system

Abstract

We provide the system. [Solution] An input means for the user to enter an inquiry, A server means for receiving and analyzing the query, An AI generation means that causes a generative AI to generate a response based on the analysis results, Output means for receiving the generated response and displaying it to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional customer support system, there was a problem that customers' inquiries covered a wide range and it was unclear which was the appropriate contact point because the responsible person or department for each inquiry was different. In addition, since some responsible persons or departments could only respond during regular business hours on weekdays, it was difficult to respond promptly to inquiries outside business hours. As a result, there was a problem that the user experience was impaired and prompt problem-solving was hindered.

Means for Solving the Problems

[0005] This invention provides a server means that receives and analyzes user inquiries. It includes an AI generation means in which a generative AI generates an appropriate response based on the analysis results, and an output means in which the generated response is displayed to the user. Furthermore, by including an authentication means in which the user's authentication information is verified, a quick response can be provided while ensuring security. In addition, by including a transmission means in which the generated response is formatted and sent to the user's terminal, a system is realized that can quickly provide appropriate information to the user.

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

[0007] An "inquiry" refers to a question or request that a user makes through the system.

[0008] "Input means" refers to a device or interface for a user to input an inquiry.

[0009] A "server system" refers to a server that has the function of receiving and analyzing queries and sending data to a generative AI.

[0010] "Generative AI" refers to an artificial intelligence engine that generates appropriate responses based on the received analysis results.

[0011] "AI generation method" refers to a system that uses generative AI to generate responses to inquiries.

[0012] "Output means" refers to a device or interface for displaying the generated response to the user.

[0013] "Authentication method" refers to a mechanism that verifies the user's legitimacy by comparing the authentication information provided by the user.

[0014] "Transmission means" refers to the function that converts the generated response into an appropriate format and sends it to the user's terminal.

Brief Description of the Drawings

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

Modes for Carrying Out the Invention

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

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

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

[0019] In the following embodiments, the numbered 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 numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[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 allows users to make inquiries smoothly and obtain quick and accurate responses. To implement this system, the system includes a terminal for the user to input inquiries, a server that receives and processes inquiries, a generative AI that generates appropriate responses, and a terminal that displays the responses to the user.

[0037] composition

[0038] 1. User's terminal

[0039] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0040] 2. Server

[0041] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0042] 3. Generative AI

[0043] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0044] 4. Response Display

[0045] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0046] Program processing flow

[0047] The user enters an inquiry.

[0048] The user opens the inquiry form on their device, types "Please tell me how to deal with connection problems," and presses the submit button.

[0049] The terminal sends a query to the server.

[0050] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0051] The server receives and analyzes the query.

[0052] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0053] Generative AI generates responses.

[0054] Based on the analysis results received from the server, the generative AI generates a response that says, "If you experience connection problems, please try restarting your equipment first. If the problem persists, please contact professional support."

[0055] The server receives the generated response and sends it to the terminal.

[0056] The server receives the response from the generative AI, formats it, and sends it to the user's terminal.

[0057] The device displays a response.

[0058] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0059] As a concrete example, the following inquiries are possible:

[0060] "Please explain the procedure for cross-connecting."

[0061] "What should I do if a connection problem occurs?"

[0062] "How do I use the remote hand service?"

[0063] By having a generative AI generate individual responses to these inquiries and provide them to the user, the system can quickly resolve the user's problems. This system is highly effective as a means of providing consistent support to the user, even when multiple related departments or personnel are involved.

[0064] The following describes the processing flow.

[0065] Step 1:

[0066] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "Please tell me about the Cross Connect procedure" in the inquiry form, and clicks the submit button.

[0067] Step 2:

[0068] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal then sends this data to the server using the HTTPS protocol.

[0069] Step 3:

[0070] The server receives the query. The server parses the received query content in JSON format and authentication information, and compares it against the database to verify if the user is authenticated.

[0071] Step 4:

[0072] The server analyzes the query. If authentication is successful, the server passes the query to a natural language processing engine for intent analysis.

[0073] Step 5:

[0074] The server sends the analysis results to the generative AI. The server converts the analysis results into a format that the AI ​​engine can easily understand and makes a request to the generative AI's API endpoint.

[0075] Step 6:

[0076] The generative AI generates a response. Based on the received analysis results, the generative AI generates a response stating, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it," and sends it back to the server.

[0077] Step 7:

[0078] The server receives the generated response. The server converts the received response into the appropriate format and prepares to send it to the user's terminal.

[0079] Step 8:

[0080] The server sends a response to the terminal. The server converts the generated response into an appropriate format, such as JSON, and sends it to the user's terminal using the HTTPS protocol.

[0081] Step 9:

[0082] The terminal receives and displays the response. The user's terminal receives the response from the server and displays it on the screen. The user will see a message that reads, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it."

[0083] (Example 1)

[0084] 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."

[0085] Traditional inquiry systems have the drawback of long response times, making rapid problem resolution difficult. Furthermore, the quality of responses to inquiries is inconsistent, and there is little guarantee that users will receive satisfactory answers. Additionally, the increasing complexity of systems, including user authentication and data format conversion, presents challenges in terms of security and processing efficiency.

[0086] 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.

[0087] In this invention, the server includes input means for the user to input a query, server means for receiving and analyzing the query, generation means for causing a generative AI to generate a response based on the analysis results, output means for receiving the generated response and displaying it to the user, and formatting means for converting the response into an appropriate format. This enables the user to obtain a quick and accurate response. Furthermore, it improves the overall security and efficiency of the system and increases user satisfaction.

[0088] "Input method" refers to a device or software that provides an interface (such as a web form or chat box) for users to input inquiries.

[0089] "Server means" refers to devices or software that analyze the content of inquiries received from users and perform the necessary processing.

[0090] "Generation means" refers to a generative AI that generates an appropriate response based on the analysis results received from the server.

[0091] "Output means" refers to devices or software that receive the generated response and display it to the user.

[0092] "Formatting means" refers to the processing or device used to convert the generated response into an appropriate format and transmit it to the user.

[0093] "Authentication means" refers to a function that verifies a user's authentication information and confirms whether they are a legitimate user.

[0094] "Conversion means" refers to the processing or device used to format the generated response and send it to the user's terminal.

[0095] The system of this invention enables users to make inquiries smoothly and obtain quick and accurate responses. Specific components of the system include a user terminal, a server, a generative AI, and a terminal for displaying responses.

[0096] User's terminal

[0097] Users enter their inquiries using their own computers, smartphones, or other devices. Web forms and chat boxes are provided as input interfaces, allowing users to submit inquiries intuitively and easily. The device converts the user's input into JSON format and securely sends it to the server using HTTPS.

[0098] server

[0099] The server handles multiple functions. After receiving a query, it first verifies the user's authentication information. If authentication is successful, it passes the query content to a natural language processing engine for analysis. This analysis process uses libraries such as Python's "spaCy" or "NLTK". Based on the analysis results, it sends an API request to a generative AI to generate a response.

[0100] Generative AI

[0101] Generative AI receives analysis results from a server and generates an appropriate response. For example, if a user asks, "What should I do if I experience connection problems?", the generative AI will generate a specific response such as, "If you experience connection problems, first try restarting your equipment. If that doesn't solve the problem, please contact our dedicated support." Common generative AI models include "GPT-3(registered trademark)".

[0102] Response display

[0103] The server converts the response received from the generative AI into an appropriate format and sends it to the user's terminal. Formats such as HTML and JSON are used for this conversion. Finally, the terminal displays the received response to the user. This allows the user to obtain information quickly and accurately.

[0104] Specific example

[0105] The following examples will make it easier to understand how the system works.

[0106] Example 1: For a user who wants to know the procedure for cross-connecting.

[0107] The user types "Please tell me how to do CrossConnect" and sends it. The terminal converts it to JSON format and sends it to the server via HTTPS. The server receives it, analyzes it with the NLU module, and sends the result to the generative AI. The generative AI generates a response saying, "To do CrossConnect, first access the dedicated page, fill in the designated form, and submit it." The server formats the response and sends it to the terminal. The terminal receives the response and displays it on the browser screen.

[0108] Example 2: For a user who wants to know how to troubleshoot connection problems.

[0109] The user types and sends the question, "What should I do if I experience connection problems?" The server receives the message and sends it to the AI. The AI ​​generates a response: "If you experience connection problems, please try restarting your device first. If the problem persists, please contact our dedicated support." The terminal receives and displays the response.

[0110] Example of a prompt

[0111] The following are examples of prompt statements:

[0112] "Please explain the procedure for cross-connecting."

[0113] "What should I do if I encounter connection problems?"

[0114] "How do I use the remote hand service?"

[0115] This system allows users to receive quick and accurate responses to their inquiries, enabling smooth problem resolution.

[0116] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0117] Step 1:

[0118] The user enters an inquiry.

[0119] Users enter their inquiries into web forms or chat boxes on their devices. Through this input interface, users describe specific questions or problems. For example, a user might enter, "Please tell me how to deal with connection problems." This input data is then used directly in the next process.

[0120] Step 2:

[0121] The device sends the query to the server.

[0122] When the user presses the submit button, the device converts the inquiry content into JSON format and sends it to the server using the HTTPS protocol. The input data (user inquiry content) is sent as converted JSON data. Specific examples include the Python "requests" library and JavaScript's "axios" library. At this time, the device also sends authentication information.

[0123] Step 3:

[0124] The server receives and analyzes the query.

[0125] The server receives JSON data sent from the terminal. First, it checks the authentication information to confirm that the query is from a legitimate user. After this, the server passes the query content to an NLU (Natural Language Understanding) module for analysis. Here, libraries such as Python's "spaCy" or "NLTK" are used for the analysis. As a result of the analysis, the intent of the query and important keywords are extracted.

[0126] Step 4:

[0127] The server sends a request to the generative AI.

[0128] The server sends a request to the generative AI based on the analysis results. This request includes the analyzed query content, and the generative AI makes an API call. Specifically, the analysis results are sent via the API request, and an appropriate answer is obtained as response data.

[0129] Step 5:

[0130] Generative AI generates responses.

[0131] The generative AI generates an appropriate response based on the received analysis results. For example, if the inquiry is "Please tell me how to deal with connection problems," it will generate a response such as "First, please try restarting your equipment. If that does not resolve the issue, please contact our specialist support." The generated response is then sent back to the server as an API response.

[0132] Step 6:

[0133] The server receives the generated response and formats it.

[0134] The server receives the response from the generative AI and converts it into an appropriate format for display to the user. For example, it performs conversion to formats such as HTML or JSON. The formatted data is then generated.

[0135] Step 7:

[0136] The server sends a response to the terminal.

[0137] The server sends formatted response data to the terminal. The data is then securely transmitted again using the HTTPS protocol. This data is in JSON or HTML format.

[0138] Step 8:

[0139] The device displays a response.

[0140] Ultimately, the device displays the received response to the user. The browser might display a message such as, "If you experience connection problems, please try restarting your device first. If the problem persists, please contact professional support." The user can then see this message and take appropriate action.

[0141] (Application Example 1)

[0142] 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."

[0143] In traditional security services, it is difficult for users to obtain the appropriate information necessary to quickly resolve security-related problems. Furthermore, the inability to provide appropriate and expert responses to inquiries often leads to delays in problem resolution. Therefore, a system is needed that provides quick and accurate solutions when users report security problems.

[0144] 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.

[0145] In this invention, the server includes input means for a user to input an inquiry, server means for receiving and analyzing the inquiry, AI generation means for causing a generative AI to generate a response based on the analysis results, response generation means for providing a method for resolving security-related problems, and output means for receiving the generated response and displaying it to the user. This makes it possible to respond quickly and accurately to security problems and promptly resolve user anxieties and problems.

[0146] An "input method" is an interface for users to enter their inquiries.

[0147] A "server system" refers to a server that receives and analyzes queries.

[0148] An "AI generation method" is a means of causing a generative AI to generate a response based on the analysis results.

[0149] A "response generation means" is a means for generating a response to provide a solution for security-related problems.

[0150] "Output means" refers to means for receiving the generated response and displaying it to the user.

[0151] "Authentication means" refers to a method for verifying a user's authentication information.

[0152] "Transmission means" refers to the means for formatting the generated response and sending it to the user's terminal.

[0153] "System" refers to the entire configuration that includes these means.

[0154] The embodiments for carrying out this invention will be described in detail below.

[0155] System Program Overview

[0156] The system of this invention consists of multiple components, which work together to provide a fast and accurate response to user inquiries. The main components of the system include input means, server means, AI generation means, response generation means, output means, authentication means, and transmission means.

[0157] Hardware and software usage

[0158] The system is implemented using the following hardware and software:

[0159] User terminal: The interface in which the user enters their inquiry. This can be a smartphone (iOS or Android®) or a computer.

[0160] Server: A cloud server that receives and analyzes queries. A specific example is AWS® EC2.

[0161] Generative AI: AI that generates responses based on analysis results. A concrete example is the use of OpenAI's GPT-3 API.

[0162] Natural language processing engine: An engine used to analyze query content. Examples include NLTK and SpaCy.

[0163] Program processing

[0164] When a user enters an inquiry from a device such as a smartphone or computer, the inquiry is converted into JSON format and sent to the server. The server analyzes the received inquiry and verifies the user's authentication information using an authentication method. If authentication is successful, the inquiry is analyzed by a natural language processing engine, and the analysis results are passed to an AI generation method, which generates an appropriate response. This response is reformatted and sent to the user's terminal, and finally displayed to the user by an output method.

