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate the optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for using an emotion engine to analyze the user's emotions, means for sending the emotion information analyzed by the emotion engine to the generative AI, and means for the generative AI to generate a more accurate answer based on the emotion information. This makes it possible for staff in physical stores to provide the optimal response in real time according to the customer's emotions.

[0922] The "user interface" is the part of a system that provides an interactive screen or form for users to input inquiry details and view the generated response.

[0923] A "server" is a central computer that receives user inquiries and manages and processes communication with databases, generative AI APIs, and emotion engines.

[0924] A "database" is a data management system used to store and manage information such as inquiry content, generated responses, and sentiment analysis results.

[0925] "Generative AI" refers to a system that uses artificial intelligence technology to analyze the content of an input inquiry and generate the most appropriate response.

[0926] A "generative AI API" is a programmatic interface for sending inquiries to a generative AI and obtaining the most appropriate response.

[0927] An "emotion engine" is a system that analyzes user emotions based on the content of their inquiries and the writing style they use.

[0928] "Formatting" refers to the process of converting the generated response into a format suitable for the user interface.

[0929] "Inquiry content" refers to questions or requests that users enter into the system.

[0930] "Answer" refers to the optimal response generated by a generative AI in response to an inquiry that has been analyzed.

[0931] This invention is a system that utilizes generative AI and an emotion engine to streamline user support at inquiry desks. Specific embodiments for carrying out this invention are described below.

[0932] System Configuration

[0933] This system consists of multiple components, including a user interface, server, generative AI API, emotion engine, and database.

[0934] User Interface (UI)

[0935] The user interface provides interactive screens and forms for users to input inquiries and review generated responses. Specifically, it is implemented as a smartphone or tablet application.

[0936] server

[0937] The server receives user inquiries and stores them in a database. It also sends the inquiry content to a generative AI API, formats the generated response, and sends it to the user interface. The server handles the main central processing and manages the coordination with the emotion engine and generative AI API.

[0938] Emotional Engine

[0939] The emotion engine analyzes user inquiries and interprets their emotions based on their writing style and keywords. The analyzed emotion information is sent to the generative AI via the server and used to improve the accuracy of the generated responses.

[0940] Generative AI API

[0941] The generative AI API generates the optimal response based on the user's inquiry and sentiment analysis results. The generated response is sent to the server and formatted for display in the user interface.

[0942] database

[0943] The database stores and manages information such as inquiry content, generated responses, and sentiment analysis results. This makes it possible to track the entire inquiry history.

[0944] Flow of operations

[0945] When a user enters an inquiry using a smartphone or tablet, that information is sent to the server. The server stores the received inquiry in a database and sends it to an emotion engine for sentiment analysis. The emotion information obtained from the emotion engine is sent to a generative AI to generate the optimal response. The generated response is returned to the server, formatted in a way that can be displayed to the user, and then sent to the user interface.

[0946] Specific example

[0947] For example, imagine a staff member at a physical store receiving a customer inquiry via smartphone asking, "Do you have this item in stock?" If the emotion engine analyzes the customer's emotion to be "anxiety," the generative AI uses this information to generate a response such as, "We have it in stock. However, it may take some time for the next shipment to arrive." This allows the staff member to respond quickly and appropriately.

[0948] Example of a prompt

[0949] Enter the following as the prompt:

[0950] Prompt: A customer in a store asks, "Do you have this item in stock?" Generate the best response using a generative AI model, incorporating the emotion analyzed as "anxiety" by the emotion engine.

[0951] The above describes the "mode for carrying out the invention." A system following this mode can improve the efficiency of user support and enhance customer satisfaction.

[0952] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0953] Step 1:

[0954] The user enters their inquiry.

[0955] Input: User input from smartphones or tablets (e.g., "Is this product in stock?").

[0956] Output: The entered query content is sent to the server.

[0957] Specific operation: When a user enters their inquiry into a text box on the user interface (UI) and presses the submit button, that text data is sent from the terminal to the server.

[0958] Step 2:

[0959] The server receives the query and saves it to the database.

[0960] Input: The content of the inquiry submitted by the user.

[0961] Output: The query details are saved in the database and registered along with the query ID and timestamp.

[0962] Specific operation: The server temporarily stores the received query in memory, establishes a database connection, and permanently stores the query. Metadata such as ID, user ID, and timestamp is attached to the query.

[0963] Step 3:

[0964] The server sends the query to the emotion engine, which then analyzes the emotions.

[0965] Input: The query content stored in the database.

[0966] Output: Emotional information analyzed by the emotion engine (e.g., "anxiety").

[0967] Specific operation: The server sends the stored query content to the sentiment engine's API, and the sentiment engine analyzes the writing style and keywords to return sentiment information. The server receives this sentiment information.

[0968] Step 4:

[0969] The server sends the inquiry content and sentiment information to a generative AI API, which then generates the optimal response.

[0970] Input: Inquiry content and sentiment information returned by the sentiment engine.

[0971] Output: Response generated from a generative AI API (e.g., "We have stock. However, it may take some time before the next shipment arrives.").

[0972] Specific operation: The server combines the inquiry content and sentiment information and sends it to a generative AI API. The generative AI then performs natural language processing based on this information, generates the optimal response, and sends it to the server.

[0973] Step 5:

[0974] The server receives the generated response and formats it for the user interface.

[0975] Input: Response received from a generative AI.

[0976] Output: Formatted response data.

[0977] Specific operation: The server converts the received response from JSON format to HTML or plain text format and formats it so that it can be displayed in the user interface.

[0978] Step 6:

[0979] The server sends the formatted response to the user interface, and the user receives the response.

[0980] Input: Formatted response data.

[0981] Output: The answer displayed on the user interface.

[0982] Specific operation: The server sends the formatted response to the terminal and visualizes it in the user interface. The user can view the response on their smartphone or tablet screen.

[0983] This allows users to receive optimal responses tailored to their emotions in real time, streamlining customer service in physical stores.

[0984] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0985] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0986] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0987] [Third Embodiment]

[0988] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0989] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0990] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0991] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0992] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0993] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0994] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0995] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0996] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0997] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0998] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0999] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1000] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[1001] System Overview

[1002] This system mainly consists of the following components:

[1003] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1004] 2. Server: Receives the query content and communicates with the database and generative AI.

[1005] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1006] 4. Database: Stores and manages inquiry content and its responses.

[1007] Program processing

[1008] Inquiry reception

[1009] Users enter their inquiries via chatbots or email forms. For example, a user might type, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[1010] Receiving and saving inquiry details

[1011] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and inquiry timestamp are recorded. This allows the entire inquiry history to be tracked.

[1012] Sending to a generative AI

[1013] The server formats the received query and sends it to the generative AI API. The generative AI API analyzes the query data sent from the server and performs natural language processing to understand the intent of the query.

[1014] Answer generation

[1015] The generative AI analyzes the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days." This response is sent back to the server in real time.

[1016] Receiving and formatting responses

[1017] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[1018] Submit and display of responses

[1019] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days."

[1020] Specific example

[1021] Case 1: Inquiry via chat

[1022] 1. User enters inquiry: User: "Please explain the return process."

[1023] 2. Server receives and saves query: The query content is saved to the database.

[1024] 3. Analysis of the inquiry: Generative AI analyzes "Please tell me about the return process."

[1025] 4. Response generation: The generation AI generates "For information on the return process, please read the following steps..."

[1026] 5. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1027] 6. The user receives the response: The chatbot displays the response to the user.

[1028] Case 2: Inquiry via email

[1029] 1. User enters inquiry: User: "How do I place an additional order?"

[1030] 2. Server receives and saves query: The query content is saved to the database.

[1031] 3. Analysis of the inquiry: The generative AI analyzes the inquiry "How do I place an additional order?"

[1032] 4. Response generation: The generation AI generates the message, "For instructions on how to place an additional order, please proceed through your My Page on the online store."

[1033] 5. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1034] 6. The user receives the response: The email client displays the response to the user.

[1035] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and responses in a database, it can also be used for future service improvements.

[1036] The following describes the processing flow.

[1037] Step 1:

[1038] The user enters their inquiry.

[1039] Users enter their inquiries into the chatbot or email form on their device. For example, they might type, "What is the delivery date for the product?"

[1040] Step 2:

[1041] The server receives the query and saves it to the database.

[1042] The server receives query data from the user interface.

[1043] The server saves the received query data to a database. The query ID, user ID, timestamp, and query content are recorded.

[1044] Step 3:

[1045] The server prepares to send the query content to the generative AI API.

[1046] The server formats the query content into a format that the generative AI API can understand (for example, JSON format).

[1047] Step 4:

[1048] The server sends the query content to the generative AI API.

[1049] The server sends the formatted query data to the endpoint of the generative AI API.

[1050] Step 5:

[1051] A generative AI analyzes the content of the inquiry.

[1052] Generative AI analyzes received data to extract the intent and keywords of inquiries. For example, generative AI might extract information related to "product delivery dates."

[1053] Step 6:

[1054] The generative AI generates the optimal answer.

[1055] Generative AI generates the optimal answer based on the analysis results. For example, it might generate the answer, "The delivery time for products is usually 3 to 5 business days."

[1056] Step 7:

[1057] The server receives the response generated by the generative AI.

[1058] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[1059] Step 8:

[1060] The server formats the received response for the user interface.

[1061] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[1062] Step 9:

[1063] The server sends the formatted response to the user interface.

[1064] The server sends the formatted response to the chatbot or email system.

[1065] Step 10:

[1066] The user receives the response on their device.

[1067] The response will be displayed on the chatbot screen or email client on the user's device. For example, it might say, "The delivery time for products is usually 3-5 business days."

[1068] In this way, the system ensures that the entire process, from the user submitting an inquiry to receiving a response, is carried out quickly and efficiently.

[1069] (Example 1)

[1070] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1071] Traditional inquiry handling systems often resulted in long waiting times between user inquiry submission and response, and sometimes generated inconsistent answers. Furthermore, inadequate management of inquiry history prevented the effective utilization of past inquiry information. This led to decreased user satisfaction and hindered the efficiency of corporate response processes.

[1072] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1073] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer, and send it to the user interface, means for the user to receive the answer, means for the inquiry content to be sent to the server in real time, means for the server to store the inquiry ID, user ID, and timestamp for the received inquiry content in a database, means for the server to convert the JSON format data to HTML or plain text after receiving the answer from the generative AI, means for the server to send the formatted answer to the user interface in real time, and means for displaying the formatted answer on the user's terminal. This enables a rapid and consistent response to inquiries, improving user satisfaction and the efficiency of corporate responses.