[0165] Specific example

[0166] A user makes the following inquiry using their smartphone:

[0167] "I can no longer connect to the network."

[0168] This query is parsed by the server, and the following prompt is sent to the generative AI:

[0169] "A user reported being unable to connect to the network. Please provide possible causes and solutions."

[0170] The generative AI receives this prompt and generates the following response:

[0171] "If you can't connect to the network, first try restarting your router or modem. If that doesn't work, check that your device is connected to the correct network and try temporarily disabling your security software."

[0172] This response is reformatted, sent to the user's terminal via the transmission means, and finally displayed to the user by the output means.

[0173] In this way, the system of the present invention encompasses a series of processes from the input of an inquiry to the display of a response, enabling a rapid and accurate response to security problems.

[0174] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0175] Step 1:

[0176] The user enters their inquiry on their device.

[0177] The user enters the message "I can no longer connect to the network" into an input form displayed on their smartphone or computer screen and presses the submit button. This input is then converted into JSON format.

[0178] Step 2:

[0179] The terminal sends a query to the server.

[0180] The terminal converts the user's input into JSON format and then sends it to the server via HTTPS along with authentication information. During this process, the input data is encrypted before transmission.

[0181] Step 3:

[0182] The server receives the query and analyzes it.

[0183] The server stores the received query in a database and verifies the user's authentication information using an authentication method. If authentication is successful, the query content is passed to a natural language processing engine (e.g., NLTK or SpaCy) for text analysis. The analysis results include the intent of the query and important keywords.

[0184] Step 4:

[0185] The generative AI generates the response.

[0186] The server passes the analysis results to the AI ​​generation system, which then sends a prompt message to the generative AI (for example, OpenAI's GPT-3 API). An example of a prompt message is: "The user has reported being unable to connect to the network. Please indicate possible causes and solutions." The generative AI analyzes the prompt message and generates an appropriate response: "If you are unable to connect to the network, first try restarting your router or modem. If that doesn't solve the problem, check that your device is connected to the correct network and try temporarily disabling your security software."

[0187] Step 5:

[0188] The server receives the generated response and formats it.

[0189] The server receives the response from the generative AI and formats it as needed. This formatting includes converting the response into a simple and easy-to-read format. For example, it may add specific tags or styles.

[0190] Step 6:

[0191] The server sends a response to the terminal.

[0192] The formatted response is converted to JSON format and sent to the user's terminal via HTTPS. This transmitted data is also encrypted.

[0193] Step 7:

[0194] The terminal receives and displays the response.

[0195] The user's device analyzes the response received from the server and displays it on the screen. The user can see the response containing the appropriate solution on the device's screen. This allows the user to quickly obtain a means to resolve the problem.

[0196] 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.

[0197] This invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to user inquiries. To implement this system, the system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0198] composition

[0199] 1. User's terminal

[0200] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0201] 2. Server

[0202] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0203] 3. Generative AI

[0204] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0205] 4. Emotional Engine

[0206] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results.

[0207] 5. Response adjustment

[0208] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0209] 6. Response Display

[0210] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0211] Program processing flow

[0212] The user enters an inquiry.

[0213] The user opens the inquiry form on their device, types "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", and presses the submit button.

[0214] The terminal sends a query to the server.

[0215] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0216] The server receives and analyzes the query.

[0217] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0218] The emotion engine recognizes emotions

[0219] The emotion engine analyzes the text of incoming inquiries to recognize the user's emotions. For example, if a user says something like "I'm in a lot of trouble," it determines that the user is expressing urgency and dissatisfaction.

[0220] Generative AI generates responses.

[0221] The generative AI takes into account the recognition results of the emotion engine to generate empathetic and prompt responses. For example, it might generate a response like, "We are very sorry. Could you please try the following steps to resolve the issue? If it still doesn't work, please contact our support team immediately."

[0222] The server receives the generated response and sends it to the terminal.

[0223] The server receives the response from the generative AI, formats it, and prepares it to send to the user's terminal.

[0224] The terminal receives and displays a response.

[0225] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0226] As a concrete example, the following inquiries are possible:

[0227] "Please explain the procedure for cross-connecting."

[0228] "What should I do if a connection problem occurs?"

[0229] "How do I use the remote hand service?"

[0230] By combining generative AI and an emotion engine, this system can provide more accurate and emotionally resonant responses to these inquiries. This system is highly effective in providing consistent support to users, even when multiple departments or individuals are involved.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" into the inquiry form, and clicks the submit button.

[0234] Step 2:

[0235] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal securely sends this data to the server using the HTTPS protocol.

[0236] Step 3:

[0237] The server receives the query. The server analyzes the received query content in JSON format and authentication information, and checks against the database to confirm whether the user is authenticated.

[0238] Step 4:

[0239] The server passes the query details to the sentiment engine. If authentication is successful, the server sends the query details to the sentiment recognition engine to analyze the user's emotions.

[0240] Step 5:

[0241] The emotion engine recognizes the user's emotions and sends the emotion data back to the server. For example, from the phrase "I am in a lot of trouble," the emotion engine recognizes the urgency and dissatisfaction and sends that information to the server.

[0242] Step 6:

[0243] The server adds emotional data to the analysis results and sends them to the generative AI. The server adds the received emotional data to the analysis results and sends a request to the generative AI's API endpoint.

[0244] Step 7:

[0245] The generative AI generates a response. Based on the analysis results and sentiment data, the generative AI generates a response saying, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately," and sends it back to the server.

[0246] Step 8:

[0247] The server receives the generated response. The server receives the response from the generative AI, converts it to the appropriate format, and prepares to send it to the user's terminal.

[0248] Step 9:

[0249] The server sends a response to the terminal. The server sends the generated response to the user's terminal using the HTTPS protocol.

[0250] Step 10:

[0251] The device receives the response and displays it on the screen. The user's device displays the response received from the server, which may say something like, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately." This allows the user to receive quick and appropriate information.

[0252] (Example 2)

[0253] 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".

[0254] Existing inquiry response systems fail to adequately consider user emotions and urgency, making it difficult to provide prompt and accurate responses. Furthermore, delays can occur during the process of properly formatting and resubmitting user inquiries, leading to decreased user satisfaction.

[0255] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for recognizing the emotion of the user's inquiry, response adjustment means for adjusting the response content based on the results of the emotion recognition means, and AI generation means for causing a generative AI to generate a response. This enables a quick and accurate response that takes into account the user's emotions and urgency.

[0256] "Input means" refers to devices or interfaces used by users to input inquiries.

[0257] A "server system" is a computer system that has the function of receiving and analyzing inquiries from users.

[0258] The "AI generation means" is a function that automatically generates an appropriate response using a generative AI based on the results analyzed by the server means.

[0259] "Output means" refers to a device or interface for reformatting the generated response and displaying it to the user.

[0260] "Emotion recognition means" refers to software or a device that has the function of analyzing emotions from a user's inquiry and recognizing those emotions.

[0261] "Response adjustment means" refers to software or a device that has the function of adjusting the generated response content based on the results of emotion recognition means.

[0262] "Authentication means" refers to software or a device that has the function of verifying a user's authentication information and confirming their identity.

[0263] "Transmission means" refers to a device or interface for formatting the generated response and sending it to the user's terminal.

[0264] The present invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to a user's inquiry. The system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0265] composition

[0266] 1. User's terminal

[0267] Users enter their inquiries using their own computers, smartphones, or other devices. The device provides an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS. Specifically, JavaScript is used to validate the input, and the inquiry content is sent to the server using the HTTPS protocol.

[0268] 2. Server

[0269] The server handles multiple functions, including receiving queries and verifying user authentication information. It also analyzes the received query content and passes it on to a generative AI for processing. Furthermore, it receives responses from the generative AI, converts them to the appropriate format, and sends them to the user's terminal. User authentication is performed using methods such as OAuth 2.0 or JWT (JSON Web Token). A natural language processing engine (e.g., spaCy) is used for text analysis.

[0270] 3. Generative AI

[0271] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is sent back to the server. The generative AI can use OpenAI's GPT-3.

[0272] 4. Emotional Engine

[0273] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results. Python libraries such as TextBlob are used for emotion recognition.

[0274] 5. Response adjustment

[0275] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0276] 6. Response Display

[0277] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to smoothly obtain clues to solve the problem. JavaScript or a front-end framework (e.g., React, Vue.js) is used for display.

[0278] Specific example

[0279] Let's say a user types and submits an inquiry asking, "Please tell me how to do cross-connect." This inquiry is converted to JSON format by the device and sent to the server. The server receives the inquiry, verifies the authentication information, and then passes the inquiry content to a natural language processing engine for analysis. The emotion engine recognizes the emotion from the text and sends a prompt to the generative AI based on the user's emotional state.

[0280] Specific examples of prompt statements are as follows:

[0281] "User Inquiry: Please teach me the cross-connect procedure."

[0282] "Result of the Emotion Engine: Without any particular emotional expression."

[0283] "Prompt for Generative AI: The user wants to know the cross-connect procedure. Please explain the procedure in detail."

[0284] Based on this prompt, the generative AI generates a response and provides a response saying, "For the cross-connect procedure, first access the dedicated page, enter the specified form, and submit it." The server reformats this response and sends it to the user's terminal. Finally, the terminal receives the response and displays it to the user. As a result, the user can quickly learn the necessary procedures.

[0285] With this system, the user can receive quick and accurate support and obtain a rich response that also meets emotional needs.

[0286] The flow of the specific process in Example 2 will be described using FIG. 13.

[0287] Step 1:

[0288] The user inputs an inquiry

[0289] The user opens an inquiry form on their terminal (computer or smartphone). The user enters inquiry content such as "I'm in great trouble. Please urgently resolve the connection problem!" and presses the "Send" button. The input data is converted into JSON format.

[0290] Input: User inquiry content (example: "I'm in great trouble. Please urgently resolve the connection problem!")

[0291] Output: Query data in JSON format (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345"})

[0292] Step 2:

[0293] The terminal sends a query to the server.

[0294] The terminal sends the user-entered query data in JSON format and authentication information to the server using the HTTPS protocol. The authentication information includes the user ID and token.

[0295] Input: JSON format query data, authentication information (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345", "token": "abcdef"})

[0296] Output: HTTPS request

[0297] Step 3:

[0298] The server receives and analyzes the query.

[0299] The server receives the query and verifies the user's authentication information. Once authentication is complete, the query content is passed to a natural language processing (NLP) engine. Here, spaCy is used as an example NLP engine.

[0300] Input: HTTPS request data (inquiry data in JSON format, authentication information)

[0301] Data processing / calculations: Authentication process, NLP analysis (e.g., text analysis of the "message" field)

[0302] Output: Parsed text data (example: {"intent": "troubleshoot_connection", "sentiment": "negative"})

[0303] Step 4:

[0304] The sentiment engine recognizes the sentiment

[0305] The server calls the sentiment engine (example: TextBlob) to recognize the sentiment from the text. The sentiment engine extracts urgency and dissatisfaction from "I'm very troubled".

[0306] Input: Parsed text data (example: {"intent": "troubleshoot_connection", "sentiment": "negative"})

[0307] Data processing / operation: Sentiment analysis

[0308] Output: Sentiment recognition data (example: {"emotion": "urgent_and_dissatisfied"})

[0309] Step 5:

[0310] The generative AI generates a response

[0311] The server sends the sentiment recognition data and the prompt text to the generative AI (example: GPT-3) to generate a response. The prompt text is "The user is having trouble connecting and wants it to be resolved quickly. Please generate a response showing a caring and prompt attitude."

[0312] Input: Sentiment recognition data, prompt text

[0313] Data processing / operation: Response generation by generative AI

[0314] Output: Generated response (Example: "We are very sorry. Please try the following steps to resolve the issue. If the problem persists, please contact our support team immediately.")

[0315] Step 6:

[0316] The server receives the generated response and sends it to the terminal.

[0317] The server receives the response from the generative AI and converts it into a format suitable for the user's device (e.g., HTML or text). A template engine (e.g., Jinja2) can be used for this conversion process. After conversion, the server sends the response back to the device using HTTPS.

[0318] Input: Generated response

[0319] Data processing / calculations: Format conversion (e.g., JSON to HTML)

[0320] Output: HTTPS response (Example: " We sincerely apologize. First, please try to resolve the issue by following the steps below. If the problem persists, please contact our support team immediately. ")

[0321] Step 7:

[0322] The terminal receives and displays a response.

[0323] The terminal receives a response from the server and displays it to the user using JavaScript or a front-end framework (e.g., React, Vue.js). This allows the user to smoothly obtain clues to solve the problem on the screen.

[0324] Input: HTTPS response (formatted response)

[0325] Output: Screen display (e.g., the response is displayed on a web page)

[0326] (Application Example 2)

[0327] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0328] Conventional inquiry systems generate uniform responses that do not take into account the user's emotions, which is problematic because they cannot adequately address user dissatisfaction or urgency. The present invention aims to improve user satisfaction by recognizing the user's emotions and generating appropriate responses based on those emotions.

[0329] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for the user to input an inquiry, an emotion recognition means for receiving the inquiry and recognizing the emotion, an AI generation means for causing a generative AI to generate a response based on the result of the emotion recognition means, and an output means for receiving the generated response and displaying it to the user. This enables flexible and appropriate responses that are attuned to the user's emotions.

[0330] An "input method" refers to a device or interface used by a user to input inquiries or information.

[0331] An "emotion recognition system" is a mechanism for analyzing and recognizing emotions from text and information entered by the user.

[0332] "AI generation means" refers to the function of artificial intelligence that generates appropriate responses based on the results of emotion recognition means.

[0333] "Output means" refers to a device or interface for displaying the generated response to the user.

[0334] An "authentication method" is a system used to verify a user's authentication information and confirm whether that user has legitimate access rights.

[0335] A "response adjustment mechanism" is a system that adjusts the generated response based on the user's emotions to make it more appropriate and emotionally resonant.

[0336] In order to implement this invention, it is necessary to construct a system that includes the following means: an input means for a user to input an inquiry; an emotion recognition means for receiving the inquiry and recognizing the emotion; an AI generation means for generating a response based on the results of the emotion recognition means; and an output means for displaying the generated response to the user.

[0337] Hardware and software configuration

[0338] Hardware configuration

[0339] 1. User terminal: A device used by a user to enter inquiries, such as a smartphone or computer.

[0340] 2. Server: A computer system that performs multiple functions (receiving queries, parsing, sentiment recognition, and response generation).

[0341] Software Configuration

[0342] 1. Input Interface: A web form or chat box for users to enter inquiries.

[0343] 2. Server program: Uses a framework such as FastAPI to receive and properly parse queries.

[0344] 3. Emotion Recognition Engine: Software used for emotion analysis, such as "EmotionEngine".

[0345] 4. Generative AI Models: Artificial intelligence models such as "AIModel" that generate appropriate responses while taking user emotions into consideration.

[0346] 5. Response Adjustment Program: A program to adjust responses from generative AI based on emotions.

[0347] 6. Output Interface: A screen display interface for showing the generated response to the user.

[0348] Specific usage examples

[0349] How to use the system

[0350] 1. Inquiry Input: Users enter questions or problems through a smartphone app. Alternatively, they may use a web form or chat box. Example: "My home alarm seems to be malfunctioning. What should I do?"

[0351] 2. Sending the inquiry: The entered inquiry is securely sent to the server using HTTPS.

[0352] 3. Emotion Recognition: The server analyzes the received inquiry using emotion recognition tools to recognize the user's emotions (anxiety, impatience, etc.).

[0353] 4. Response Generation: Based on the emotion recognition results, a generative AI model generates the optimal response. For example, "We are very sorry. Please try resetting the alarm first. If that does not resolve the issue, please contact our support team immediately."

[0354] 5. Response adjustment: Ensure that generated responses are appropriately adjusted based on emotions and are user-friendly.

[0355] 6. Display of response: Finally, the adjusted response sent from the server is displayed on the user's terminal.

[0356] This allows users to receive appropriate responses based on their emotions, leading to quicker and smoother problem resolution.

[0357] Example prompt statements

[0358] "It seems my home alarm is malfunctioning. What should I do?"

[0359] "We are in a very difficult situation. Please resolve the connection problem as soon as possible!"

[0360] Regardless of the type of inquiry a user makes, this system aims to consider the user's feelings and provide a prompt, appropriate, and empathetic response.

[0361] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0362] Step 1:

[0363] The user enters their inquiry. The user uses a smartphone app, web form, or chat box to enter their inquiry. For example, they might enter, "My home alarm seems to be malfunctioning. What should I do?" This input is recorded as text data on the device.

[0364] Step 2:

[0365] The terminal sends the query to the server. The user's input query is converted to JSON format and securely sent to the server. The HTTPS protocol is used to ensure data security. The input is a text-based query, and the output is a secure JSON-formatted request.

[0366] Step 3:

[0367] The server receives the query and performs emotion recognition. The server parses the received JSON data and extracts the text data. Then, it uses an emotion recognition engine (EmotionEngine) to analyze the text data and recognize the user's emotions (anxiety, impatience, anger, etc.). The input is the text data of the query, and the output is the emotion analysis result.

[0368] Step 4:

[0369] The server generates responses using a generative AI model (AIModel). The server creates a response generation prompt based on the results of the emotion recognition engine and passes it to the generative AI. For example, if the prompt "It seems my home alarm is malfunctioning. What should I do?" and the recognized emotion are input, the server will generate the response "We are very sorry. First, please try resetting the alarm. If that does not resolve the issue, please contact our support team immediately." The input is the prompt text and the emotion analysis result, and the output is the generated response.

[0370] Step 5:

[0371] The server adjusts the generated response. The response from the generative AI is appropriately adjusted based on the analysis results of the emotion recognition engine. For example, if the user is particularly anxious, it will include more empathetic and reassuring words. This adjustment is performed, and the optimized response is output. The input is the generated response, and the output is the adjusted response.

[0372] Step 6:

[0373] The server sends a refined response to the user's terminal. The optimized response is converted back into JSON format and sent to the user's terminal. The input is the refined response text data, and the output is the response data in secure JSON format.

[0374] Step 7:

[0375] The terminal receives and displays the response. The user's terminal receives the response data sent from the server and displays it on the screen. This allows the user to receive a quick and appropriate response. The input is the response data from the server, and the output is the text displayed on the user's screen.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] [Second Embodiment]

[0380] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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".

[0392] This invention relates to a system that allows users to make inquiries smoothly and obtain quick and accurate responses. To implement this system, the system includes a terminal for the user to input inquiries, a server that receives and processes inquiries, a generative AI that generates appropriate responses, and a terminal that displays the responses to the user.

[0393] composition

[0394] 1. User's terminal

[0395] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0396] 2. Server

[0397] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0398] 3. Generative AI

[0399] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0400] 4. Response Display

[0401] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0402] Program processing flow

[0403] The user enters an inquiry.

[0404] The user opens the inquiry form on their device, types "Please tell me how to deal with connection problems," and presses the submit button.

[0405] The terminal sends a query to the server.

[0406] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0407] The server receives and analyzes the query.

[0408] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0409] Generative AI generates responses.

[0410] Based on the analysis results received from the server, the generative AI generates a response that says, "If you experience connection problems, please try restarting your equipment first. If the problem persists, please contact professional support."

[0411] The server receives the generated response and sends it to the terminal.

[0412] The server receives the response from the generative AI, formats it, and sends it to the user's terminal.

[0413] The device displays a response.

[0414] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0415] As a concrete example, the following inquiries are possible:

[0416] "Please explain the procedure for cross-connecting."

[0417] "What should I do if a connection problem occurs?"

[0418] "How do I use the remote hand service?"

[0419] By having a generative AI generate individual responses to these inquiries and provide them to the user, the system can quickly resolve the user's problems. This system is highly effective as a means of providing consistent support to the user, even when multiple related departments or personnel are involved.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "Please tell me about the Cross Connect procedure" in the inquiry form, and clicks the submit button.

[0423] Step 2:

[0424] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal then sends this data to the server using the HTTPS protocol.

[0425] Step 3:

[0426] The server receives the query. The server parses the received query content in JSON format and authentication information, and compares it against the database to verify if the user is authenticated.

[0427] Step 4:

[0428] The server analyzes the query. If authentication is successful, the server passes the query to a natural language processing engine for intent analysis.

[0429] Step 5:

[0430] The server sends the analysis results to the generative AI. The server converts the analysis results into a format that the AI ​​engine can easily understand and makes a request to the generative AI's API endpoint.

[0431] Step 6:

[0432] The generative AI generates a response. Based on the received analysis results, the generative AI generates a response stating, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it," and sends it back to the server.

[0433] Step 7:

[0434] The server receives the generated response. The server converts the received response into the appropriate format and prepares to send it to the user's terminal.

[0435] Step 8:

[0436] The server sends a response to the terminal. The server converts the generated response into an appropriate format, such as JSON, and sends it to the user's terminal using the HTTPS protocol.

[0437] Step 9:

[0438] The terminal receives and displays the response. The user's terminal receives the response from the server and displays it on the screen. The user will see a message that reads, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it."

[0439] (Example 1)

[0440] 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."

[0441] Traditional inquiry systems have the drawback of long response times, making rapid problem resolution difficult. Furthermore, the quality of responses to inquiries is inconsistent, and there is little guarantee that users will receive satisfactory answers. Additionally, the increasing complexity of systems, including user authentication and data format conversion, presents challenges in terms of security and processing efficiency.

[0442] 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.

[0443] In this invention, the server includes input means for the user to input a query, server means for receiving and analyzing the query, generation means for causing a generative AI to generate a response based on the analysis results, output means for receiving the generated response and displaying it to the user, and formatting means for converting the response into an appropriate format. This enables the user to obtain a quick and accurate response. Furthermore, it improves the overall security and efficiency of the system and increases user satisfaction.

[0444] "Input method" refers to a device or software that provides an interface (such as a web form or chat box) for users to input inquiries.

[0445] "Server means" refers to devices or software that analyze the content of inquiries received from users and perform the necessary processing.

[0446] "Generation means" refers to a generative AI that generates an appropriate response based on the analysis results received from the server.

[0447] "Output means" refers to devices or software that receive the generated response and display it to the user.

[0448] "Formatting means" refers to the processing or device used to convert the generated response into an appropriate format and transmit it to the user.

[0449] "Authentication means" refers to a function that verifies a user's authentication information and confirms whether they are a legitimate user.

[0450] "Conversion means" refers to the processing or device used to format the generated response and send it to the user's terminal.

[0451] The system of this invention enables users to make inquiries smoothly and obtain quick and accurate responses. Specific components of the system include a user terminal, a server, a generative AI, and a terminal for displaying responses.

[0452] User's terminal

[0453] Users enter their inquiries using their own computers, smartphones, or other devices. Web forms and chat boxes are provided as input interfaces, allowing users to submit inquiries intuitively and easily. The device converts the user's input into JSON format and securely sends it to the server using HTTPS.

[0454] server

[0455] The server handles multiple functions. After receiving a query, it first verifies the user's authentication information. If authentication is successful, it passes the query content to a natural language processing engine for analysis. This analysis process uses libraries such as Python's "spaCy" or "NLTK". Based on the analysis results, it sends an API request to a generative AI to generate a response.

[0456] Generative AI

[0457] Generative AI receives analysis results from a server and generates an appropriate response. For example, if a user asks, "What should I do if I experience connection problems?", the generative AI will generate a specific response such as, "If you experience connection problems, first try restarting your equipment. If that doesn't solve the problem, please contact our dedicated support." Models such as "GPT-3" are often used for generative AI.

[0458] Response display

[0459] The server converts the response received from the generative AI into an appropriate format and sends it to the user's terminal. Formats such as HTML and JSON are used for this conversion. Finally, the terminal displays the received response to the user. This allows the user to obtain information quickly and accurately.

[0460] Specific example

[0461] The following examples will make it easier to understand how the system works.

[0462] Example 1: For a user who wants to know the procedure for cross-connecting.

[0463] The user types "Please tell me how to do CrossConnect" and sends it. The terminal converts it to JSON format and sends it to the server via HTTPS. The server receives it, analyzes it with the NLU module, and sends the result to the generative AI. The generative AI generates a response saying, "To do CrossConnect, first access the dedicated page, fill in the designated form, and submit it." The server formats the response and sends it to the terminal. The terminal receives the response and displays it on the browser screen.

[0464] Example 2: For a user who wants to know how to troubleshoot connection problems.

[0465] The user types and sends the question, "What should I do if I experience connection problems?" The server receives the message and sends it to the AI. The AI ​​generates a response: "If you experience connection problems, please try restarting your device first. If the problem persists, please contact our dedicated support." The terminal receives and displays the response.

[0466] Example of a prompt

[0467] The following are examples of prompt statements:

[0468] "Please explain the procedure for cross-connecting."

[0469] "What should I do if I encounter connection problems?"

[0470] "How do I use the remote hand service?"

[0471] This system allows users to receive quick and accurate responses to their inquiries, enabling smooth problem resolution.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The user enters an inquiry.

[0475] Users enter their inquiries into web forms or chat boxes on their devices. Through this input interface, users describe specific questions or problems. For example, a user might enter, "Please tell me how to deal with connection problems." This input data is then used directly in the next process.

[0476] Step 2:

[0477] The device sends the query to the server.

[0478] When the user presses the submit button, the device converts the inquiry content into JSON format and sends it to the server using the HTTPS protocol. The input data (user inquiry content) is sent as converted JSON data. Specific examples of libraries used include Python's "requests" library and JavaScript's "axios". At this time, the device also sends authentication information.

[0479] Step 3:

[0480] The server receives and analyzes the query.

[0481] The server receives JSON data sent from the terminal. First, it checks the authentication information to confirm that the query is from a legitimate user. After this, the server passes the query content to an NLU (Natural Language Understanding) module for analysis. Here, libraries such as Python's "spaCy" or "NLTK" are used for the analysis. As a result of the analysis, the intent of the query and important keywords are extracted.

[0482] Step 4:

[0483] The server sends a request to the generative AI.

[0484] The server sends a request to the generative AI based on the analysis results. This request includes the analyzed query content, and the generative AI makes an API call. Specifically, the analysis results are sent via the API request, and an appropriate answer is obtained as response data.

[0485] Step 5:

[0486] Generative AI generates responses.

[0487] The generative AI generates an appropriate response based on the received analysis results. For example, if the inquiry is "Please tell me how to deal with connection problems," it will generate a response such as "First, please try restarting your equipment. If that does not resolve the issue, please contact our specialist support." The generated response is then sent back to the server as an API response.

[0488] Step 6:

[0489] The server receives the generated response and formats it.