[1074] A "user" refers to an individual or organization that uses the system to make an inquiry.

[1075] "Inquiry details" refers to information including questions and requests entered by the user into the system.

[1076] A "server" refers to a computer system that receives and processes inquiries.

[1077] A "database" refers to a collection of digital information used to store and manage inquiries and the responses to them.

[1078] "Generative AI" refers to an artificial intelligence system that analyzes user inquiries and generates appropriate responses.

[1079] An "API" refers to an interface for exchanging data between a server and a generative AI.

[1080] "Formatting" refers to the process of converting data or information into a specific format.

[1081] "User interface" refers to the screen or form on which a user makes an inquiry and receives a response.

[1082] A "timestamp" refers to information indicating the date and time the inquiry was made.

[1083] "Real-time" refers to a state where user actions and inquiries are responded to immediately.

[1084] "JSON format" is a type of data exchange format, and is an abbreviation for JavaScript Object Notation.

[1085] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[1086] System Overview

[1087] This system mainly consists of the following components:

[1088] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1089] 2. Server: Receives the query content and communicates with the database and generative AI.

[1090] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1091] 4. Database: Stores and manages inquiry content and its responses.

[1092] Program processing

[1093] The program processes the information as follows: First, the user enters their inquiry via a chatbot or email form. For example, the user might enter, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[1094] The server saves the received query content to a database. The information saved includes the query ID, user ID, and query timestamp. This makes it possible to track the entire query history. Next, the server formats the received query content and sends it to the generative AI API.

[1095] The generative AI API analyzes inquiry data sent from the server and performs natural language processing to understand the intent of the inquiry. The generative AI analyzes the content of the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3 to 5 business days." This response is sent back to the server in real time.

[1096] The server receives responses from the generative AI and formats them for the user interface. For example, it converts JSON data to HTML or plain text. The formatted response is sent from the server to the user interface, and the user's device displays a message such as "Product delivery time is usually 3-5 business days" on the chatbot screen or in their email client.

[1097] Specific example

[1098] Case 1: Inquiry via chat

[1099] 1. User enters inquiry: The user enters "Please explain the return process."

[1100] 2. Server receives and saves query: The server saves the query content to the database.

[1101] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[1102] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to "Please tell me about the return process" (e.g., "For information on the return process, please read the following steps...").

[1103] 5. Server receives and formats the generated response: The server receives the response from the generation AI and formats it in HTML format.

[1104] 6. Server sends response to terminal, user receives: The server sends the formatted response to the chatbot's UI, which is then displayed to the user on the chatbot screen.

[1105] Case 2: Inquiry via email

[1106] 1. User enters inquiry: The user enters "Please tell me how to place an additional order" into the email form.

[1107] 2. Server receives and saves query: The server saves the query content to the database.

[1108] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[1109] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to the question "How do I place an additional order?" (Example: "To place an additional order, please proceed through your My Page on the online store.").

[1110] 5. Server receives and formats the generated response: The server receives the response from the generative AI and formats it in plain text format.

[1111] 6. Server sends response to terminal, user receives: The server sends the formatted response to the email system, and the user's email client displays a message saying, "For instructions on how to place an additional order, please proceed from your online store's My Page."

[1112] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and their responses in a database, it can also be used for future service improvements. This system makes it possible to improve user satisfaction and increase the operational efficiency of companies.

[1113] Example of a prompt

[1114] "When is the product due?"

[1115] "Please tell me about the return process."

[1116] "Please tell me how to place an additional order."

[1117] By entering these prompts, the generative AI will provide the corresponding answer.

[1118] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1119] Step 1:

[1120] The user enters an inquiry.

[1121] The user enters their inquiry using a terminal. For example, the user might enter, "What is the delivery date for the product?" This becomes the input data. The terminal then sends the entered inquiry to the server in real time.

[1122] Step 2:

[1123] The server receives the query.

[1124] The server receives user inquiries in real time. This received data becomes the input data. The server first saves the received inquiry content to a database. When saving, it also records additional information such as the inquiry ID, user ID, and timestamp. This makes it possible to track the inquiry history.

[1125] Step 3:

[1126] The server formats the query content.

[1127] The server retrieves query data stored in the database and converts it into the format necessary for sending it to the generative AI. This format conversion is data processing. For example, the query data is converted into JSON format. The converted JSON data becomes the output data.

[1128] Step 4:

[1129] The server sends the formatted query content to the generation AI API.

[1130] The server sends formatted JSON data to the generative AI API. This becomes the input data. The server performs error checking and data integrity verification during transmission. Once the generative AI receives the data, it begins analyzing the query.

[1131] Step 5:

[1132] The generative AI analyzes the inquiry and generates a response.

[1133] The generative AI analyzes the JSON-formatted query received from the server. This analysis is data processing. The generative AI uses natural language processing techniques to understand the intent of the query and generate an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3-5 business days." This generated response becomes the output data.

[1134] Step 6:

[1135] The server receives the response from the generative AI.

[1136] The server receives the response generated by the generative AI. The received response data in JSON format becomes the input data. The server then performs a verification process on the received data for comparison.

[1137] Step 7:

[1138] The server formats the generated response.

[1139] The server formats the received JSON response for the user interface. Specifically, it converts the JSON data into HTML or plain text. This format conversion is data processing. The converted data becomes the output data.

[1140] Step 8:

[1141] The server sends the formatted response to the user interface.

[1142] The server sends the formatted response data to the user's terminal. The converted data is sent as input data. The server checks the data integrity and confirms delivery upon transmission.

[1143] Step 9:

[1144] The answer will be displayed on the user's device.

[1145] The user's device receives a formatted response sent from the server. This received data becomes the input data. The device then displays the received data appropriately. For example, it might display "Product delivery time is usually 3-5 business days" on the chatbot screen or in the email client.

[1146] Through these steps, users' inquiries will be answered quickly and appropriately.

[1147] (Application Example 1)

[1148] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1149] Electronic payment services require prompt and accurate responses to user inquiries. However, traditional systems often resulted in inconsistent quality in inquiry handling, frequently lowering user satisfaction. Furthermore, there was a lack of efficient methods for managing inquiry content and response history. As a result, inquiry handling took a significant amount of time, negatively impacting user convenience.

[1150] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1151] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to a user interface, means for the user to receive the answer, means for handling inquiries using an application installed on a smartphone, smart glasses, head-mounted display, or robot, and means for processing inquiries related to electronic payment services. This makes it possible to improve the quality of inquiry handling and enhance user convenience.

[1152] A "server" is a computer system that receives user inquiries, stores them in a database, and sends them to a generative AI API.

[1153] A "user interface" is a means of providing a screen or form for a user to input their inquiry and receive a generated response.

[1154] "Generative AI" refers to artificial intelligence that analyzes inquiries and generates the most appropriate response.

[1155] A "generative AI API" is an application programming interface for sending and receiving query data between a server and a generative AI.

[1156] A "database" is a system for storing and managing query content and generated responses.

[1157] A "smartphone" is a portable computer device used to input inquiries and receive generated responses.

[1158] "Smart glasses" are wearable devices used by users to input inquiries and receive generated responses.

[1159] A "head-mounted display" is a display device worn by the user, used for inputting inquiries and receiving generated responses.

[1160] A "robot" is an automated machine programmed to handle inquiries.

[1161] An "electronic payment service" is a system that allows users to pay electronically for goods and services they purchase online or in physical stores.

[1162] "Inquiry history" refers to a record of user inquiries and the corresponding responses.

[1163] The system for implementing this invention automates the reception, analysis, and response generation of inquiries, thereby improving the efficiency of handling inquiries related to electronic payment services. Specifically, it uses the following hardware and software.

[1164] System Overview

[1165] hardware

[1166] 1. Server: A high-performance computer server receives user inquiries and sends data to the generative AI. It also stores the inquiry content and its response in a database.

[1167] 2. User terminal: This refers to devices such as smartphones, smart glasses, head-mounted displays, and robots. These are used by users to input inquiries and display generated responses.

[1168] software

[1169] 1. User Interface (UI): The screen or form on which a user enters an inquiry and receives a generated response. Frameworks such as React Native or Flutter are used.

[1170] 2. Server Application: Built using Node.js and Express. It receives, stores, and sends query data to the generation AI, formats the generated responses, and sends them to the user's terminal.

[1171] 3. Generative AI: A generative AI model (e.g., GPT-4) is used to analyze the inquiry content and generate an appropriate response.

[1172] 4. Database: Use a relational database such as MySQL to manage queries and their responses.

[1173] Program processing

[1174] Receiving and saving inquiries

[1175] The user enters their inquiry through a smartphone application. For example, an inquiry such as, "What should I do about a canceled payment?" The server receives this inquiry and saves it to a database. The inquiry ID, user ID, and timestamp are recorded.

[1176] Sending to a generative AI

[1177] The server sends the received query to a generative AI API. The generative AI analyzes the query and uses natural language processing techniques to understand its intent. It then generates an appropriate response.

[1178] Answer generation and formatting

[1179] The generative AI generates a response such as, "For canceled payments, please follow these instructions..." This response is sent back to the server in real time. The server formats the received response for display to the user. For example, it converts JSON data into plain text.

[1180] Submit and display of responses

[1181] The formatted response is sent from the server to the user interface. The user's device, such as a smartphone or smart glasses screen, displays a response such as, "For canceled payments, please follow these instructions."

[1182] Specific example

[1183] Example 1: Inquiry

[1184] The user typed "What should I do about the canceled payment?" into the smartphone app.

[1185] The server receives the data and saves it to the database.

[1186] Send to a generative AI API.

[1187] The generative AI analyzes the data and generates a response saying, "For canceled payments, please follow these instructions."

[1188] The server formats the file and sends it to the user's terminal.

[1189] The user checks their answer on their smartphone.

[1190] Example of a prompt

[1191] "This is an inquiry regarding electronic payment cancellations. A user has asked about the payment cancellation process. Please provide an appropriate answer."

[1192] "A user is inquiring about a failed payment method. Please generate specific instructions."

[1193] By implementing this invention, the efficiency and quality of handling inquiries are improved, and user convenience is significantly enhanced.

[1194] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1195] Step 1:

[1196] The user enters their inquiry using a device (e.g., a smartphone). For example, they might enter an inquiry such as "What should I do about a canceled payment?" into the application screen. This input is sent to the server in real time through the UI component.