[0490] The server receives the response from the generative AI and converts it into an appropriate format for display to the user. For example, it performs conversion to formats such as HTML or JSON. The formatted data is then generated.

[0491] Step 7:

[0492] The server sends a response to the terminal.

[0493] The server sends formatted response data to the terminal. The data is then securely transmitted again using the HTTPS protocol. This data is in JSON or HTML format.

[0494] Step 8:

[0495] The device displays a response.

[0496] Ultimately, the device displays the received response to the user. The browser might display a message such as, "If you experience connection problems, please try restarting your device first. If the problem persists, please contact professional support." The user can then see this message and take appropriate action.

[0497] (Application Example 1)

[0498] 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."

[0499] In traditional security services, it is difficult for users to obtain the appropriate information necessary to quickly resolve security-related problems. Furthermore, the inability to provide appropriate and expert responses to inquiries often leads to delays in problem resolution. Therefore, a system is needed that provides quick and accurate solutions when users report security problems.

[0500] 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.

[0501] In this invention, the server includes input means for a user to input an inquiry, server means for receiving and analyzing the inquiry, AI generation means for causing a generative AI to generate a response based on the analysis results, response generation means for providing a method for resolving security-related problems, and output means for receiving the generated response and displaying it to the user. This makes it possible to respond quickly and accurately to security problems and promptly resolve user anxieties and problems.

[0502] An "input method" is an interface for users to enter their inquiries.

[0503] A "server system" refers to a server that receives and analyzes queries.

[0504] An "AI generation method" is a means of causing a generative AI to generate a response based on the analysis results.

[0505] A "response generation means" is a means for generating a response to provide a solution for security-related problems.

[0506] "Output means" refers to means for receiving the generated response and displaying it to the user.

[0507] "Authentication means" refers to a method for verifying a user's authentication information.

[0508] "Transmission means" refers to the means for formatting the generated response and sending it to the user's terminal.

[0509] "System" refers to the entire configuration that includes these means.

[0510] The embodiments for carrying out this invention will be described in detail below.

[0511] System Program Overview

[0512] The system of this invention consists of multiple components, which work together to provide a fast and accurate response to user inquiries. The main components of the system include input means, server means, AI generation means, response generation means, output means, authentication means, and transmission means.

[0513] Hardware and software usage

[0514] The system is implemented using the following hardware and software:

[0515] User terminal: The interface where the user enters their inquiry. This can be a smartphone (iOS or Android) or a computer.

[0516] Server: A cloud server that receives and analyzes queries. AWS EC2 can be used as a specific example.

[0517] Generative AI: AI that generates responses based on analysis results. A concrete example is the OpenAI GPT-3 API.

[0518] Natural language processing engine: An engine used to analyze query content. Examples include NLTK and SpaCy.

[0519] Program processing

[0520] When a user enters an inquiry from a device such as a smartphone or computer, the inquiry is converted into JSON format and sent to the server. The server analyzes the received inquiry and verifies the user's authentication information using an authentication method. If authentication is successful, the inquiry is analyzed by a natural language processing engine, and the analysis results are passed to an AI generation method, which generates an appropriate response. This response is reformatted and sent to the user's terminal, and finally displayed to the user by an output method.

[0521] Specific example

[0522] A user makes the following inquiry using their smartphone:

[0523] "I can no longer connect to the network."

[0524] This query is parsed by the server, and the following prompt is sent to the generative AI:

[0525] "A user reported being unable to connect to the network. Please provide possible causes and solutions."

[0526] The generative AI receives this prompt and generates the following response:

[0527] "If you can't connect to the network, first try restarting your router or modem. If that doesn't work, check that your device is connected to the correct network and try temporarily disabling your security software."

[0528] This response is reformatted, sent to the user's terminal via the transmission means, and finally displayed to the user by the output means.

[0529] In this way, the system of the present invention encompasses a series of processes from the input of an inquiry to the display of a response, enabling a rapid and accurate response to security problems.

[0530] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0531] Step 1:

[0532] The user enters their inquiry on their device.

[0533] The user enters the message "I can no longer connect to the network" into an input form displayed on their smartphone or computer screen and presses the submit button. This input is then converted into JSON format.

[0534] Step 2:

[0535] The terminal sends a query to the server.

[0536] The terminal converts the user's input into JSON format and then sends it to the server via HTTPS along with authentication information. During this process, the input data is encrypted before transmission.

[0537] Step 3:

[0538] The server receives the query and analyzes it.

[0539] The server stores the received query in a database and verifies the user's authentication information using an authentication method. If authentication is successful, the query content is passed to a natural language processing engine (e.g., NLTK or SpaCy) for text analysis. The analysis results include the intent of the query and important keywords.

[0540] Step 4:

[0541] The generative AI generates the response.

[0542] The server passes the analysis results to the AI ​​generation system, which then sends a prompt message to the generative AI (for example, OpenAI's GPT-3 API). An example of a prompt message is: "The user has reported being unable to connect to the network. Please indicate possible causes and solutions." The generative AI analyzes the prompt message and generates an appropriate response: "If you are unable to connect to the network, first try restarting your router or modem. If that doesn't solve the problem, check that your device is connected to the correct network and try temporarily disabling your security software."

[0543] Step 5:

[0544] The server receives the generated response and formats it.

[0545] The server receives the response from the generative AI and formats it as needed. This formatting includes converting the response into a simple and easy-to-read format. For example, it may add specific tags or styles.

[0546] Step 6:

[0547] The server sends a response to the terminal.

[0548] The formatted response is converted to JSON format and sent to the user's terminal via HTTPS. This transmitted data is also encrypted.

[0549] Step 7:

[0550] The terminal receives and displays the response.

[0551] The user's device analyzes the response received from the server and displays it on the screen. The user can see the response containing the appropriate solution on the device's screen. This allows the user to quickly obtain a means to resolve the problem.

[0552] 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.

[0553] This invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to user inquiries. To implement this system, the system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0554] composition

[0555] 1. User's terminal

[0556] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0557] 2. Server

[0558] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0559] 3. Generative AI

[0560] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0561] 4. Emotional Engine

[0562] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results.

[0563] 5. Response adjustment

[0564] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0565] 6. Response Display

[0566] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0567] Program processing flow

[0568] The user enters an inquiry.

[0569] The user opens the inquiry form on their device, types "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", and presses the submit button.

[0570] The terminal sends a query to the server.

[0571] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0572] The server receives and analyzes the query.

[0573] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0574] The emotion engine recognizes emotions

[0575] The emotion engine analyzes the text of incoming inquiries to recognize the user's emotions. For example, if a user says something like "I'm in a lot of trouble," it determines that the user is expressing urgency and dissatisfaction.

[0576] Generative AI generates responses.

[0577] The generative AI takes into account the recognition results of the emotion engine to generate empathetic and prompt responses. For example, it might generate a response like, "We are very sorry. Could you please try the following steps to resolve the issue? If it still doesn't work, please contact our support team immediately."

[0578] The server receives the generated response and sends it to the terminal.

[0579] The server receives the response from the generative AI, formats it, and prepares it to send to the user's terminal.

[0580] The terminal receives and displays a response.

[0581] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0582] As a concrete example, the following inquiries are possible:

[0583] "Please explain the procedure for cross-connecting."

[0584] "What should I do if a connection problem occurs?"

[0585] "How do I use the remote hand service?"

[0586] By combining generative AI and an emotion engine, this system can provide more accurate and emotionally resonant responses to these inquiries. This system is highly effective in providing consistent support to users, even when multiple departments or individuals are involved.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" into the inquiry form, and clicks the submit button.

[0590] Step 2:

[0591] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal securely sends this data to the server using the HTTPS protocol.

[0592] Step 3:

[0593] The server receives the query. The server analyzes the received query content in JSON format and authentication information, and checks against the database to confirm whether the user is authenticated.

[0594] Step 4:

[0595] The server passes the query details to the sentiment engine. If authentication is successful, the server sends the query details to the sentiment recognition engine to analyze the user's emotions.

[0596] Step 5:

[0597] The emotion engine recognizes the user's emotions and sends the emotion data back to the server. For example, from the phrase "I am in a lot of trouble," the emotion engine recognizes the urgency and dissatisfaction and sends that information to the server.

[0598] Step 6:

[0599] The server adds emotional data to the analysis results and sends them to the generative AI. The server adds the received emotional data to the analysis results and sends a request to the generative AI's API endpoint.

[0600] Step 7:

[0601] The generative AI generates a response. Based on the analysis results and sentiment data, the generative AI generates a response saying, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately," and sends it back to the server.

[0602] Step 8:

[0603] The server receives the generated response. The server receives the response from the generative AI, converts it to the appropriate format, and prepares to send it to the user's terminal.

[0604] Step 9:

[0605] The server sends a response to the terminal. The server sends the generated response to the user's terminal using the HTTPS protocol.

[0606] Step 10:

[0607] The device receives the response and displays it on the screen. The user's device displays the response received from the server, which may say something like, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately." This allows the user to receive quick and appropriate information.

[0608] (Example 2)

[0609] 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".

[0610] Existing inquiry response systems fail to adequately consider user emotions and urgency, making it difficult to provide prompt and accurate responses. Furthermore, delays can occur during the process of properly formatting and resubmitting user inquiries, leading to decreased user satisfaction.

[0611] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for recognizing the emotion of the user's inquiry, response adjustment means for adjusting the response content based on the results of the emotion recognition means, and AI generation means for causing a generative AI to generate a response. This enables a quick and accurate response that takes into account the user's emotions and urgency.

[0612] "Input means" refers to devices or interfaces used by users to input inquiries.

[0613] A "server system" is a computer system that has the function of receiving and analyzing inquiries from users.

[0614] The "AI generation means" is a function that automatically generates an appropriate response using a generative AI based on the results analyzed by the server means.

[0615] "Output means" refers to a device or interface for reformatting the generated response and displaying it to the user.

[0616] "Emotion recognition means" refers to software or a device that has the function of analyzing emotions from a user's inquiry and recognizing those emotions.

[0617] "Response adjustment means" refers to software or a device that has the function of adjusting the generated response content based on the results of emotion recognition means.

[0618] "Authentication means" refers to software or a device that has the function of verifying a user's authentication information and confirming their identity.

[0619] "Transmission means" refers to a device or interface for formatting the generated response and sending it to the user's terminal.

[0620] The present invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to a user's inquiry. The system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0621] composition

[0622] 1. User's terminal

[0623] Users enter their inquiries using their own computers, smartphones, or other devices. The device provides an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS. Specifically, JavaScript is used to validate the input, and the inquiry content is sent to the server using the HTTPS protocol.

[0624] 2. Server

[0625] The server handles multiple functions, including receiving queries and verifying user authentication information. It also analyzes the received query content and passes it on to a generative AI for processing. Furthermore, it receives responses from the generative AI, converts them to the appropriate format, and sends them to the user's terminal. User authentication is performed using methods such as OAuth 2.0 or JWT (JSON Web Token). A natural language processing engine (e.g., spaCy) is used for text analysis.

[0626] 3. Generative AI

[0627] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is sent back to the server. The generative AI can use OpenAI's GPT-3.

[0628] 4. Emotional Engine

[0629] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results. Python libraries such as TextBlob are used for emotion recognition.

[0630] 5. Response adjustment

[0631] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0632] 6. Response Display

[0633] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to smoothly obtain clues to solve the problem. JavaScript or a front-end framework (e.g., React, Vue.js) is used for display.

[0634] Specific example

[0635] Let's say a user types and submits an inquiry asking, "Please tell me how to do cross-connect." This inquiry is converted to JSON format by the device and sent to the server. The server receives the inquiry, verifies the authentication information, and then passes the inquiry content to a natural language processing engine for analysis. The emotion engine recognizes the emotion from the text and sends a prompt to the generative AI based on the user's emotional state.

[0636] Specific examples of prompt statements are as follows:

[0637] "User Inquiry: Please explain the procedure for cross-connecting."

[0638] "Emotional Engine Result: No particular emotional expression."

[0639] "Prompt to the generative AI: The user wants to know the procedure for cross-connecting. Please explain the procedure in detail."

[0640] The generative AI generates a response based on this prompt, providing a response such as, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it." The server reformats this response and sends it to the user's terminal. Finally, the terminal receives the response and displays it to the user. This allows the user to quickly learn the necessary procedures.

[0641] This system allows users to receive prompt and accurate support, as well as comprehensive responses that address their emotional needs.

[0642] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0643] Step 1:

[0644] The user enters an inquiry.

[0645] The user opens the inquiry form on their device (computer or smartphone). The user enters an inquiry message such as, "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" and presses the "Send" button. The input data is converted to JSON format.

[0646] Input: User's inquiry (Example: "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!")

[0647] Output: Query data in JSON format (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345"})

[0648] Step 2:

[0649] The terminal sends a query to the server.

[0650] The terminal sends the user-entered query data in JSON format and authentication information to the server using the HTTPS protocol. The authentication information includes the user ID and token.

[0651] Input: JSON format query data, authentication information (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345", "token": "abcdef"})

[0652] Output: HTTPS request

[0653] Step 3:

[0654] The server receives and analyzes the query.

[0655] The server receives the query and verifies the user's authentication information. Once authentication is complete, the query content is passed to a natural language processing (NLP) engine. Here, spaCy is used as an example NLP engine.

[0656] Input: HTTPS request data (inquiry data in JSON format, authentication information)

[0657] Data processing / calculations: Authentication process, NLP analysis (e.g., text analysis of the "message" field)

[0658] Output: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[0659] Step 4:

[0660] The emotion engine recognizes emotions

[0661] The server invokes an emotion engine (e.g., TextBlob) to recognize emotions from the text. The emotion engine extracts urgency and frustration from "I'm in a lot of trouble."

[0662] Input: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[0663] Data processing / calculation: Sentiment analysis

[0664] Output: Emotion recognition data (Example: {"emotion": "urgent_and_dissatisfied"})

[0665] Step 5:

[0666] Generative AI generates responses.

[0667] The server sends emotion recognition data and a prompt message to a generative AI (e.g., GPT-3) to generate a response. The prompt message would be: "The user is experiencing connection problems and wants to resolve them as quickly as possible. Please generate a response that shows empathy and prompt assistance."

[0668] Input: emotion recognition data, prompt text

[0669] Data processing / calculation: Response generation by generative AI

[0670] Output: Generated response (Example: "We are very sorry. Please try the following steps to resolve the issue. If the problem persists, please contact our support team immediately.")

[0671] Step 6:

[0672] The server receives the generated response and sends it to the terminal.

[0673] The server receives the response from the generative AI and converts it into a format suitable for the user's device (e.g., HTML or text). A template engine (e.g., Jinja2) can be used for this conversion process. After conversion, the server sends the response back to the device using HTTPS.

[0674] Input: Generated response

[0675] Data processing / calculations: Format conversion (e.g., JSON to HTML)

[0676] Output: HTTPS response (Example: " We sincerely apologize. First, please try to resolve the issue by following the steps below. If the problem persists, please contact our support team immediately. ")

[0677] Step 7:

[0678] The terminal receives and displays a response.

[0679] The terminal receives a response from the server and displays it to the user using JavaScript or a front-end framework (e.g., React, Vue.js). This allows the user to smoothly obtain clues to solve the problem on the screen.

[0680] Input: HTTPS response (formatted response)

[0681] Output: Screen display (e.g., the response is displayed on a web page)

[0682] (Application Example 2)

[0683] 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."

[0684] Conventional inquiry systems generate uniform responses that do not take into account the user's emotions, which is problematic because they cannot adequately address user dissatisfaction or urgency. The present invention aims to improve user satisfaction by recognizing the user's emotions and generating appropriate responses based on those emotions.

[0685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for the user to input an inquiry, an emotion recognition means for receiving the inquiry and recognizing the emotion, an AI generation means for causing a generative AI to generate a response based on the result of the emotion recognition means, and an output means for receiving the generated response and displaying it to the user. This enables flexible and appropriate responses that are attuned to the user's emotions.

[0686] An "input method" refers to a device or interface used by a user to input inquiries or information.

[0687] An "emotion recognition system" is a mechanism for analyzing and recognizing emotions from text and information entered by the user.

[0688] "AI generation means" refers to the function of artificial intelligence that generates appropriate responses based on the results of emotion recognition means.

[0689] "Output means" refers to a device or interface for displaying the generated response to the user.

[0690] An "authentication method" is a system used to verify a user's authentication information and confirm whether that user has legitimate access rights.

[0691] A "response adjustment mechanism" is a system that adjusts the generated response based on the user's emotions to make it more appropriate and emotionally resonant.

[0692] In order to implement this invention, it is necessary to construct a system that includes the following means: an input means for a user to input an inquiry; an emotion recognition means for receiving the inquiry and recognizing the emotion; an AI generation means for generating a response based on the results of the emotion recognition means; and an output means for displaying the generated response to the user.

[0693] Hardware and software configuration

[0694] Hardware configuration

[0695] 1. User terminal: A device used by a user to enter inquiries, such as a smartphone or computer.

[0696] 2. Server: A computer system that performs multiple functions (receiving queries, parsing, sentiment recognition, and response generation).

[0697] Software Configuration

[0698] 1. Input Interface: A web form or chat box for users to enter inquiries.

[0699] 2. Server program: Uses a framework such as FastAPI to receive and properly parse queries.

[0700] 3. Emotion Recognition Engine: Software used for emotion analysis, such as "EmotionEngine".

[0701] 4. Generative AI Models: Artificial intelligence models such as "AIModel" that generate appropriate responses while taking user emotions into consideration.

[0702] 5. Response Adjustment Program: A program to adjust responses from generative AI based on emotions.

[0703] 6. Output Interface: A screen display interface for showing the generated response to the user.

[0704] Specific usage examples

[0705] How to use the system

[0706] 1. Inquiry Input: Users enter questions or problems through a smartphone app. Alternatively, they may use a web form or chat box. Example: "My home alarm seems to be malfunctioning. What should I do?"

[0707] 2. Sending the inquiry: The entered inquiry is securely sent to the server using HTTPS.

[0708] 3. Emotion Recognition: The server analyzes the received inquiry using emotion recognition tools to recognize the user's emotions (anxiety, impatience, etc.).

[0709] 4. Response Generation: Based on the emotion recognition results, a generative AI model generates the optimal response. For example, "We are very sorry. Please try resetting the alarm first. If that does not resolve the issue, please contact our support team immediately."

[0710] 5. Response adjustment: Ensure that generated responses are appropriately adjusted based on emotions and are user-friendly.

[0711] 6. Display of response: Finally, the adjusted response sent from the server is displayed on the user's terminal.

[0712] This allows users to receive appropriate responses based on their emotions, leading to quicker and smoother problem resolution.

[0713] Example prompt statements

[0714] "It seems my home alarm is malfunctioning. What should I do?"

[0715] "We are in a very difficult situation. Please resolve the connection problem as soon as possible!"

[0716] Regardless of the type of inquiry a user makes, this system aims to consider the user's feelings and provide a prompt, appropriate, and empathetic response.

[0717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0718] Step 1:

[0719] The user enters their inquiry. The user uses a smartphone app, web form, or chat box to enter their inquiry. For example, they might enter, "My home alarm seems to be malfunctioning. What should I do?" This input is recorded as text data on the device.

[0720] Step 2:

[0721] The terminal sends the query to the server. The user's input query is converted to JSON format and securely sent to the server. The HTTPS protocol is used to ensure data security. The input is a text-based query, and the output is a secure JSON-formatted request.

[0722] Step 3:

[0723] The server receives the query and performs emotion recognition. The server parses the received JSON data and extracts the text data. Then, it uses an emotion recognition engine (EmotionEngine) to analyze the text data and recognize the user's emotions (anxiety, impatience, anger, etc.). The input is the text data of the query, and the output is the emotion analysis result.

[0724] Step 4:

[0725] The server generates responses using a generative AI model (AIModel). The server creates a response generation prompt based on the results of the emotion recognition engine and passes it to the generative AI. For example, if the prompt "It seems my home alarm is malfunctioning. What should I do?" and the recognized emotion are input, the server will generate the response "We are very sorry. First, please try resetting the alarm. If that does not resolve the issue, please contact our support team immediately." The input is the prompt text and the emotion analysis result, and the output is the generated response.

[0726] Step 5:

[0727] The server adjusts the generated response. The response from the generative AI is appropriately adjusted based on the analysis results of the emotion recognition engine. For example, if the user is particularly anxious, it will include more empathetic and reassuring words. This adjustment is performed, and the optimized response is output. The input is the generated response, and the output is the adjusted response.

[0728] Step 6:

[0729] The server sends a refined response to the user's terminal. The optimized response is converted back into JSON format and sent to the user's terminal. The input is the refined response text data, and the output is the response data in secure JSON format.

[0730] Step 7:

[0731] The terminal receives and displays the response. The user's terminal receives the response data sent from the server and displays it on the screen. This allows the user to receive a quick and appropriate response. The input is the response data from the server, and the output is the text displayed on the user's screen.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] [Third Embodiment]

[0736] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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).

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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".

[0748] This invention relates to a system that allows users to make inquiries smoothly and obtain quick and accurate responses. To implement this system, the system includes a terminal for the user to input inquiries, a server that receives and processes inquiries, a generative AI that generates appropriate responses, and a terminal that displays the responses to the user.

[0749] composition

[0750] 1. User's terminal

[0751] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0752] 2. Server

[0753] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0754] 3. Generative AI

[0755] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0756] 4. Response Display

[0757] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0758] Program processing flow

[0759] The user enters an inquiry.

[0760] The user opens the inquiry form on their device, types "Please tell me how to deal with connection problems," and presses the submit button.

[0761] The terminal sends a query to the server.

[0762] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0763] The server receives and analyzes the query.

[0764] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0765] Generative AI generates responses.

[0766] Based on the analysis results received from the server, the generative AI generates a response that says, "If you experience connection problems, please try restarting your equipment first. If the problem persists, please contact professional support."

[0767] The server receives the generated response and sends it to the terminal.

[0768] The server receives the response from the generative AI, formats it, and sends it to the user's terminal.

[0769] The device displays a response.

[0770] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0771] As a concrete example, the following inquiries are possible:

[0772] "Please explain the procedure for cross-connecting."

[0773] "What should I do if a connection problem occurs?"

[0774] "How do I use the remote hand service?"

[0775] By having a generative AI generate individual responses to these inquiries and provide them to the user, the system can quickly resolve the user's problems. This system is highly effective as a means of providing consistent support to the user, even when multiple related departments or personnel are involved.

[0776] The following describes the processing flow.

[0777] Step 1:

[0778] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "Please tell me about the Cross Connect procedure" in the inquiry form, and clicks the submit button.

[0779] Step 2:

[0780] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal then sends this data to the server using the HTTPS protocol.

[0781] Step 3:

[0782] The server receives the query. The server parses the received query content in JSON format and authentication information, and compares it against the database to verify if the user is authenticated.

[0783] Step 4:

[0784] The server analyzes the query. If authentication is successful, the server passes the query to a natural language processing engine for intent analysis.

[0785] Step 5:

[0786] The server sends the analysis results to the generative AI. The server converts the analysis results into a format that the AI ​​engine can easily understand and makes a request to the generative AI's API endpoint.

[0787] Step 6:

[0788] The generative AI generates a response. Based on the received analysis results, the generative AI generates a response stating, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it," and sends it back to the server.

[0789] Step 7:

[0790] The server receives the generated response. The server converts the received response into the appropriate format and prepares to send it to the user's terminal.

[0791] Step 8:

[0792] The server sends a response to the terminal. The server converts the generated response into an appropriate format, such as JSON, and sends it to the user's terminal using the HTTPS protocol.

[0793] Step 9:

[0794] The terminal receives and displays the response. The user's terminal receives the response from the server and displays it on the screen. The user will see a message that reads, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it."

[0795] (Example 1)

[0796] 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."

[0797] Traditional inquiry systems have the drawback of long response times, making rapid problem resolution difficult. Furthermore, the quality of responses to inquiries is inconsistent, and there is little guarantee that users will receive satisfactory answers. Additionally, the increasing complexity of systems, including user authentication and data format conversion, presents challenges in terms of security and processing efficiency.

[0798] 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.

[0799] In this invention, the server includes input means for the user to input a query, server means for receiving and analyzing the query, generation means for causing a generative AI to generate a response based on the analysis results, output means for receiving the generated response and displaying it to the user, and formatting means for converting the response into an appropriate format. This enables the user to obtain a quick and accurate response. Furthermore, it improves the overall security and efficiency of the system and increases user satisfaction.

[0800] "Input method" refers to a device or software that provides an interface (such as a web form or chat box) for users to input inquiries.

[0801] "Server means" refers to devices or software that analyze the content of inquiries received from users and perform the necessary processing.

[0802] "Generation means" refers to a generative AI that generates an appropriate response based on the analysis results received from the server.

[0803] "Output means" refers to devices or software that receive the generated response and display it to the user.

[0804] "Formatting means" refers to the processing or device used to convert the generated response into an appropriate format and transmit it to the user.

[0805] "Authentication means" refers to a function that verifies a user's authentication information and confirms whether they are a legitimate user.

[0806] "Conversion means" refers to the processing or device used to format the generated response and send it to the user's terminal.

[0807] The system of this invention enables users to make inquiries smoothly and obtain quick and accurate responses. Specific components of the system include a user terminal, a server, a generative AI, and a terminal for displaying responses.

[0808] User's terminal

[0809] Users enter their inquiries using their own computers, smartphones, or other devices. Web forms and chat boxes are provided as input interfaces, allowing users to submit inquiries intuitively and easily. The device converts the user's input into JSON format and securely sends it to the server using HTTPS.

[0810] server

[0811] The server handles multiple functions. After receiving a query, it first verifies the user's authentication information. If authentication is successful, it passes the query content to a natural language processing engine for analysis. This analysis process uses libraries such as Python's "spaCy" or "NLTK". Based on the analysis results, it sends an API request to a generative AI to generate a response.

[0812] Generative AI

[0813] Generative AI receives analysis results from a server and generates an appropriate response. For example, if a user asks, "What should I do if I experience connection problems?", the generative AI will generate a specific response such as, "If you experience connection problems, first try restarting your equipment. If that doesn't solve the problem, please contact our dedicated support." Models such as "GPT-3" are often used for generative AI.

[0814] Response display

[0815] The server converts the response received from the generative AI into an appropriate format and sends it to the user's terminal. Formats such as HTML and JSON are used for this conversion. Finally, the terminal displays the received response to the user. This allows the user to obtain information quickly and accurately.

[0816] Specific example

[0817] The following examples will make it easier to understand how the system works.

[0818] Example 1: For a user who wants to know the procedure for cross-connecting.