[1197] Step 2:

[1198] The server receives the query content sent from the terminal. The received content is stored in the database. Metadata such as the query ID, user ID, and timestamp is also stored here. The input is the query content, and the output is the record stored in the database.

[1199] Step 3:

[1200] The server formats the received query and sends it to the generative AI API. For example, it prepares the query as JSON data and sends a request to the API endpoint. The input is the formatted query, and the output is the request to the generative AI.

[1201] Step 4:

[1202] The generative AI analyzes the inquiry content and performs natural language processing to understand its intent. It then generates an appropriate response. For example, it might generate the prompt "For canceled payments, please follow these steps." The input is the received inquiry, and the output is the generated response.

[1203] Step 5:

[1204] The server receives the responses generated by the generative AI. The server then formats the received responses for the user interface. For example, it might convert JSON data to plain text. The input is the generated response, and the output is the formatted response.

[1205] Step 6:

[1206] The server sends a formatted response to the user interface. It converts the response to a format that can be displayed on the application's chat screen and sends it to the user's device. The input is the formatted response, and the output is the display of the response on the user's device.

[1207] Step 7:

[1208] The user's device displays the response received from the server. The user sees a specific response on their smartphone screen, such as "For canceled payments, please follow these instructions." The input is the formatted response received from the server, and the output is the display on the user's screen.

[1209] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1210] This invention relates to a system that achieves more accurate responses by combining a system that uses generative AI to streamline customer service responses with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1211] System Overview

[1212] This system mainly consists of the following components:

[1213] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1214] 2. Server: Receives the query content and communicates with the database and generative AI.

[1215] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1216] 4. Emotion Engine: Analyzes user emotions from the content of their inquiries and the writing style used during input.

[1217] 5. Database: Stores and manages inquiry content, responses, and sentiment analysis results.

[1218] Program processing

[1219] Inquiry reception

[1220] Users enter their inquiries via chatbots or email forms. For example, a user might type, "When is the delivery date for the product? Is it too late?" This inquiry is sent to the server in real time.

[1221] Receiving and saving inquiry details

[1222] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and timestamp are recorded. This allows the entire inquiry history to be tracked.

[1223] Analysis using an emotion engine

[1224] The server sends the received inquiry to the sentiment engine. The sentiment engine analyzes the user's emotions based on the style and keywords of the inquiry. For example, from the sentence "Is it too late?", the sentiment engine might determine that the user is irritated.

[1225] Sending to a generative AI

[1226] The server sends the inquiry details, including the sentiment analysis results obtained from the sentiment engine, to the generative AI API. The generative AI API then generates the optimal response based on the inquiry data and sentiment analysis results.

[1227] Answer generation

[1228] The generative AI generates the optimal response based on the analysis results. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions." This response is sent back to the server in real time.

[1229] Receiving and formatting responses

[1230] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[1231] Submit and display of responses

[1232] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1233] Specific example

[1234] Case 1: How to calm frustration in a chat

[1235] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[1236] 2. Server receives and saves query: The query content is saved to the database.

[1237] 3. Emotional Engine Analysis: Detecting frustration from "Is it too late?"

[1238] 4. Sending to the Generative AI: Send the content of your inquiry and your frustration to the Generative AI.

[1239] 5. Generate response: Generate the response: "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1240] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1241] 7. The user receives the response: The chatbot displays the response.

[1242] Case Study 2: Responding to a thank-you message via email

[1243] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[1244] 2. Server receives and saves query: The query content is saved to the database.

[1245] 3. Analysis using an emotion engine: Detecting gratitude from "Thank you."

[1246] 4. Sending to the Generative AI: Send the inquiry details and your thanks to the Generative AI.

[1247] 5. Generating the response: Generate the response: "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[1248] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1249] 7. The user receives the response: The email client displays the response.

[1250] This system recognizes user emotions and responds accordingly, thereby improving user satisfaction and enabling efficient inquiry handling. The emotion analysis results are stored in a database and can be used for future service improvements.

[1251] The following describes the processing flow.

[1252] Step 1:

[1253] The user enters their inquiry.

[1254] Users type "When is the product due? Is it too late?" into the chatbot or email form on their device.

[1255] Step 2:

[1256] The server receives the query and saves the query details to the database.

[1257] The server receives the inquiry details from the user interface.

[1258] The server saves the received query data (query ID, user ID, timestamp, and query content) to the database.

[1259] Step 3:

[1260] The server prepares to send the query content to the emotion engine.

[1261] The server formats the query content into a format that the sentiment engine can analyze (for example, text format).

[1262] Step 4:

[1263] The server sends the query to the emotion engine.

[1264] The server sends the formatted query data to the sentiment engine.

[1265] Step 5:

[1266] The emotion engine analyzes the content of the inquiry.

[1267] The emotion engine analyzes the received data and detects the user's emotions from the style and keywords of the inquiry. For example, it might determine that the user is feeling frustrated from the phrase, "Is it too late?"

[1268] Step 6:

[1269] The server receives the emotion analysis results from the emotion engine.

[1270] The server receives the emotion analysis results sent from the emotion engine.

[1271] The server stores the query data and sentiment analysis results in a database.

[1272] Step 7:

[1273] The server prepares to send the inquiry details and sentiment analysis results to the generative AI API.

[1274] The server formats the inquiry content and sentiment analysis results into a format that the generative AI API can understand (for example, JSON format).

[1275] Step 8:

[1276] The server sends the query content and sentiment analysis results to the generative AI API.

[1277] The server sends the formatted query content and sentiment analysis results to the generative AI API endpoint.

[1278] Step 9:

[1279] A generative AI analyzes the content of the inquiry and the results of the sentiment analysis.

[1280] Generative AI analyzes received data and generates the most appropriate response tailored to the user's intent and emotional state. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1281] Step 10:

[1282] The server receives the response generated by the generative AI.

[1283] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[1284] Step 11:

[1285] The server formats the received response for the user interface.

[1286] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[1287] Step 12:

[1288] The server sends the formatted response to the user interface.

[1289] The server sends the formatted response to the chatbot or email system.

[1290] Step 13:

[1291] The user receives the response on their device.

[1292] The user's device will display a message via chatbot or email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us for further assistance if you have any questions."

[1293] In this way, this system enables the analysis of user emotions and the response accordingly, thereby improving user satisfaction.

[1294] (Example 2)

[1295] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1296] Traditional customer service systems often use canned responses without considering user emotions, resulting in decreased user satisfaction. Furthermore, managing inquiry content while incorporating sentiment analysis results was difficult. This led to problems with the quality and efficiency of responses.

[1297] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1298] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to an emotion analysis engine and analyze the user's emotions, means for the server to send the inquiry content and emotion analysis results to a generative AI API, means for the generative AI to generate an optimal answer based on the inquiry content and emotion analysis results, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for the user to receive the answer, and means for storing the inquiry content, generated answer, and emotion analysis results in a database and managing the inquiry history. This makes it possible to quickly provide the optimal answer while taking the user's emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[1299] A "user" is a person or group that accesses the system and enters their inquiry.

[1300] "Inquiry details" refer to information such as questions and requests that users enter and send to the system.

[1301] A "server" is a computer system that receives queries, performs necessary processing, and interacts with databases and other components.

[1302] A "database" is an information storage system that stores and manages inquiry content, responses, and sentiment analysis results.

[1303] A "sentiment analysis engine" is software and algorithms that analyze the content of inquiries and determine the user's emotions.

[1304] A "generative AI API" is an application programming interface for artificial intelligence that operates based on the content of an inquiry and the results of sentiment analysis in order to provide an appropriate generated response.

[1305] "Formatting" refers to the process of shaping the response obtained from a generative AI for use in a user interface.

[1306] A "user interface" refers to the elements of interaction, including screens and forms, that allow a user to input inquiries into a system and receive generated responses.

[1307] "Inquiry history" refers to a record of all past inquiries, the responses to those inquiries, and data including sentiment analysis results.

[1308] This invention relates to a system that improves user satisfaction by streamlining customer service response using generative AI and an emotion analysis engine. Specific embodiments of this invention are described below.

[1309] Hardware and software to be used

[1310] To implement the invention, the following hardware and software are used.

[1311] Hardware:

[1312] Server: Receives, stores, and communicates with the AI ​​API for generating queries.

[1313] Terminal: A device (such as a PC or smartphone) used by the user to enter their inquiry and receive a response.

[1314] software:

[1315] Database: A system for storing and managing inquiry content, responses, and sentiment analysis results.

[1316] Sentiment analysis engine: Software that analyzes inquiry content and determines the user's emotions.

[1317] Generative AI API: An API for generating the optimal response based on the content of the inquiry and the results of sentiment analysis.

[1318] User interface: A screen or form on which a user enters their inquiry and receives a response.

[1319] Data processing and calculation

[1320] server

[1321] 1. The server receives data from forms or chatbots where users enter their inquiries.

[1322] 2. Save the received inquiry details to the database. At this time, metadata such as the inquiry ID, user ID, and timestamp will also be recorded.

[1323] 3. The server sends the saved query content to the sentiment analysis engine. The sentiment analysis engine analyzes the writing style and keywords to determine the user's emotions.

[1324] 4. The server that receives the sentiment analysis results sends the inquiry content and sentiment analysis results to the generative AI API.

[1325] 5. The generative AI generates the optimal response based on the inquiry content and sentiment analysis results, and returns the result to the server.

[1326] 6. The server formats the generated response for the user interface and sends the response to the terminal.

[1327] terminal

[1328] 1. Users enter their inquiries using their devices. For example, they might use a website's chatbot screen or email form.

[1329] 2. The user receives the response sent from the server on their device. They then review the formatted response using a chatbot or email app.

[1330] Examples of specific cases and prompt statements

[1331] Example 1: Handling inquiries via chat

[1332] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[1333] 2. Server receives and stores query: The server stores the query content in the database.

[1334] 3. Emotional analysis: The emotional analysis engine detects frustration from the phrase "Is it too late?"

[1335] 4. Sending to the Generative AI: The server sends the query content and the frustration to the Generative AI.

[1336] 5. Response Generation: The generation AI generates the response: "The delivery time for products is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1337] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1338] 7. The user receives the response: The user confirms the response via the chatbot.

[1339] Example 2: Responding to inquiries via email

[1340] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[1341] 2. Server receives and stores query: The server stores the query content in the database.

[1342] 3. Analysis by the emotion engine: The emotion analysis engine detects gratitude from "Thank you."