[0819] The user types "Please tell me how to do CrossConnect" and sends it. The terminal converts it to JSON format and sends it to the server via HTTPS. The server receives it, analyzes it with the NLU module, and sends the result to the generative AI. The generative AI generates a response saying, "To do CrossConnect, first access the dedicated page, fill in the designated form, and submit it." The server formats the response and sends it to the terminal. The terminal receives the response and displays it on the browser screen.

[0820] Example 2: For a user who wants to know how to troubleshoot connection problems.

[0821] The user types and sends the question, "What should I do if I experience connection problems?" The server receives the message and sends it to the AI. The AI ​​generates a response: "If you experience connection problems, please try restarting your device first. If the problem persists, please contact our dedicated support." The terminal receives and displays the response.

[0822] Example of a prompt

[0823] The following are examples of prompt statements:

[0824] "Please explain the procedure for cross-connecting."

[0825] "What should I do if I encounter connection problems?"

[0826] "How do I use the remote hand service?"

[0827] This system allows users to receive quick and accurate responses to their inquiries, enabling smooth problem resolution.

[0828] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0829] Step 1:

[0830] The user enters an inquiry.

[0831] Users enter their inquiries into web forms or chat boxes on their devices. Through this input interface, users describe specific questions or problems. For example, a user might enter, "Please tell me how to deal with connection problems." This input data is then used directly in the next process.

[0832] Step 2:

[0833] The device sends the query to the server.

[0834] When the user presses the submit button, the device converts the inquiry content into JSON format and sends it to the server using the HTTPS protocol. The input data (user inquiry content) is sent as converted JSON data. Specific examples of libraries used include Python's "requests" library and JavaScript's "axios". At this time, the device also sends authentication information.

[0835] Step 3:

[0836] The server receives and analyzes the query.

[0837] The server receives JSON data sent from the terminal. First, it checks the authentication information to confirm that the query is from a legitimate user. After this, the server passes the query content to an NLU (Natural Language Understanding) module for analysis. Here, libraries such as Python's "spaCy" or "NLTK" are used for the analysis. As a result of the analysis, the intent of the query and important keywords are extracted.

[0838] Step 4:

[0839] The server sends a request to the generative AI.

[0840] The server sends a request to the generative AI based on the analysis results. This request includes the analyzed query content, and the generative AI makes an API call. Specifically, the analysis results are sent via the API request, and an appropriate answer is obtained as response data.

[0841] Step 5:

[0842] Generative AI generates responses.

[0843] The generative AI generates an appropriate response based on the received analysis results. For example, if the inquiry is "Please tell me how to deal with connection problems," it will generate a response such as "First, please try restarting your equipment. If that does not resolve the issue, please contact our specialist support." The generated response is then sent back to the server as an API response.

[0844] Step 6:

[0845] The server receives the generated response and formats it.

[0846] The server receives the response from the generative AI and converts it into an appropriate format for display to the user. For example, it performs conversion to formats such as HTML or JSON. The formatted data is then generated.

[0847] Step 7:

[0848] The server sends a response to the terminal.

[0849] The server sends formatted response data to the terminal. The data is then securely transmitted again using the HTTPS protocol. This data is in JSON or HTML format.

[0850] Step 8:

[0851] The device displays a response.

[0852] Ultimately, the device displays the received response to the user. The browser might display a message such as, "If you experience connection problems, please try restarting your device first. If the problem persists, please contact professional support." The user can then see this message and take appropriate action.

[0853] (Application Example 1)

[0854] 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."

[0855] In traditional security services, it is difficult for users to obtain the appropriate information necessary to quickly resolve security-related problems. Furthermore, the inability to provide appropriate and expert responses to inquiries often leads to delays in problem resolution. Therefore, a system is needed that provides quick and accurate solutions when users report security problems.

[0856] 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.

[0857] In this invention, the server includes input means for a user to input an inquiry, server means for receiving and analyzing the inquiry, AI generation means for causing a generative AI to generate a response based on the analysis results, response generation means for providing a method for resolving security-related problems, and output means for receiving the generated response and displaying it to the user. This makes it possible to respond quickly and accurately to security problems and promptly resolve user anxieties and problems.

[0858] An "input method" is an interface for users to enter their inquiries.

[0859] A "server system" refers to a server that receives and analyzes queries.

[0860] An "AI generation method" is a means of causing a generative AI to generate a response based on the analysis results.

[0861] A "response generation means" is a means for generating a response to provide a solution for security-related problems.

[0862] "Output means" refers to means for receiving the generated response and displaying it to the user.

[0863] "Authentication means" refers to a method for verifying a user's authentication information.

[0864] "Transmission means" refers to the means for formatting the generated response and sending it to the user's terminal.

[0865] "System" refers to the entire configuration that includes these means.

[0866] The embodiments for carrying out this invention will be described in detail below.

[0867] System Program Overview

[0868] The system of this invention consists of multiple components, which work together to provide a fast and accurate response to user inquiries. The main components of the system include input means, server means, AI generation means, response generation means, output means, authentication means, and transmission means.

[0869] Hardware and software usage

[0870] The system is implemented using the following hardware and software:

[0871] User terminal: The interface where the user enters their inquiry. This can be a smartphone (iOS or Android) or a computer.

[0872] Server: A cloud server that receives and analyzes queries. AWS EC2 can be used as a specific example.

[0873] Generative AI: AI that generates responses based on analysis results. A concrete example is the OpenAI GPT-3 API.

[0874] Natural language processing engine: An engine used to analyze query content. Examples include NLTK and SpaCy.

[0875] Program processing

[0876] When a user enters an inquiry from a device such as a smartphone or computer, the inquiry is converted into JSON format and sent to the server. The server analyzes the received inquiry and verifies the user's authentication information using an authentication method. If authentication is successful, the inquiry is analyzed by a natural language processing engine, and the analysis results are passed to an AI generation method, which generates an appropriate response. This response is reformatted and sent to the user's terminal, and finally displayed to the user by an output method.

[0877] Specific example

[0878] A user makes the following inquiry using their smartphone:

[0879] "I can no longer connect to the network."

[0880] This query is parsed by the server, and the following prompt is sent to the generative AI:

[0881] "A user reported being unable to connect to the network. Please provide possible causes and solutions."

[0882] The generative AI receives this prompt and generates the following response:

[0883] "If you can't connect to the network, first try restarting your router or modem. If that doesn't work, check that your device is connected to the correct network and try temporarily disabling your security software."

[0884] This response is reformatted, sent to the user's terminal via the transmission means, and finally displayed to the user by the output means.

[0885] In this way, the system of the present invention encompasses a series of processes from the input of an inquiry to the display of a response, enabling a rapid and accurate response to security problems.

[0886] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0887] Step 1:

[0888] The user enters their inquiry on their device.

[0889] The user enters the message "I can no longer connect to the network" into an input form displayed on their smartphone or computer screen and presses the submit button. This input is then converted into JSON format.

[0890] Step 2:

[0891] The terminal sends a query to the server.

[0892] The terminal converts the user's input into JSON format and then sends it to the server via HTTPS along with authentication information. During this process, the input data is encrypted before transmission.

[0893] Step 3:

[0894] The server receives the query and analyzes it.

[0895] The server stores the received query in a database and verifies the user's authentication information using an authentication method. If authentication is successful, the query content is passed to a natural language processing engine (e.g., NLTK or SpaCy) for text analysis. The analysis results include the intent of the query and important keywords.

[0896] Step 4:

[0897] The generative AI generates the response.

[0898] The server passes the analysis results to the AI ​​generation system, which then sends a prompt message to the generative AI (for example, OpenAI's GPT-3 API). An example of a prompt message is: "The user has reported being unable to connect to the network. Please indicate possible causes and solutions." The generative AI analyzes the prompt message and generates an appropriate response: "If you are unable to connect to the network, first try restarting your router or modem. If that doesn't solve the problem, check that your device is connected to the correct network and try temporarily disabling your security software."

[0899] Step 5:

[0900] The server receives the generated response and formats it.

[0901] The server receives the response from the generative AI and formats it as needed. This formatting includes converting the response into a simple and easy-to-read format. For example, it may add specific tags or styles.

[0902] Step 6:

[0903] The server sends a response to the terminal.

[0904] The formatted response is converted to JSON format and sent to the user's terminal via HTTPS. This transmitted data is also encrypted.

[0905] Step 7:

[0906] The terminal receives and displays the response.

[0907] The user's device analyzes the response received from the server and displays it on the screen. The user can see the response containing the appropriate solution on the device's screen. This allows the user to quickly obtain a means to resolve the problem.

[0908] 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.

[0909] This invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to user inquiries. To implement this system, the system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0910] composition

[0911] 1. User's terminal

[0912] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[0913] 2. Server

[0914] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[0915] 3. Generative AI

[0916] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[0917] 4. Emotional Engine

[0918] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results.

[0919] 5. Response adjustment

[0920] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0921] 6. Response Display

[0922] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[0923] Program processing flow

[0924] The user enters an inquiry.

[0925] The user opens the inquiry form on their device, types "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", and presses the submit button.

[0926] The terminal sends a query to the server.

[0927] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[0928] The server receives and analyzes the query.

[0929] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[0930] The emotion engine recognizes emotions

[0931] The emotion engine analyzes the text of incoming inquiries to recognize the user's emotions. For example, if a user says something like "I'm in a lot of trouble," it determines that the user is expressing urgency and dissatisfaction.

[0932] Generative AI generates responses.

[0933] The generative AI takes into account the recognition results of the emotion engine to generate empathetic and prompt responses. For example, it might generate a response like, "We are very sorry. Could you please try the following steps to resolve the issue? If it still doesn't work, please contact our support team immediately."

[0934] The server receives the generated response and sends it to the terminal.

[0935] The server receives the response from the generative AI, formats it, and prepares it to send to the user's terminal.

[0936] The terminal receives and displays a response.

[0937] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[0938] As a concrete example, the following inquiries are possible:

[0939] "Please explain the procedure for cross-connecting."

[0940] "What should I do if a connection problem occurs?"

[0941] "How do I use the remote hand service?"

[0942] By combining generative AI and an emotion engine, this system can provide more accurate and emotionally resonant responses to these inquiries. This system is highly effective in providing consistent support to users, even when multiple departments or individuals are involved.

[0943] The following describes the processing flow.

[0944] Step 1:

[0945] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" into the inquiry form, and clicks the submit button.

[0946] Step 2:

[0947] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal securely sends this data to the server using the HTTPS protocol.

[0948] Step 3:

[0949] The server receives the query. The server analyzes the received query content in JSON format and authentication information, and checks against the database to confirm whether the user is authenticated.

[0950] Step 4:

[0951] The server passes the query details to the sentiment engine. If authentication is successful, the server sends the query details to the sentiment recognition engine to analyze the user's emotions.

[0952] Step 5:

[0953] The emotion engine recognizes the user's emotions and sends the emotion data back to the server. For example, from the phrase "I am in a lot of trouble," the emotion engine recognizes the urgency and dissatisfaction and sends that information to the server.

[0954] Step 6:

[0955] The server adds emotional data to the analysis results and sends them to the generative AI. The server adds the received emotional data to the analysis results and sends a request to the generative AI's API endpoint.

[0956] Step 7:

[0957] The generative AI generates a response. Based on the analysis results and sentiment data, the generative AI generates a response saying, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately," and sends it back to the server.

[0958] Step 8:

[0959] The server receives the generated response. The server receives the response from the generative AI, converts it to the appropriate format, and prepares to send it to the user's terminal.

[0960] Step 9:

[0961] The server sends a response to the terminal. The server sends the generated response to the user's terminal using the HTTPS protocol.

[0962] Step 10:

[0963] The device receives the response and displays it on the screen. The user's device displays the response received from the server, which may say something like, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately." This allows the user to receive quick and appropriate information.

[0964] (Example 2)

[0965] 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."

[0966] Existing inquiry response systems fail to adequately consider user emotions and urgency, making it difficult to provide prompt and accurate responses. Furthermore, delays can occur during the process of properly formatting and resubmitting user inquiries, leading to decreased user satisfaction.

[0967] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for recognizing the emotion of the user's inquiry, response adjustment means for adjusting the response content based on the results of the emotion recognition means, and AI generation means for causing a generative AI to generate a response. This enables a quick and accurate response that takes into account the user's emotions and urgency.

[0968] "Input means" refers to devices or interfaces used by users to input inquiries.

[0969] A "server system" is a computer system that has the function of receiving and analyzing inquiries from users.

[0970] The "AI generation means" is a function that automatically generates an appropriate response using a generative AI based on the results analyzed by the server means.

[0971] "Output means" refers to a device or interface for reformatting the generated response and displaying it to the user.

[0972] "Emotion recognition means" refers to software or a device that has the function of analyzing emotions from a user's inquiry and recognizing those emotions.

[0973] "Response adjustment means" refers to software or a device that has the function of adjusting the generated response content based on the results of emotion recognition means.

[0974] "Authentication means" refers to software or a device that has the function of verifying a user's authentication information and confirming their identity.

[0975] "Transmission means" refers to a device or interface for formatting the generated response and sending it to the user's terminal.

[0976] The present invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to a user's inquiry. The system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[0977] composition

[0978] 1. User's terminal

[0979] Users enter their inquiries using their own computers, smartphones, or other devices. The device provides an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS. Specifically, JavaScript is used to validate the input, and the inquiry content is sent to the server using the HTTPS protocol.

[0980] 2. Server

[0981] The server handles multiple functions, including receiving queries and verifying user authentication information. It also analyzes the received query content and passes it on to a generative AI for processing. Furthermore, it receives responses from the generative AI, converts them to the appropriate format, and sends them to the user's terminal. User authentication is performed using methods such as OAuth 2.0 or JWT (JSON Web Token). A natural language processing engine (e.g., spaCy) is used for text analysis.

[0982] 3. Generative AI

[0983] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is sent back to the server. The generative AI can use OpenAI's GPT-3.

[0984] 4. Emotional Engine

[0985] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results. Python libraries such as TextBlob are used for emotion recognition.

[0986] 5. Response adjustment

[0987] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[0988] 6. Response Display

[0989] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to smoothly obtain clues to solve the problem. JavaScript or a front-end framework (e.g., React, Vue.js) is used for display.

[0990] Specific example

[0991] Let's say a user types and submits an inquiry asking, "Please tell me how to do cross-connect." This inquiry is converted to JSON format by the device and sent to the server. The server receives the inquiry, verifies the authentication information, and then passes the inquiry content to a natural language processing engine for analysis. The emotion engine recognizes the emotion from the text and sends a prompt to the generative AI based on the user's emotional state.

[0992] Specific examples of prompt statements are as follows:

[0993] "User Inquiry: Please explain the procedure for cross-connecting."

[0994] "Emotional Engine Result: No particular emotional expression."

[0995] "Prompt to the generative AI: The user wants to know the procedure for cross-connecting. Please explain the procedure in detail."

[0996] The generative AI generates a response based on this prompt, providing a response such as, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it." The server reformats this response and sends it to the user's terminal. Finally, the terminal receives the response and displays it to the user. This allows the user to quickly learn the necessary procedures.

[0997] This system allows users to receive prompt and accurate support, as well as comprehensive responses that address their emotional needs.

[0998] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0999] Step 1:

[1000] The user enters an inquiry.

[1001] The user opens the inquiry form on their device (computer or smartphone). The user enters an inquiry message such as, "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" and presses the "Send" button. The input data is converted to JSON format.

[1002] Input: User's inquiry (Example: "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!")

[1003] Output: Query data in JSON format (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345"})

[1004] Step 2:

[1005] The terminal sends a query to the server.

[1006] The terminal sends the user-entered query data in JSON format and authentication information to the server using the HTTPS protocol. The authentication information includes the user ID and token.

[1007] Input: JSON format query data, authentication information (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345", "token": "abcdef"})

[1008] Output: HTTPS request

[1009] Step 3:

[1010] The server receives and analyzes the query.

[1011] The server receives the query and verifies the user's authentication information. Once authentication is complete, the query content is passed to a natural language processing (NLP) engine. Here, spaCy is used as an example NLP engine.

[1012] Input: HTTPS request data (inquiry data in JSON format, authentication information)

[1013] Data processing / calculations: Authentication process, NLP analysis (e.g., text analysis of the "message" field)

[1014] Output: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[1015] Step 4:

[1016] The emotion engine recognizes emotions

[1017] The server invokes an emotion engine (e.g., TextBlob) to recognize emotions from the text. The emotion engine extracts urgency and frustration from "I'm in a lot of trouble."

[1018] Input: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[1019] Data processing / calculation: Sentiment analysis

[1020] Output: Emotion recognition data (Example: {"emotion": "urgent_and_dissatisfied"})

[1021] Step 5:

[1022] Generative AI generates responses.

[1023] The server sends emotion recognition data and a prompt message to a generative AI (e.g., GPT-3) to generate a response. The prompt message would be: "The user is experiencing connection problems and wants to resolve them as quickly as possible. Please generate a response that shows empathy and prompt assistance."

[1024] Input: emotion recognition data, prompt text

[1025] Data processing / calculation: Response generation by generative AI

[1026] Output: Generated response (Example: "We are very sorry. Please try the following steps to resolve the issue. If the problem persists, please contact our support team immediately.")

[1027] Step 6:

[1028] The server receives the generated response and sends it to the terminal.

[1029] The server receives the response from the generative AI and converts it into a format suitable for the user's device (e.g., HTML or text). A template engine (e.g., Jinja2) can be used for this conversion process. After conversion, the server sends the response back to the device using HTTPS.

[1030] Input: Generated response

[1031] Data processing / calculations: Format conversion (e.g., JSON to HTML)

[1032] Output: HTTPS response (Example: " We sincerely apologize. First, please try to resolve the issue by following the steps below. If the problem persists, please contact our support team immediately. ")

[1033] Step 7:

[1034] The terminal receives and displays a response.

[1035] The terminal receives a response from the server and displays it to the user using JavaScript or a front-end framework (e.g., React, Vue.js). This allows the user to smoothly obtain clues to solve the problem on the screen.

[1036] Input: HTTPS response (formatted response)

[1037] Output: Screen display (e.g., the response is displayed on a web page)

[1038] (Application Example 2)

[1039] 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."

[1040] Conventional inquiry systems generate uniform responses that do not take into account the user's emotions, which is problematic because they cannot adequately address user dissatisfaction or urgency. The present invention aims to improve user satisfaction by recognizing the user's emotions and generating appropriate responses based on those emotions.

[1041] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for the user to input an inquiry, an emotion recognition means for receiving the inquiry and recognizing the emotion, an AI generation means for causing a generative AI to generate a response based on the result of the emotion recognition means, and an output means for receiving the generated response and displaying it to the user. This enables flexible and appropriate responses that are attuned to the user's emotions.

[1042] An "input method" refers to a device or interface used by a user to input inquiries or information.

[1043] An "emotion recognition system" is a mechanism for analyzing and recognizing emotions from text and information entered by the user.

[1044] "AI generation means" refers to the function of artificial intelligence that generates appropriate responses based on the results of emotion recognition means.

[1045] "Output means" refers to a device or interface for displaying the generated response to the user.

[1046] An "authentication method" is a system used to verify a user's authentication information and confirm whether that user has legitimate access rights.

[1047] A "response adjustment mechanism" is a system that adjusts the generated response based on the user's emotions to make it more appropriate and emotionally resonant.

[1048] In order to implement this invention, it is necessary to construct a system that includes the following means: an input means for a user to input an inquiry; an emotion recognition means for receiving the inquiry and recognizing the emotion; an AI generation means for generating a response based on the results of the emotion recognition means; and an output means for displaying the generated response to the user.

[1049] Hardware and software configuration

[1050] Hardware configuration

[1051] 1. User terminal: A device used by a user to enter inquiries, such as a smartphone or computer.

[1052] 2. Server: A computer system that performs multiple functions (receiving queries, parsing, sentiment recognition, and response generation).

[1053] Software Configuration

[1054] 1. Input Interface: A web form or chat box for users to enter inquiries.

[1055] 2. Server program: Uses a framework such as FastAPI to receive and properly parse queries.

[1056] 3. Emotion Recognition Engine: Software used for emotion analysis, such as "EmotionEngine".

[1057] 4. Generative AI Models: Artificial intelligence models such as "AIModel" that generate appropriate responses while taking user emotions into consideration.

[1058] 5. Response Adjustment Program: A program to adjust responses from generative AI based on emotions.

[1059] 6. Output Interface: A screen display interface for showing the generated response to the user.

[1060] Specific usage examples

[1061] How to use the system

[1062] 1. Inquiry Input: Users enter questions or problems through a smartphone app. Alternatively, they may use a web form or chat box. Example: "My home alarm seems to be malfunctioning. What should I do?"

[1063] 2. Sending the inquiry: The entered inquiry is securely sent to the server using HTTPS.

[1064] 3. Emotion Recognition: The server analyzes the received inquiry using emotion recognition tools to recognize the user's emotions (anxiety, impatience, etc.).

[1065] 4. Response Generation: Based on the emotion recognition results, a generative AI model generates the optimal response. For example, "We are very sorry. Please try resetting the alarm first. If that does not resolve the issue, please contact our support team immediately."

[1066] 5. Response adjustment: Ensure that generated responses are appropriately adjusted based on emotions and are user-friendly.

[1067] 6. Display of response: Finally, the adjusted response sent from the server is displayed on the user's terminal.

[1068] This allows users to receive appropriate responses based on their emotions, leading to quicker and smoother problem resolution.

[1069] Example prompt statements

[1070] "It seems my home alarm is malfunctioning. What should I do?"

[1071] "We are in a very difficult situation. Please resolve the connection problem as soon as possible!"

[1072] Regardless of the type of inquiry a user makes, this system aims to consider the user's feelings and provide a prompt, appropriate, and empathetic response.

[1073] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1074] Step 1:

[1075] The user enters their inquiry. The user uses a smartphone app, web form, or chat box to enter their inquiry. For example, they might enter, "My home alarm seems to be malfunctioning. What should I do?" This input is recorded as text data on the device.

[1076] Step 2:

[1077] The terminal sends the query to the server. The user's input query is converted to JSON format and securely sent to the server. The HTTPS protocol is used to ensure data security. The input is a text-based query, and the output is a secure JSON-formatted request.

[1078] Step 3:

[1079] The server receives the query and performs emotion recognition. The server parses the received JSON data and extracts the text data. Then, it uses an emotion recognition engine (EmotionEngine) to analyze the text data and recognize the user's emotions (anxiety, impatience, anger, etc.). The input is the text data of the query, and the output is the emotion analysis result.

[1080] Step 4:

[1081] The server generates responses using a generative AI model (AIModel). The server creates a response generation prompt based on the results of the emotion recognition engine and passes it to the generative AI. For example, if the prompt "It seems my home alarm is malfunctioning. What should I do?" and the recognized emotion are input, the server will generate the response "We are very sorry. First, please try resetting the alarm. If that does not resolve the issue, please contact our support team immediately." The input is the prompt text and the emotion analysis result, and the output is the generated response.

[1082] Step 5:

[1083] The server adjusts the generated response. The response from the generative AI is appropriately adjusted based on the analysis results of the emotion recognition engine. For example, if the user is particularly anxious, it will include more empathetic and reassuring words. This adjustment is performed, and the optimized response is output. The input is the generated response, and the output is the adjusted response.

[1084] Step 6:

[1085] The server sends a refined response to the user's terminal. The optimized response is converted back into JSON format and sent to the user's terminal. The input is the refined response text data, and the output is the response data in secure JSON format.

[1086] Step 7:

[1087] The terminal receives and displays the response. The user's terminal receives the response data sent from the server and displays it on the screen. This allows the user to receive a quick and appropriate response. The input is the response data from the server, and the output is the text displayed on the user's screen.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] [Fourth Embodiment]

[1092] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1093] 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.

[1094] 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).

[1095] 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.

[1096] 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.

[1097] 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).

[1098] 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.

[1099] 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.

[1100] 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.

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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".

[1105] This invention relates to a system that allows users to make inquiries smoothly and obtain quick and accurate responses. To implement this system, the system includes a terminal for the user to input inquiries, a server that receives and processes inquiries, a generative AI that generates appropriate responses, and a terminal that displays the responses to the user.

[1106] composition

[1107] 1. User's terminal

[1108] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[1109] 2. Server

[1110] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[1111] 3. Generative AI

[1112] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[1113] 4. Response Display

[1114] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[1115] Program processing flow

[1116] The user enters an inquiry.

[1117] The user opens the inquiry form on their device, types "Please tell me how to deal with connection problems," and presses the submit button.

[1118] The terminal sends a query to the server.

[1119] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[1120] The server receives and analyzes the query.

[1121] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[1122] Generative AI generates responses.

[1123] Based on the analysis results received from the server, the generative AI generates a response that says, "If you experience connection problems, please try restarting your equipment first. If the problem persists, please contact professional support."

[1124] The server receives the generated response and sends it to the terminal.

[1125] The server receives the response from the generative AI, formats it, and sends it to the user's terminal.

[1126] The device displays a response.

[1127] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[1128] As a concrete example, the following inquiries are possible:

[1129] "Please explain the procedure for cross-connecting."

[1130] "What should I do if a connection problem occurs?"

[1131] "How do I use the remote hand service?"

[1132] By having a generative AI generate individual responses to these inquiries and provide them to the user, the system can quickly resolve the user's problems. This system is highly effective as a means of providing consistent support to the user, even when multiple related departments or personnel are involved.

[1133] The following describes the processing flow.

[1134] Step 1:

[1135] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "Please tell me about the Cross Connect procedure" in the inquiry form, and clicks the submit button.

[1136] Step 2:

[1137] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal then sends this data to the server using the HTTPS protocol.

[1138] Step 3:

[1139] The server receives the query. The server parses the received query content in JSON format and authentication information, and compares it against the database to verify if the user is authenticated.

[1140] Step 4:

[1141] The server analyzes the query. If authentication is successful, the server passes the query to a natural language processing engine for intent analysis.

[1142] Step 5:

[1143] The server sends the analysis results to the generative AI. The server converts the analysis results into a format that the AI ​​engine can easily understand and makes a request to the generative AI's API endpoint.

[1144] Step 6:

[1145] The generative AI generates a response. Based on the received analysis results, the generative AI generates a response stating, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it," and sends it back to the server.

[1146] Step 7:

[1147] The server receives the generated response. The server converts the received response into the appropriate format and prepares to send it to the user's terminal.

[1148] Step 8:

[1149] The server sends a response to the terminal. The server converts the generated response into an appropriate format, such as JSON, and sends it to the user's terminal using the HTTPS protocol.

[1150] Step 9:

[1151] The terminal receives and displays the response. The user's terminal receives the response from the server and displays it on the screen. The user will see a message that reads, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it."