[1343] 4. Sending to the Generative AI: The server sends the inquiry details and a message of thanks to the Generative AI.

[1344] 5. Response generation: The generation AI generates the response, "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[1345] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1346] 7. The user receives the response: The user confirms the response via their email client.

[1347] Example of a prompt

[1348] 1. A prompt to calm frustration during a chat: "When is the product due? Is it too late?"

[1349] 2. Prompt response to a thank-you email: "Thank you as always. Please let me know about your next sale."

[1350] This embodiment makes it possible to quickly provide the optimal answer while taking user emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[1351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1352] Step 1:

[1353] The user enters an inquiry.

[1354] Input: The user enters their inquiry into a chatbot or email form.

[1355] Processing: The user enters, for example, "When is the delivery date for the product? Is it too late?"

[1356] Operation: The entered inquiry content is displayed in the terminal's input field, and when the submit button is pressed, that content is sent to the server.

[1357] Output: The user's inquiry is sent to the server.

[1358] Step 2:

[1359] The server receives and stores the query.

[1360] Input: The content of the inquiry submitted by the user.

[1361] Processing: The server receives the query in real time. The received content is analyzed and saved to the database along with the relevant metadata (query ID, user ID, timestamp, etc.).

[1362] Operation: The server adds the query content to the database as a new record. This makes the query content traceable within the system.

[1363] Output: The query details are saved in the database.

[1364] Step 3:

[1365] The server sends the inquiry details to the sentiment analysis engine.

[1366] Input: The query content stored in the database.

[1367] Processing: The server sends the inquiry content as an API request to the sentiment analysis engine. The sentiment analysis engine analyzes the user's emotions using the writing style and keywords.

[1368] Operation: The server sends data to the sentiment analysis engine using an HTTP POST request and receives the analysis results.

[1369] Output: Sentiment analysis results from the emotion analysis engine.

[1370] Step 4:

[1371] The server sends the sentiment analysis results and inquiry content to a generative AI API.

[1372] Input: Inquiry details and sentiment analysis results.

[1373] Processing: The server sends the inquiry details and sentiment analysis results to a generative AI API. The generative AI API generates the optimal response based on the received information.

[1374] Operation: The server sends data to a generative AI API and sets prompts to generate the optimal response.

[1375] Output: Response data from a generative AI.

[1376] Step 5:

[1377] Generative AI generates the optimal answer.

[1378] Input: Prompts based on the inquiry content and sentiment analysis results.

[1379] Processing: The generative AI analyzes the input prompt and generates an appropriate response to the inquiry. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1380] Operation: Generative AI uses internal algorithms to analyze the content and sentiment of inquiries and construct responses.

[1381] Output: Generated response data.

[1382] Step 6:

[1383] The server formats the generated response.

[1384] Input: Response data generated by a generative AI.

[1385] Processing: The server formats the received response data for the user interface. This process includes converting JSON data to HTML or plain text.

[1386] Operation: The server converts the received data into an appropriate format and displays it in a way that is easy for the user to read.

[1387] Output: Formatted response data.

[1388] Step 7:

[1389] The server sends the formatted response to the user interface.

[1390] Input: Formatted response data.

[1391] Processing: The server sends the formatted response to the user interface, such as a chatbot screen or email system.

[1392] Operation: Data is sent from the server to the user interface and displayed on the terminal in real time.

[1393] Output: Response data displayed on the user's device.

[1394] Step 8:

[1395] The user receives the response.

[1396] Input: Formatted response data submitted from the user interface.

[1397] Processing: The user's device receives the response data and displays it on the screen.

[1398] Operation: Users review the responses via the chatbot screen or email client and decide on their next action.

[1399] Output: The user reviews the displayed answer.

[1400] (Application Example 2)

[1401] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1402] Traditional customer service systems often provide formulaic responses without considering user emotions, leading to decreased customer satisfaction. Furthermore, staff in physical stores lacked the means to provide appropriate answers and responses in real time, making efficient and effective customer service difficult.

[1403] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for sending the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate the optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for using an emotion engine to analyze the user's emotions, means for sending the emotion information analyzed by the emotion engine to the generative AI, and means for the generative AI to generate a more accurate answer based on the emotion information. This makes it possible for staff in physical stores to provide the optimal response in real time according to the customer's emotions.

[1404] The "user interface" is the part of a system that provides an interactive screen or form for users to input inquiry details and view the generated response.

[1405] A "server" is a central computer that receives user inquiries and manages and processes communication with databases, generative AI APIs, and emotion engines.

[1406] A "database" is a data management system used to store and manage information such as inquiry content, generated responses, and sentiment analysis results.

[1407] "Generative AI" refers to a system that uses artificial intelligence technology to analyze the content of an input inquiry and generate the most appropriate response.

[1408] A "generative AI API" is a programmatic interface for sending inquiries to a generative AI and obtaining the most appropriate response.

[1409] An "emotion engine" is a system that analyzes user emotions based on the content of their inquiries and the writing style they use.

[1410] "Formatting" refers to the process of converting the generated response into a format suitable for the user interface.

[1411] "Inquiry content" refers to questions or requests that users enter into the system.

[1412] "Answer" refers to the optimal response generated by a generative AI in response to an inquiry that has been analyzed.

[1413] This invention is a system that utilizes generative AI and an emotion engine to streamline user support at inquiry desks. Specific embodiments for carrying out this invention are described below.

[1414] System Configuration

[1415] This system consists of multiple components, including a user interface, server, generative AI API, emotion engine, and database.

[1416] User Interface (UI)

[1417] The user interface provides interactive screens and forms for users to input inquiries and review generated responses. Specifically, it is implemented as a smartphone or tablet application.

[1418] server

[1419] The server receives user inquiries and stores them in a database. It also sends the inquiry content to a generative AI API, formats the generated response, and sends it to the user interface. The server handles the main central processing and manages the coordination with the emotion engine and generative AI API.

[1420] Emotional Engine

[1421] The emotion engine analyzes user inquiries and interprets their emotions based on their writing style and keywords. The analyzed emotion information is sent to the generative AI via the server and used to improve the accuracy of the generated responses.

[1422] Generative AI API

[1423] The generative AI API generates the optimal response based on the user's inquiry and sentiment analysis results. The generated response is sent to the server and formatted for display in the user interface.

[1424] database

[1425] The database stores and manages information such as inquiry content, generated responses, and sentiment analysis results. This makes it possible to track the entire inquiry history.

[1426] Flow of operations

[1427] When a user enters an inquiry using a smartphone or tablet, that information is sent to the server. The server stores the received inquiry in a database and sends it to an emotion engine for sentiment analysis. The emotion information obtained from the emotion engine is sent to a generative AI to generate the optimal response. The generated response is returned to the server, formatted in a way that can be displayed to the user, and then sent to the user interface.

[1428] Specific example

[1429] For example, imagine a staff member at a physical store receiving a customer inquiry via smartphone asking, "Do you have this item in stock?" If the emotion engine analyzes the customer's emotion to be "anxiety," the generative AI uses this information to generate a response such as, "We have it in stock. However, it may take some time for the next shipment to arrive." This allows the staff member to respond quickly and appropriately.

[1430] Example of a prompt

[1431] Enter the following as the prompt:

[1432] Prompt: A customer in a store asks, "Do you have this item in stock?" Generate the best response using a generative AI model, incorporating the emotion analyzed as "anxiety" by the emotion engine.

[1433] The above describes the "mode for carrying out the invention." A system following this mode can improve the efficiency of user support and enhance customer satisfaction.

[1434] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1435] Step 1:

[1436] The user enters their inquiry.

[1437] Input: User input from smartphones or tablets (e.g., "Is this product in stock?").

[1438] Output: The entered query content is sent to the server.

[1439] Specific operation: When a user enters their inquiry into a text box on the user interface (UI) and presses the submit button, that text data is sent from the terminal to the server.

[1440] Step 2:

[1441] The server receives the query and saves it to the database.

[1442] Input: The content of the inquiry submitted by the user.

[1443] Output: The query details are saved in the database and registered along with the query ID and timestamp.

[1444] Specific operation: The server temporarily stores the received query in memory, establishes a database connection, and permanently stores the query. Metadata such as ID, user ID, and timestamp is attached to the query.

[1445] Step 3:

[1446] The server sends the query to the emotion engine, which then analyzes the emotions.

[1447] Input: The query content stored in the database.

[1448] Output: Emotional information analyzed by the emotion engine (e.g., "anxiety").

[1449] Specific operation: The server sends the stored query content to the sentiment engine's API, and the sentiment engine analyzes the writing style and keywords to return sentiment information. The server receives this sentiment information.

[1450] Step 4:

[1451] The server sends the inquiry content and sentiment information to a generative AI API, which then generates the optimal response.

[1452] Input: Inquiry content and sentiment information returned by the sentiment engine.

[1453] Output: Response generated from a generative AI API (e.g., "We have stock. However, it may take some time before the next shipment arrives.").

[1454] Specific operation: The server combines the inquiry content and sentiment information and sends it to a generative AI API. The generative AI then performs natural language processing based on this information, generates the optimal response, and sends it to the server.

[1455] Step 5:

[1456] The server receives the generated response and formats it for the user interface.

[1457] Input: Response received from a generative AI.

[1458] Output: Formatted response data.

[1459] Specific operation: The server converts the received response from JSON format to HTML or plain text format and formats it so that it can be displayed in the user interface.

[1460] Step 6:

[1461] The server sends the formatted response to the user interface, and the user receives the response.

[1462] Input: Formatted response data.

[1463] Output: The answer displayed on the user interface.

[1464] Specific operation: The server sends the formatted response to the terminal and visualizes it in the user interface. The user can view the response on their smartphone or tablet screen.

[1465] This allows users to receive optimal responses tailored to their emotions in real time, streamlining customer service in physical stores.

[1466] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1467] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1468] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1469] [Fourth Embodiment]

[1470] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1471] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1472] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1473] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1474] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1475] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1476] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1477] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1478] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1479] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1480] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1481] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1482] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1483] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[1484] System Overview

[1485] This system mainly consists of the following components:

[1486] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1487] 2. Server: Receives the query content and communicates with the database and generative AI.

[1488] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1489] 4. Database: Stores and manages inquiry content and its responses.

[1490] Program processing

[1491] Inquiry reception

[1492] Users enter their inquiries via chatbots or email forms. For example, a user might type, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[1493] Receiving and saving inquiry details

[1494] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and inquiry timestamp are recorded. This allows the entire inquiry history to be tracked.

[1495] Sending to a generative AI

[1496] The server formats the received query and sends it to the generative AI API. The generative AI API analyzes the query data sent from the server and performs natural language processing to understand the intent of the query.

[1497] Answer generation

[1498] The generative AI analyzes the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days." This response is sent back to the server in real time.

[1499] Receiving and formatting responses

[1500] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[1501] Submit and display of responses

[1502] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days."

[1503] Specific example

[1504] Case 1: Inquiry via chat

[1505] 1. User enters inquiry: User: "Please explain the return process."

[1506] 2. Server receives and saves query: The query content is saved to the database.

[1507] 3. Analysis of the inquiry: Generative AI analyzes "Please tell me about the return process."

[1508] 4. Response generation: The generation AI generates "For information on the return process, please read the following steps..."

[1509] 5. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1510] 6. The user receives the response: The chatbot displays the response to the user.

[1511] Case 2: Inquiry via email

[1512] 1. User enters inquiry: User: "How do I place an additional order?"

[1513] 2. Server receives and saves query: The query content is saved to the database.

[1514] 3. Analysis of the inquiry: The generative AI analyzes the inquiry "How do I place an additional order?"

[1515] 4. Response generation: The generation AI generates the message, "For instructions on how to place an additional order, please proceed through your My Page on the online store."

[1516] 5. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1517] 6. The user receives the response: The email client displays the response to the user.

[1518] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and responses in a database, it can also be used for future service improvements.

[1519] The following describes the processing flow.

[1520] Step 1:

[1521] The user enters their inquiry.

[1522] Users enter their inquiries into the chatbot or email form on their device. For example, they might type, "What is the delivery date for the product?"

[1523] Step 2:

[1524] The server receives the query and saves it to the database.

[1525] The server receives query data from the user interface.

[1526] The server saves the received query data to a database. The query ID, user ID, timestamp, and query content are recorded.

[1527] Step 3:

[1528] The server prepares to send the query content to the generative AI API.

[1529] The server formats the query content into a format that the generative AI API can understand (for example, JSON format).

[1530] Step 4:

[1531] The server sends the query content to the generative AI API.

[1532] The server sends the formatted query data to the endpoint of the generative AI API.

[1533] Step 5:

[1534] A generative AI analyzes the content of the inquiry.

[1535] Generative AI analyzes received data to extract the intent and keywords of inquiries. For example, generative AI might extract information related to "product delivery dates."

[1536] Step 6:

[1537] The generative AI generates the optimal answer.

[1538] Generative AI generates the optimal answer based on the analysis results. For example, it might generate the answer, "The delivery time for products is usually 3 to 5 business days."

[1539] Step 7:

[1540] The server receives the response generated by the generative AI.

[1541] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[1542] Step 8:

[1543] The server formats the received response for the user interface.

[1544] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[1545] Step 9:

[1546] The server sends the formatted response to the user interface.

[1547] The server sends the formatted response to the chatbot or email system.

[1548] Step 10:

[1549] The user receives the response on their device.

[1550] The response will be displayed on the chatbot screen or email client on the user's device. For example, it might say, "The delivery time for products is usually 3-5 business days."

[1551] In this way, the system ensures that the entire process, from the user submitting an inquiry to receiving a response, is carried out quickly and efficiently.

[1552] (Example 1)

[1553] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1554] Traditional inquiry handling systems often resulted in long waiting times between user inquiry submission and response, and sometimes generated inconsistent answers. Furthermore, inadequate management of inquiry history prevented the effective utilization of past inquiry information. This led to decreased user satisfaction and hindered the efficiency of corporate response processes.

[1555] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1556] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer, and send it to the user interface, means for the user to receive the answer, means for the inquiry content to be sent to the server in real time, means for the server to store the inquiry ID, user ID, and timestamp for the received inquiry content in a database, means for the server to convert the JSON format data to HTML or plain text after receiving the answer from the generative AI, means for the server to send the formatted answer to the user interface in real time, and means for displaying the formatted answer on the user's terminal. This enables a rapid and consistent response to inquiries, improving user satisfaction and the efficiency of corporate responses.

[1557] A "user" refers to an individual or organization that uses the system to make an inquiry.

[1558] "Inquiry details" refers to information including questions and requests entered by the user into the system.

[1559] A "server" refers to a computer system that receives and processes inquiries.

[1560] A "database" refers to a collection of digital information used to store and manage inquiries and the responses to them.

[1561] "Generative AI" refers to an artificial intelligence system that analyzes user inquiries and generates appropriate responses.

[1562] An "API" refers to an interface for exchanging data between a server and a generative AI.

[1563] "Formatting" refers to the process of converting data or information into a specific format.

[1564] "User interface" refers to the screen or form on which a user makes an inquiry and receives a response.

[1565] A "timestamp" refers to information indicating the date and time the inquiry was made.

[1566] "Real-time" refers to a state where user actions and inquiries are responded to immediately.

[1567] "JSON format" is a type of data exchange format, and is an abbreviation for JavaScript Object Notation.

[1568] This invention relates to a system that uses generative AI to streamline customer service inquiries. This system integrates multiple components to process user inquiries with rapid and consistent responses. Specific embodiments are described below.

[1569] System Overview

[1570] This system mainly consists of the following components:

[1571] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1572] 2. Server: Receives the query content and communicates with the database and generative AI.

[1573] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1574] 4. Database: Stores and manages inquiry content and its responses.

[1575] Program processing

[1576] The program processes the information as follows: First, the user enters their inquiry via a chatbot or email form. For example, the user might enter, "What is the delivery date for the product?" This inquiry is sent to the server in real time.

[1577] The server saves the received query content to a database. The information saved includes the query ID, user ID, and query timestamp. This makes it possible to track the entire query history. Next, the server formats the received query content and sends it to the generative AI API.

[1578] The generative AI API analyzes inquiry data sent from the server and performs natural language processing to understand the intent of the inquiry. The generative AI analyzes the content of the inquiry and generates an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3 to 5 business days." This response is sent back to the server in real time.

[1579] The server receives responses from the generative AI and formats them for the user interface. For example, it converts JSON data to HTML or plain text. The formatted response is sent from the server to the user interface, and the user's device displays a message such as "Product delivery time is usually 3-5 business days" on the chatbot screen or in their email client.

[1580] Specific example

[1581] Case 1: Inquiry via chat

[1582] 1. User enters inquiry: The user enters "Please explain the return process."

[1583] 2. Server receives and saves query: The server saves the query content to the database.

[1584] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[1585] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to "Please tell me about the return process" (e.g., "For information on the return process, please read the following steps...").

[1586] 5. Server receives and formats the generated response: The server receives the response from the generation AI and formats it in HTML format.

[1587] 6. Server sends response to terminal, user receives: The server sends the formatted response to the chatbot's UI, which is then displayed to the user on the chatbot screen.

[1588] Case 2: Inquiry via email

[1589] 1. User enters inquiry: The user enters "Please tell me how to place an additional order" into the email form.

[1590] 2. Server receives and saves query: The server saves the query content to the database.

[1591] 3. Server formats the query and sends it to the generative AI: The server formats the query in JSON format and sends it to the generative AI API.

[1592] 4. Generative AI analyzes the inquiry and generates a response: The generative AI generates a response to the question "How do I place an additional order?" (Example: "To place an additional order, please proceed through your My Page on the online store.").

[1593] 5. Server receives and formats the generated response: The server receives the response from the generative AI and formats it in plain text format.

[1594] 6. Server sends response to terminal, user receives: The server sends the formatted response to the email system, and the user's email client displays a message saying, "For instructions on how to place an additional order, please proceed from your online store's My Page."

[1595] Thus, the system according to the present invention provides an integrated solution for handling inquiries quickly and with high quality. By saving the history of inquiries and their responses in a database, it can also be used for future service improvements. This system makes it possible to improve user satisfaction and increase the operational efficiency of companies.

[1596] Example of a prompt

[1597] "When is the product due?"

[1598] "Please tell me about the return process."

[1599] "Please tell me how to place an additional order."

[1600] By entering these prompts, the generative AI will provide the corresponding answer.

[1601] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1602] Step 1:

[1603] The user enters an inquiry.

[1604] The user enters their inquiry using a terminal. For example, the user might enter, "What is the delivery date for the product?" This becomes the input data. The terminal then sends the entered inquiry to the server in real time.

[1605] Step 2:

[1606] The server receives the query.

[1607] The server receives user inquiries in real time. This received data becomes the input data. The server first saves the received inquiry content to a database. When saving, it also records additional information such as the inquiry ID, user ID, and timestamp. This makes it possible to track the inquiry history.

[1608] Step 3:

[1609] The server formats the query content.

[1610] The server retrieves query data stored in the database and converts it into the format necessary for sending it to the generative AI. This format conversion is data processing. For example, the query data is converted into JSON format. The converted JSON data becomes the output data.

[1611] Step 4:

[1612] The server sends the formatted query content to the generation AI API.

[1613] The server sends formatted JSON data to the generative AI API. This becomes the input data. The server performs error checking and data integrity verification during transmission. Once the generative AI receives the data, it begins analyzing the query.

[1614] Step 5:

[1615] The generative AI analyzes the inquiry and generates a response.

[1616] The generative AI analyzes the JSON-formatted query received from the server. This analysis is data processing. The generative AI uses natural language processing techniques to understand the intent of the query and generate an appropriate response. For example, it might generate a response such as, "The delivery time for products is usually 3-5 business days." This generated response becomes the output data.

[1617] Step 6:

[1618] The server receives the response from the generative AI.

[1619] The server receives the response generated by the generative AI. The received response data in JSON format becomes the input data. The server then performs a verification process on the received data for comparison.

[1620] Step 7:

[1621] The server formats the generated response.

[1622] The server formats the received JSON response for the user interface. Specifically, it converts the JSON data into HTML or plain text. This format conversion is data processing. The converted data becomes the output data.

[1623] Step 8:

[1624] The server sends the formatted response to the user interface.

[1625] The server sends the formatted response data to the user's terminal. The converted data is sent as input data. The server checks the data integrity and confirms delivery upon transmission.

[1626] Step 9:

[1627] The answer will be displayed on the user's device.

[1628] The user's device receives a formatted response sent from the server. This received data becomes the input data. The device then displays the received data appropriately. For example, it might display "Product delivery time is usually 3-5 business days" on the chatbot screen or in the email client.

[1629] Through these steps, users' inquiries will be answered quickly and appropriately.

[1630] (Application Example 1)

[1631] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1632] Electronic payment services require prompt and accurate responses to user inquiries. However, traditional systems often resulted in inconsistent quality in inquiry handling, frequently lowering user satisfaction. Furthermore, there was a lack of efficient methods for managing inquiry content and response history. As a result, inquiry handling took a significant amount of time, negatively impacting user convenience.

[1633] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1634] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate an optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to a user interface, means for the user to receive the answer, means for handling inquiries using an application installed on a smartphone, smart glasses, head-mounted display, or robot, and means for processing inquiries related to electronic payment services. This makes it possible to improve the quality of inquiry handling and enhance user convenience.

[1635] A "server" is a computer system that receives user inquiries, stores them in a database, and sends them to a generative AI API.

[1636] A "user interface" is a means of providing a screen or form for a user to input their inquiry and receive a generated response.

[1637] "Generative AI" refers to artificial intelligence that analyzes inquiries and generates the most appropriate response.

[1638] A "generative AI API" is an application programming interface for sending and receiving query data between a server and a generative AI.

[1639] A "database" is a system for storing and managing query content and generated responses.

[1640] A "smartphone" is a portable computer device used to input inquiries and receive generated responses.

[1641] "Smart glasses" are wearable devices used by users to input inquiries and receive generated responses.

[1642] A "head-mounted display" is a display device worn by the user, used for inputting inquiries and receiving generated responses.

[1643] A "robot" is an automated machine programmed to handle inquiries.

[1644] An "electronic payment service" is a system that allows users to pay electronically for goods and services they purchase online or in physical stores.

[1645] "Inquiry history" refers to a record of user inquiries and the corresponding responses.

[1646] The system for implementing this invention automates the reception, analysis, and response generation of inquiries, thereby improving the efficiency of handling inquiries related to electronic payment services. Specifically, it uses the following hardware and software.

[1647] System Overview

[1648] hardware

[1649] 1. Server: A high-performance computer server receives user inquiries and sends data to the generative AI. It also stores the inquiry content and its response in a database.

[1650] 2. User terminal: This refers to devices such as smartphones, smart glasses, head-mounted displays, and robots. These are used by users to input inquiries and display generated responses.

[1651] software

[1652] 1. User Interface (UI): The screen or form on which a user enters an inquiry and receives a generated response. Frameworks such as React Native or Flutter are used.

[1653] 2. Server Application: Built using Node.js and Express. It receives, stores, and sends query data to the generation AI, formats the generated responses, and sends them to the user's terminal.

[1654] 3. Generative AI: A generative AI model (e.g., GPT-4) is used to analyze the inquiry content and generate an appropriate response.

[1655] 4. Database: Use a relational database such as MySQL to manage queries and their responses.

[1656] Program processing

[1657] Receiving and saving inquiries

[1658] The user enters their inquiry through a smartphone application. For example, an inquiry such as, "What should I do about a canceled payment?" The server receives this inquiry and saves it to a database. The inquiry ID, user ID, and timestamp are recorded.

[1659] Sending to a generative AI

[1660] The server sends the received query to a generative AI API. The generative AI analyzes the query and uses natural language processing techniques to understand its intent. It then generates an appropriate response.

[1661] Answer generation and formatting

[1662] The generative AI generates a response such as, "For canceled payments, please follow these instructions..." This response is sent back to the server in real time. The server formats the received response for display to the user. For example, it converts JSON data into plain text.

[1663] Submit and display of responses

[1664] The formatted response is sent from the server to the user interface. The user's device, such as a smartphone or smart glasses screen, displays a response such as, "For canceled payments, please follow these instructions."

[1665] Specific example

[1666] Example 1: Inquiry

[1667] The user typed "What should I do about the canceled payment?" into the smartphone app.

[1668] The server receives the data and saves it to the database.

[1669] Send to a generative AI API.

[1670] The generative AI analyzes the data and generates a response saying, "For canceled payments, please follow these instructions."

[1671] The server formats the file and sends it to the user's terminal.

[1672] The user checks their answer on their smartphone.

[1673] Example of a prompt

[1674] "This is an inquiry regarding electronic payment cancellations. A user has asked about the payment cancellation process. Please provide an appropriate answer."

[1675] "A user is inquiring about a failed payment method. Please generate specific instructions."

[1676] By implementing this invention, the efficiency and quality of handling inquiries are improved, and user convenience is significantly enhanced.

[1677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1678] Step 1:

[1679] The user enters their inquiry using a device (e.g., a smartphone). For example, they might enter an inquiry such as "What should I do about a canceled payment?" into the application screen. This input is sent to the server in real time through the UI component.

[1680] Step 2:

[1681] The server receives the query content sent from the terminal. The received content is stored in the database. Metadata such as the query ID, user ID, and timestamp is also stored here. The input is the query content, and the output is the record stored in the database.

[1682] Step 3:

[1683] The server formats the received query and sends it to the generative AI API. For example, it prepares the query as JSON data and sends a request to the API endpoint. The input is the formatted query, and the output is the request to the generative AI.

[1684] Step 4:

[1685] The generative AI analyzes the inquiry content and performs natural language processing to understand its intent. It then generates an appropriate response. For example, it might generate the prompt "For canceled payments, please follow these steps." The input is the received inquiry, and the output is the generated response.

[1686] Step 5:

[1687] The server receives the responses generated by the generative AI. The server then formats the received responses for the user interface. For example, it might convert JSON data to plain text. The input is the generated response, and the output is the formatted response.

[1688] Step 6:

[1689] The server sends a formatted response to the user interface. It converts the response to a format that can be displayed on the application's chat screen and sends it to the user's device. The input is the formatted response, and the output is the display of the response on the user's device.

[1690] Step 7:

[1691] The user's device displays the response received from the server. The user sees a specific response on their smartphone screen, such as "For canceled payments, please follow these instructions." The input is the formatted response received from the server, and the output is the display on the user's screen.

[1692] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1693] This invention relates to a system that achieves more accurate responses by combining a system that uses generative AI to streamline customer service responses with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1694] System Overview

[1695] This system mainly consists of the following components:

[1696] 1. User Interface (UI): Provides screens or forms for users to enter inquiries and receive responses.

[1697] 2. Server: Receives the query content and communicates with the database and generative AI.

[1698] 3. Generative AI API: The server sends the inquiry details to the generative AI, which generates an appropriate response.

[1699] 4. Emotion Engine: Analyzes user emotions from the content of their inquiries and the writing style used during input.

[1700] 5. Database: Stores and manages inquiry content, responses, and sentiment analysis results.

[1701] Program processing

[1702] Inquiry reception

[1703] Users enter their inquiries via chatbots or email forms. For example, a user might type, "When is the delivery date for the product? Is it too late?" This inquiry is sent to the server in real time.

[1704] Receiving and saving inquiry details

[1705] The server receives a user inquiry and first saves its contents to the database. The inquiry ID, user ID, and timestamp are recorded. This allows the entire inquiry history to be tracked.

[1706] Analysis using an emotion engine

[1707] The server sends the received inquiry to the sentiment engine. The sentiment engine analyzes the user's emotions based on the style and keywords of the inquiry. For example, from the sentence "Is it too late?", the sentiment engine might determine that the user is irritated.

[1708] Sending to a generative AI

[1709] The server sends the inquiry details, including the sentiment analysis results obtained from the sentiment engine, to the generative AI API. The generative AI API then generates the optimal response based on the inquiry data and sentiment analysis results.

[1710] Answer generation

[1711] The generative AI generates the optimal response based on the analysis results. For example, it might generate a response such as, "The delivery time for this product is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions." This response is sent back to the server in real time.

[1712] Receiving and formatting responses

[1713] The server receives responses from the generative AI and formats them for the user interface. For example, it might convert JSON data into HTML or plain text.

[1714] Submit and display of responses

[1715] The formatted response is sent from the server to the user interface. The user's device will then display a message on the chatbot screen or in their email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1716] Specific example

[1717] Case 1: How to calm frustration in a chat

[1718] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[1719] 2. Server receives and saves query: The query content is saved to the database.

[1720] 3. Emotional Engine Analysis: Detecting frustration from "Is it too late?"

[1721] 4. Sending to the Generative AI: Send the content of your inquiry and your frustration to the Generative AI.

[1722] 5. Generate response: Generate the response: "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1723] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1724] 7. The user receives the response: The chatbot displays the response.

[1725] Case Study 2: Responding to a thank-you message via email

[1726] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[1727] 2. Server receives and saves query: The query content is saved to the database.

[1728] 3. Analysis using an emotion engine: Detecting gratitude from "Thank you."

[1729] 4. Sending to the Generative AI: Send the inquiry details and your thanks to the Generative AI.

[1730] 5. Generating the response: Generate the response: "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[1731] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1732] 7. The user receives the response: The email client displays the response.

[1733] This system recognizes user emotions and responds accordingly, thereby improving user satisfaction and enabling efficient inquiry handling. The emotion analysis results are stored in a database and can be used for future service improvements.

[1734] The following describes the processing flow.

[1735] Step 1:

[1736] The user enters their inquiry.

[1737] Users type "When is the product due? Is it too late?" into the chatbot or email form on their device.

[1738] Step 2:

[1739] The server receives the query and saves the query details to the database.

[1740] The server receives the inquiry details from the user interface.

[1741] The server saves the received query data (query ID, user ID, timestamp, and query content) to the database.

[1742] Step 3:

[1743] The server prepares to send the query content to the emotion engine.

[1744] The server formats the query content into a format that the sentiment engine can analyze (for example, text format).

[1745] Step 4:

[1746] The server sends the query to the emotion engine.

[1747] The server sends the formatted query data to the sentiment engine.

[1748] Step 5:

[1749] The emotion engine analyzes the content of the inquiry.

[1750] The emotion engine analyzes the received data and detects the user's emotions from the style and keywords of the inquiry. For example, it might determine that the user is feeling frustrated from the phrase, "Is it too late?"

[1751] Step 6:

[1752] The server receives the emotion analysis results from the emotion engine.

[1753] The server receives the emotion analysis results sent from the emotion engine.

[1754] The server stores the query data and sentiment analysis results in a database.

[1755] Step 7:

[1756] The server prepares to send the inquiry details and sentiment analysis results to the generative AI API.

[1757] The server formats the inquiry content and sentiment analysis results into a format that the generative AI API can understand (for example, JSON format).

[1758] Step 8:

[1759] The server sends the query content and sentiment analysis results to the generative AI API.

[1760] The server sends the formatted query content and sentiment analysis results to the generative AI API endpoint.

[1761] Step 9:

[1762] A generative AI analyzes the content of the inquiry and the results of the sentiment analysis.

[1763] Generative AI analyzes received data and generates the most appropriate response tailored to the user's intent and emotional state. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1764] Step 10:

[1765] The server receives the response generated by the generative AI.

[1766] The server receives response data sent from the generative AI. The received data is in a format such as JSON.

[1767] Step 11:

[1768] The server formats the received response for the user interface.

[1769] The server converts the received response data into a format that can be displayed by the user interface. For example, it converts it to HTML or plain text.

[1770] Step 12:

[1771] The server sends the formatted response to the user interface.

[1772] The server sends the formatted response to the chatbot or email system.

[1773] Step 13:

[1774] The user receives the response on their device.

[1775] The user's device will display a message via chatbot or email client stating, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us for further assistance if you have any questions."

[1776] In this way, this system enables the analysis of user emotions and the response accordingly, thereby improving user satisfaction.

[1777] (Example 2)

[1778] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1779] Traditional customer service systems often use canned responses without considering user emotions, resulting in decreased user satisfaction. Furthermore, managing inquiry content while incorporating sentiment analysis results was difficult. This led to problems with the quality and efficiency of responses.

[1780] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1781] In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for the server to send the inquiry content to an emotion analysis engine and analyze the user's emotions, means for the server to send the inquiry content and emotion analysis results to a generative AI API, means for the generative AI to generate an optimal answer based on the inquiry content and emotion analysis results, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for the user to receive the answer, and means for storing the inquiry content, generated answer, and emotion analysis results in a database and managing the inquiry history. This makes it possible to quickly provide the optimal answer while taking the user's emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[1782] A "user" is a person or group that accesses the system and enters their inquiry.

[1783] "Inquiry details" refer to information such as questions and requests that users enter and send to the system.

[1784] A "server" is a computer system that receives queries, performs necessary processing, and interacts with databases and other components.

[1785] A "database" is an information storage system that stores and manages inquiry content, responses, and sentiment analysis results.

[1786] A "sentiment analysis engine" is software and algorithms that analyze the content of inquiries and determine the user's emotions.

[1787] A "generative AI API" is an application programming interface for artificial intelligence that operates based on the content of an inquiry and the results of sentiment analysis in order to provide an appropriate generated response.

[1788] "Formatting" refers to the process of shaping the response obtained from a generative AI for use in a user interface.

[1789] A "user interface" refers to the elements of interaction, including screens and forms, that allow a user to input inquiries into a system and receive generated responses.

[1790] "Inquiry history" refers to a record of all past inquiries, the responses to those inquiries, and data including sentiment analysis results.

[1791] This invention relates to a system that improves user satisfaction by streamlining customer service response using generative AI and an emotion analysis engine. Specific embodiments of this invention are described below.

[1792] Hardware and software to be used

[1793] To implement the invention, the following hardware and software are used.

[1794] Hardware:

[1795] Server: Receives, stores, and communicates with the AI ​​API for generating queries.

[1796] Terminal: A device (such as a PC or smartphone) used by the user to enter their inquiry and receive a response.

[1797] software:

[1798] Database: A system for storing and managing inquiry content, responses, and sentiment analysis results.

[1799] Sentiment analysis engine: Software that analyzes inquiry content and determines the user's emotions.

[1800] Generative AI API: An API for generating the optimal response based on the content of the inquiry and the results of sentiment analysis.

[1801] User interface: A screen or form on which a user enters their inquiry and receives a response.

[1802] Data processing and calculation

[1803] server

[1804] 1. The server receives data from forms or chatbots where users enter their inquiries.

[1805] 2. Save the received inquiry details to the database. At this time, metadata such as the inquiry ID, user ID, and timestamp will also be recorded.

[1806] 3. The server sends the saved query content to the sentiment analysis engine. The sentiment analysis engine analyzes the writing style and keywords to determine the user's emotions.

[1807] 4. The server that receives the sentiment analysis results sends the inquiry content and sentiment analysis results to the generative AI API.

[1808] 5. The generative AI generates the optimal response based on the inquiry content and sentiment analysis results, and returns the result to the server.

[1809] 6. The server formats the generated response for the user interface and sends the response to the terminal.

[1810] terminal

[1811] 1. Users enter their inquiries using their devices. For example, they might use a website's chatbot screen or email form.

[1812] 2. The user receives the response sent from the server on their device. They then review the formatted response using a chatbot or email app.

[1813] Examples of specific cases and prompt statements

[1814] Example 1: Handling inquiries via chat

[1815] 1. User enters inquiry: User: "When is the delivery date for the product? Is it too late?"

[1816] 2. Server receives and stores query: The server stores the query content in the database.

[1817] 3. Emotional analysis: The emotional analysis engine detects frustration from the phrase "Is it too late?"

[1818] 4. Sending to the Generative AI: The server sends the query content and the frustration to the Generative AI.

[1819] 5. Response Generation: The generation AI generates the response: "The delivery time for products is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1820] 6. Formatting and submitting responses: The server formats the responses and sends them to the chatbot.

[1821] 7. The user receives the response: The user confirms the response via the chatbot.

[1822] Example 2: Responding to inquiries via email

[1823] 1. User enters inquiry: User: "Thank you as always. Could you please tell me about the next sale?"

[1824] 2. Server receives and stores query: The server stores the query content in the database.

[1825] 3. Analysis by the emotion engine: The emotion analysis engine detects gratitude from "Thank you."

[1826] 4. Sending to the Generative AI: The server sends the inquiry details and a message of thanks to the Generative AI.

[1827] 5. Response generation: The generation AI generates the response, "Thank you for your continued patronage. Our next sale is scheduled for early next month."

[1828] 6. Formatting and sending responses: The server formats the responses and sends them to the email system.

[1829] 7. The user receives the response: The user confirms the response via their email client.

[1830] Example of a prompt

[1831] 1. A prompt to calm frustration during a chat: "When is the product due? Is it too late?"

[1832] 2. Prompt response to a thank-you email: "Thank you as always. Please let me know about your next sale."

[1833] This embodiment makes it possible to quickly provide the optimal answer while taking user emotions into consideration, thereby improving the quality and efficiency of inquiry handling.

[1834] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1835] Step 1:

[1836] The user enters an inquiry.

[1837] Input: The user enters their inquiry into a chatbot or email form.

[1838] Processing: The user enters, for example, "When is the delivery date for the product? Is it too late?"

[1839] Operation: The entered inquiry content is displayed in the terminal's input field, and when the submit button is pressed, that content is sent to the server.

[1840] Output: The user's inquiry is sent to the server.

[1841] Step 2:

[1842] The server receives and stores the query.

[1843] Input: The content of the inquiry submitted by the user.

[1844] Processing: The server receives the query in real time. The received content is analyzed and saved to the database along with the relevant metadata (query ID, user ID, timestamp, etc.).

[1845] Operation: The server adds the query content to the database as a new record. This makes the query content traceable within the system.

[1846] Output: The query details are saved in the database.

[1847] Step 3:

[1848] The server sends the inquiry details to the sentiment analysis engine.

[1849] Input: The query content stored in the database.

[1850] Processing: The server sends the inquiry content as an API request to the sentiment analysis engine. The sentiment analysis engine analyzes the user's emotions using the writing style and keywords.

[1851] Operation: The server sends data to the sentiment analysis engine using an HTTP POST request and receives the analysis results.

[1852] Output: Sentiment analysis results from the emotion analysis engine.

[1853] Step 4:

[1854] The server sends the sentiment analysis results and inquiry content to a generative AI API.

[1855] Input: Inquiry details and sentiment analysis results.

[1856] Processing: The server sends the inquiry details and sentiment analysis results to a generative AI API. The generative AI API generates the optimal response based on the received information.

[1857] Operation: The server sends data to a generative AI API and sets prompts to generate the optimal response.

[1858] Output: Response data from a generative AI.

[1859] Step 5:

[1860] Generative AI generates the optimal answer.

[1861] Input: Prompts based on the inquiry content and sentiment analysis results.

[1862] Processing: The generative AI analyzes the input prompt and generates an appropriate response to the inquiry. For example, it might generate a response such as, "Product delivery is usually 3-5 business days, but delays may occur. Please contact us if you have any further questions."

[1863] Operation: Generative AI uses internal algorithms to analyze the content and sentiment of inquiries and construct responses.

[1864] Output: Generated response data.

[1865] Step 6:

[1866] The server formats the generated response.

[1867] Input: Response data generated by a generative AI.

[1868] Processing: The server formats the received response data for the user interface. This process includes converting JSON data to HTML or plain text.

[1869] Operation: The server converts the received data into an appropriate format and displays it in a way that is easy for the user to read.

[1870] Output: Formatted response data.

[1871] Step 7:

[1872] The server sends the formatted response to the user interface.

[1873] Input: Formatted response data.

[1874] Processing: The server sends the formatted response to the user interface, such as a chatbot screen or email system.

[1875] Operation: Data is sent from the server to the user interface and displayed on the terminal in real time.

[1876] Output: Response data displayed on the user's device.

[1877] Step 8:

[1878] The user receives the response.

[1879] Input: Formatted response data submitted from the user interface.

[1880] Processing: The user's device receives the response data and displays it on the screen.

[1881] Operation: Users review the responses via the chatbot screen or email client and decide on their next action.

[1882] Output: The user reviews the displayed answer.

[1883] (Application Example 2)

[1884] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1885] Traditional customer service systems often provide formulaic responses without considering user emotions, leading to decreased customer satisfaction. Furthermore, staff in physical stores lacked the means to provide appropriate answers and responses in real time, making efficient and effective customer service difficult.

[1886] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input inquiry content, means for the server to receive the inquiry content and store it in a database, means for sending the inquiry content to a generative AI API, means for the generative AI to analyze the inquiry content and generate the optimal answer, means for the server to receive the answer generated by the generative AI, format the answer and send it to the user interface, means for using an emotion engine to analyze the user's emotions, means for sending the emotion information analyzed by the emotion engine to the generative AI, and means for the generative AI to generate a more accurate answer based on the emotion information. This makes it possible for staff in physical stores to provide the optimal response in real time according to the customer's emotions.

[1887] The "user interface" is the part of a system that provides an interactive screen or form for users to input inquiry details and view the generated response.

[1888] A "server" is a central computer that receives user inquiries and manages and processes communication with databases, generative AI APIs, and emotion engines.

[1889] A "database" is a data management system used to store and manage information such as inquiry content, generated responses, and sentiment analysis results.

[1890] "Generative AI" refers to a system that uses artificial intelligence technology to analyze the content of an input inquiry and generate the most appropriate response.

[1891] A "generative AI API" is a programmatic interface for sending inquiries to a generative AI and obtaining the most appropriate response.

[1892] An "emotion engine" is a system that analyzes user emotions based on the content of their inquiries and the writing style they use.

[1893] "Formatting" refers to the process of converting the generated response into a format suitable for the user interface.

[1894] "Inquiry content" refers to questions or requests that users enter into the system.

[1895] "Answer" refers to the optimal response generated by a generative AI in response to an inquiry that has been analyzed.

[1896] This invention is a system that utilizes generative AI and an emotion engine to streamline user support at inquiry desks. Specific embodiments for carrying out this invention are described below.

[1897] System Configuration

[1898] This system consists of multiple components, including a user interface, server, generative AI API, emotion engine, and database.

[1899] User Interface (UI)

[1900] The user interface provides interactive screens and forms for users to input inquiries and review generated responses. Specifically, it is implemented as a smartphone or tablet application.

[1901] server

[1902] The server receives user inquiries and stores them in a database. It also sends the inquiry content to a generative AI API, formats the generated response, and sends it to the user interface. The server handles the main central processing and manages the coordination with the emotion engine and generative AI API.

[1903] Emotional Engine

[1904] The emotion engine analyzes user inquiries and interprets their emotions based on their writing style and keywords. The analyzed emotion information is sent to the generative AI via the server and used to improve the accuracy of the generated responses.

[1905] Generative AI API

[1906] The generative AI API generates the optimal response based on the user's inquiry and sentiment analysis results. The generated response is sent to the server and formatted for display in the user interface.

[1907] database

[1908] The database stores and manages information such as inquiry content, generated responses, and sentiment analysis results. This makes it possible to track the entire inquiry history.

[1909] Flow of operations

[1910] When a user enters an inquiry using a smartphone or tablet, that information is sent to the server. The server stores the received inquiry in a database and sends it to an emotion engine for sentiment analysis. The emotion information obtained from the emotion engine is sent to a generative AI to generate the optimal response. The generated response is returned to the server, formatted in a way that can be displayed to the user, and then sent to the user interface.

[1911] Specific example

[1912] For example, imagine a staff member at a physical store receiving a customer inquiry via smartphone asking, "Do you have this item in stock?" If the emotion engine analyzes the customer's emotion to be "anxiety," the generative AI uses this information to generate a response such as, "We have it in stock. However, it may take some time for the next shipment to arrive." This allows the staff member to respond quickly and appropriately.

[1913] Example of a prompt

[1914] Enter the following as the prompt:

[1915] Prompt: A customer in a store asks, "Do you have this item in stock?" Generate the best response using a generative AI model, incorporating the emotion analyzed as "anxiety" by the emotion engine.

[1916] The above describes the "mode for carrying out the invention." A system following this mode can improve the efficiency of user support and enhance customer satisfaction.

[1917] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1918] Step 1:

[1919] The user enters their inquiry.

[1920] Input: User input from smartphones or tablets (e.g., "Is this product in stock?").

[1921] Output: The entered query content is sent to the server.

[1922] Specific operation: When a user enters their inquiry into a text box on the user interface (UI) and presses the submit button, that text data is sent from the terminal to the server.

[1923] Step 2:

[1924] The server receives the query and saves it to the database.

[1925] Input: The content of the inquiry submitted by the user.

[1926] Output: The query details are saved in the database and registered along with the query ID and timestamp.

[1927] Specific operation: The server temporarily stores the received query in memory, establishes a database connection, and permanently stores the query. Metadata such as ID, user ID, and timestamp is attached to the query.

[1928] Step 3:

[1929] The server sends the query to the emotion engine, which then analyzes the emotions.

[1930] Input: The query content stored in the database.

[1931] Output: Emotional information analyzed by the emotion engine (e.g., "anxiety").

[1932] Specific operation: The server sends the stored query content to the sentiment engine's API, and the sentiment engine analyzes the writing style and keywords to return sentiment information. The server receives this sentiment information.

[1933] Step 4:

[1934] The server sends the inquiry content and sentiment information to a generative AI API, which then generates the optimal response.

[1935] Input: Inquiry content and sentiment information returned by the sentiment engine.

[1936] Output: Response generated from a generative AI API (e.g., "We have stock. However, it may take some time before the next shipment arrives.").

[1937] Specific operation: The server combines the inquiry content and sentiment information and sends it to a generative AI API. The generative AI then performs natural language processing based on this information, generates the optimal response, and sends it to the server.

[1938] Step 5:

[1939] The server receives the generated response and formats it for the user interface.

[1940] Input: Response received from a generative AI.

[1941] Output: Formatted response data.

[1942] Specific operation: The server converts the received response from JSON format to HTML or plain text format and formats it so that it can be displayed in the user interface.

[1943] Step 6:

[1944] The server sends the formatted response to the user interface, and the user receives the response.

[1945] Input: Formatted response data.

[1946] Output: The answer displayed on the user interface.

[1947] Specific operation: The server sends the formatted response to the terminal and visualizes it in the user interface. The user can view the response on their smartphone or tablet screen.

[1948] This allows users to receive optimal responses tailored to their emotions in real time, streamlining customer service in physical stores.

[1949] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1950] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1951] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1952] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1953] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1954] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1955] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1956] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1957] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1958] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1959] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1960] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1961] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1962] 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.

[1963] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1964] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1965] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1966] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1967] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1968] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1969] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1970] The following is further disclosed regarding the embodiments described above.

[1971] (Claim 1)

[1972] A means for users to enter their inquiry details,

[1973] A means by which the server receives the query content and stores the query content in the database,

[1974] A means by which the server sends the query content to a generation-based AI API,

[1975] A method for generating an optimal response by using a generative AI to analyze the content of an inquiry,

[1976] A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface,

[1977] A system that includes a means for users to receive responses.

[1978] (Claim 2)

[1979] The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and uses natural language processing technology to generate an appropriate response.

[1980] (Claim 3)

[1981] The system according to claim 1, further comprising means for storing inquiry content and generated responses in a database and managing inquiry history.

[1982] "Example 1"

[1983] (Claim 1)

[1984] A means for users to enter their inquiry details,

[1985] A means by which the server receives the query content and stores the query content in the database,

[1986] A means by which the server sends the query content to a generation-based AI API,

[1987] A method for generating an optimal response by using a generative AI to analyze the content of an inquiry,

[1988] A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface,

[1989] The means by which users receive responses,

[1990] A means by which the content of the inquiry is sent to the server in real time,

[1991] A means for storing the query ID, user ID, and timestamp of the query received by the server in a database,

[1992] After the server receives a response from the generative AI, it has a means to convert the JSON data into HTML or plain text,

[1993] A means by which the server sends formatted responses to the user interface in real time,

[1994] A system that includes means for displaying formatted answers on the user's device.

[1995] (Claim 2)

[1996] The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and uses natural language processing technology to generate an appropriate response.

[1997] (Claim 3)

[1998] The system according to claim 1, further comprising means for storing inquiry content and generated responses in a database and managing inquiry history.

[1999] "Application Example 1"

[2000] (Claim 1)

[2001] A means for users to enter their inquiry details,

[2002] A means by which the server receives the query content and stores the query content in the database,

[2003] A means by which the server sends the query content to a generation-based AI API,

[2004] A method for generating an optimal response by using a generative AI to analyze the content of an inquiry,

[2005] A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface,

[2006] The means by which users receive responses,

[2007] A system that includes means of handling inquiries using an application installed on a smartphone, smart glasses, head-mounted display, or robot.

[2008] (Claim 2)

[2009] The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and uses natural language processing technology to generate an appropriate response.

[2010] (Claim 3)

[2011] The system according to claim 1, further comprising means for storing inquiry content and generated responses in a database and managing inquiry history.

[2012] (Claim 4)

[2013] The system according to claim 1, which processes inquiries related to electronic payment services.

[2014] "Example 2 of combining an emotion engine"

[2015] (Claim 1)

[2016] A means for users to enter their inquiry details,

[2017] A means by which the server receives the query content and stores the query content in the database,

[2018] A method by which the server sends the inquiry content to an emotion analysis engine to analyze the user's emotions,

[2019] A means for the server to send the inquiry content and sentiment analysis results to a generative AI API,

[2020] A method by which a generative AI generates the optimal response based on the content of the inquiry and the results of sentiment analysis,

[2021] A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface,

[2022] A system that includes a means for users to receive responses.

[2023] (Claim 2)

[2024] The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and the user's emotions, and uses natural language processing technology to generate an appropriate response.

[2025] (Claim 3)

[2026] The system according to claim 1, further comprising means for storing the content of the inquiry, the generated response, and the sentiment analysis results in a database, and for managing the inquiry history.

[2027] "Application example 2 when combining with an emotional engine"

[2028] (Claim 1)

[2029] A means for users to enter their inquiry details,

[2030] A means by which the server receives the query content and stores the query content in the database,

[2031] A means by which the server sends the query content to a generation-based AI API,

[2032] A method for generating an optimal response by using a generative AI to analyze the content of an inquiry,

[2033] A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface,

[2034] A means of using an emotion engine to analyze user emotions,

[2035] A means of transmitting emotional information analyzed by the emotion engine to the generative AI,

[2036] A method for generating more accurate answers using generative AI based on emotional information,

[2037] A system that includes a means for users to receive responses.

[2038] (Claim 2)

[2039] The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and uses natural language processing technology to generate an appropriate response.

[2040] (Claim 3)

[2041] The system according to claim 1, further comprising means for storing inquiry content and generated responses in a database and managing inquiry history. [Explanation of Symbols]

[2042] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to enter their inquiry details, A means by which the server receives the query content and stores the query content in the database, A means by which the server sends the query content to a generation-based AI API, A method for generating an optimal response by using a generative AI to analyze the content of an inquiry, A means by which a server receives the response generated by a generative AI, formats the response, and sends it to the user interface, A system that includes a means for users to receive responses.

2. The system according to claim 1, wherein a generative AI analyzes the intent of the inquiry and uses natural language processing technology to generate an appropriate response.

3. The system according to claim 1, further comprising means for storing inquiry content and generated responses in a database and managing inquiry history.

Images