[1152] (Example 1)

[1153] 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".

[1154] Traditional inquiry systems have the drawback of long response times, making rapid problem resolution difficult. Furthermore, the quality of responses to inquiries is inconsistent, and there is little guarantee that users will receive satisfactory answers. Additionally, the increasing complexity of systems, including user authentication and data format conversion, presents challenges in terms of security and processing efficiency.

[1155] 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.

[1156] In this invention, the server includes input means for the user to input a query, server means for receiving and analyzing the query, generation means for causing a generative AI to generate a response based on the analysis results, output means for receiving the generated response and displaying it to the user, and formatting means for converting the response into an appropriate format. This enables the user to obtain a quick and accurate response. Furthermore, it improves the overall security and efficiency of the system and increases user satisfaction.

[1157] "Input method" refers to a device or software that provides an interface (such as a web form or chat box) for users to input inquiries.

[1158] "Server means" refers to devices or software that analyze the content of inquiries received from users and perform the necessary processing.

[1159] "Generation means" refers to a generative AI that generates an appropriate response based on the analysis results received from the server.

[1160] "Output means" refers to devices or software that receive the generated response and display it to the user.

[1161] "Formatting means" refers to the processing or device used to convert the generated response into an appropriate format and transmit it to the user.

[1162] "Authentication means" refers to a function that verifies a user's authentication information and confirms whether they are a legitimate user.

[1163] "Conversion means" refers to the processing or device used to format the generated response and send it to the user's terminal.

[1164] The system of this invention enables users to make inquiries smoothly and obtain quick and accurate responses. Specific components of the system include a user terminal, a server, a generative AI, and a terminal for displaying responses.

[1165] User's terminal

[1166] Users enter their inquiries using their own computers, smartphones, or other devices. Web forms and chat boxes are provided as input interfaces, allowing users to submit inquiries intuitively and easily. The device converts the user's input into JSON format and securely sends it to the server using HTTPS.

[1167] server

[1168] The server handles multiple functions. After receiving a query, it first verifies the user's authentication information. If authentication is successful, it passes the query content to a natural language processing engine for analysis. This analysis process uses libraries such as Python's "spaCy" or "NLTK". Based on the analysis results, it sends an API request to a generative AI to generate a response.

[1169] Generative AI

[1170] Generative AI receives analysis results from a server and generates an appropriate response. For example, if a user asks, "What should I do if I experience connection problems?", the generative AI will generate a specific response such as, "If you experience connection problems, first try restarting your equipment. If that doesn't solve the problem, please contact our dedicated support." Models such as "GPT-3" are often used for generative AI.

[1171] Response display

[1172] The server converts the response received from the generative AI into an appropriate format and sends it to the user's terminal. Formats such as HTML and JSON are used for this conversion. Finally, the terminal displays the received response to the user. This allows the user to obtain information quickly and accurately.

[1173] Specific example

[1174] The following examples will make it easier to understand how the system works.

[1175] Example 1: For a user who wants to know the procedure for cross-connecting.

[1176] The user types "Please tell me how to do CrossConnect" and sends it. The terminal converts it to JSON format and sends it to the server via HTTPS. The server receives it, analyzes it with the NLU module, and sends the result to the generative AI. The generative AI generates a response saying, "To do CrossConnect, first access the dedicated page, fill in the designated form, and submit it." The server formats the response and sends it to the terminal. The terminal receives the response and displays it on the browser screen.

[1177] Example 2: For a user who wants to know how to troubleshoot connection problems.

[1178] The user types and sends the question, "What should I do if I experience connection problems?" The server receives the message and sends it to the AI. The AI ​​generates a response: "If you experience connection problems, please try restarting your device first. If the problem persists, please contact our dedicated support." The terminal receives and displays the response.

[1179] Example of a prompt

[1180] The following are examples of prompt statements:

[1181] "Please explain the procedure for cross-connecting."

[1182] "What should I do if I encounter connection problems?"

[1183] "How do I use the remote hand service?"

[1184] This system allows users to receive quick and accurate responses to their inquiries, enabling smooth problem resolution.

[1185] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1186] Step 1:

[1187] The user enters an inquiry.

[1188] Users enter their inquiries into web forms or chat boxes on their devices. Through this input interface, users describe specific questions or problems. For example, a user might enter, "Please tell me how to deal with connection problems." This input data is then used directly in the next process.

[1189] Step 2:

[1190] The device sends the query to the server.

[1191] When the user presses the submit button, the device converts the inquiry content into JSON format and sends it to the server using the HTTPS protocol. The input data (user inquiry content) is sent as converted JSON data. Specific examples of libraries used include Python's "requests" library and JavaScript's "axios". At this time, the device also sends authentication information.

[1192] Step 3:

[1193] The server receives and analyzes the query.

[1194] The server receives JSON data sent from the terminal. First, it checks the authentication information to confirm that the query is from a legitimate user. After this, the server passes the query content to an NLU (Natural Language Understanding) module for analysis. Here, libraries such as Python's "spaCy" or "NLTK" are used for the analysis. As a result of the analysis, the intent of the query and important keywords are extracted.

[1195] Step 4:

[1196] The server sends a request to the generative AI.

[1197] The server sends a request to the generative AI based on the analysis results. This request includes the analyzed query content, and the generative AI makes an API call. Specifically, the analysis results are sent via the API request, and an appropriate answer is obtained as response data.

[1198] Step 5:

[1199] Generative AI generates responses.

[1200] The generative AI generates an appropriate response based on the received analysis results. For example, if the inquiry is "Please tell me how to deal with connection problems," it will generate a response such as "First, please try restarting your equipment. If that does not resolve the issue, please contact our specialist support." The generated response is then sent back to the server as an API response.

[1201] Step 6:

[1202] The server receives the generated response and formats it.

[1203] The server receives the response from the generative AI and converts it into an appropriate format for display to the user. For example, it performs conversion to formats such as HTML or JSON. The formatted data is then generated.

[1204] Step 7:

[1205] The server sends a response to the terminal.

[1206] The server sends formatted response data to the terminal. The data is then securely transmitted again using the HTTPS protocol. This data is in JSON or HTML format.

[1207] Step 8:

[1208] The device displays a response.

[1209] Ultimately, the device displays the received response to the user. The browser might display a message such as, "If you experience connection problems, please try restarting your device first. If the problem persists, please contact professional support." The user can then see this message and take appropriate action.

[1210] (Application Example 1)

[1211] 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".

[1212] In traditional security services, it is difficult for users to obtain the appropriate information necessary to quickly resolve security-related problems. Furthermore, the inability to provide appropriate and expert responses to inquiries often leads to delays in problem resolution. Therefore, a system is needed that provides quick and accurate solutions when users report security problems.

[1213] 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.

[1214] In this invention, the server includes input means for a user to input an inquiry, server means for receiving and analyzing the inquiry, AI generation means for causing a generative AI to generate a response based on the analysis results, response generation means for providing a method for resolving security-related problems, and output means for receiving the generated response and displaying it to the user. This makes it possible to respond quickly and accurately to security problems and promptly resolve user anxieties and problems.

[1215] An "input method" is an interface for users to enter their inquiries.

[1216] A "server system" refers to a server that receives and analyzes queries.

[1217] An "AI generation method" is a means of causing a generative AI to generate a response based on the analysis results.

[1218] A "response generation means" is a means for generating a response to provide a solution for security-related problems.

[1219] "Output means" refers to means for receiving the generated response and displaying it to the user.

[1220] "Authentication means" refers to a method for verifying a user's authentication information.

[1221] "Transmission means" refers to the means for formatting the generated response and sending it to the user's terminal.

[1222] "System" refers to the entire configuration that includes these means.

[1223] The embodiments for carrying out this invention will be described in detail below.

[1224] System Program Overview

[1225] The system of this invention consists of multiple components, which work together to provide a fast and accurate response to user inquiries. The main components of the system include input means, server means, AI generation means, response generation means, output means, authentication means, and transmission means.

[1226] Hardware and software usage

[1227] The system is implemented using the following hardware and software:

[1228] User terminal: The interface where the user enters their inquiry. This can be a smartphone (iOS or Android) or a computer.

[1229] Server: A cloud server that receives and analyzes queries. AWS EC2 can be used as a specific example.

[1230] Generative AI: AI that generates responses based on analysis results. A concrete example is the OpenAI GPT-3 API.

[1231] Natural language processing engine: An engine used to analyze query content. Examples include NLTK and SpaCy.

[1232] Program processing

[1233] When a user enters an inquiry from a device such as a smartphone or computer, the inquiry is converted into JSON format and sent to the server. The server analyzes the received inquiry and verifies the user's authentication information using an authentication method. If authentication is successful, the inquiry is analyzed by a natural language processing engine, and the analysis results are passed to an AI generation method, which generates an appropriate response. This response is reformatted and sent to the user's terminal, and finally displayed to the user by an output method.

[1234] Specific example

[1235] A user makes the following inquiry using their smartphone:

[1236] "I can no longer connect to the network."

[1237] This query is parsed by the server, and the following prompt is sent to the generative AI:

[1238] "A user reported being unable to connect to the network. Please provide possible causes and solutions."

[1239] The generative AI receives this prompt and generates the following response:

[1240] "If you can't connect to the network, first try restarting your router or modem. If that doesn't work, check that your device is connected to the correct network and try temporarily disabling your security software."

[1241] This response is reformatted, sent to the user's terminal via the transmission means, and finally displayed to the user by the output means.

[1242] In this way, the system of the present invention encompasses a series of processes from the input of an inquiry to the display of a response, enabling a rapid and accurate response to security problems.

[1243] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1244] Step 1:

[1245] The user enters their inquiry on their device.

[1246] The user enters the message "I can no longer connect to the network" into an input form displayed on their smartphone or computer screen and presses the submit button. This input is then converted into JSON format.

[1247] Step 2:

[1248] The terminal sends a query to the server.

[1249] The terminal converts the user's input into JSON format and then sends it to the server via HTTPS along with authentication information. During this process, the input data is encrypted before transmission.

[1250] Step 3:

[1251] The server receives the query and analyzes it.

[1252] The server stores the received query in a database and verifies the user's authentication information using an authentication method. If authentication is successful, the query content is passed to a natural language processing engine (e.g., NLTK or SpaCy) for text analysis. The analysis results include the intent of the query and important keywords.

[1253] Step 4:

[1254] The generative AI generates the response.

[1255] The server passes the analysis results to the AI ​​generation system, which then sends a prompt message to the generative AI (for example, OpenAI's GPT-3 API). An example of a prompt message is: "The user has reported being unable to connect to the network. Please indicate possible causes and solutions." The generative AI analyzes the prompt message and generates an appropriate response: "If you are unable to connect to the network, first try restarting your router or modem. If that doesn't solve the problem, check that your device is connected to the correct network and try temporarily disabling your security software."

[1256] Step 5:

[1257] The server receives the generated response and formats it.

[1258] The server receives the response from the generative AI and formats it as needed. This formatting includes converting the response into a simple and easy-to-read format. For example, it may add specific tags or styles.

[1259] Step 6:

[1260] The server sends a response to the terminal.

[1261] The formatted response is converted to JSON format and sent to the user's terminal via HTTPS. This transmitted data is also encrypted.

[1262] Step 7:

[1263] The terminal receives and displays the response.

[1264] The user's device analyzes the response received from the server and displays it on the screen. The user can see the response containing the appropriate solution on the device's screen. This allows the user to quickly obtain a means to resolve the problem.

[1265] 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.

[1266] This invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to user inquiries. To implement this system, the system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[1267] composition

[1268] 1. User's terminal

[1269] Users enter their inquiries using their own computers, smartphones, or other devices. These devices are provided with an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS.

[1270] 2. Server

[1271] The server handles multiple functions. After receiving a query, it verifies the user's authentication information. It also analyzes the received query content and passes it on to the generative AI for processing. Furthermore, it receives the response from the generative AI, converts it to the appropriate format, and sends it to the user's terminal.

[1272] 3. Generative AI

[1273] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is then sent back to the server.

[1274] 4. Emotional Engine

[1275] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results.

[1276] 5. Response adjustment

[1277] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[1278] 6. Response Display

[1279] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to quickly obtain clues to resolve the problem.

[1280] Program processing flow

[1281] The user enters an inquiry.

[1282] The user opens the inquiry form on their device, types "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", and presses the submit button.

[1283] The terminal sends a query to the server.

[1284] The terminal converts the user's input into JSON format and sends it to the server along with authentication information.

[1285] The server receives and analyzes the query.

[1286] The server receives the query, verifies the authentication information, and then passes the query content to the natural language processing engine.

[1287] The emotion engine recognizes emotions

[1288] The emotion engine analyzes the text of incoming inquiries to recognize the user's emotions. For example, if a user says something like "I'm in a lot of trouble," it determines that the user is expressing urgency and dissatisfaction.

[1289] Generative AI generates responses.

[1290] The generative AI takes into account the recognition results of the emotion engine to generate empathetic and prompt responses. For example, it might generate a response like, "We are very sorry. Could you please try the following steps to resolve the issue? If it still doesn't work, please contact our support team immediately."

[1291] The server receives the generated response and sends it to the terminal.

[1292] The server receives the response from the generative AI, formats it, and prepares it to send to the user's terminal.

[1293] The terminal receives and displays a response.

[1294] Ultimately, the device displays the received response to the user, allowing the user to obtain quick and relevant information.

[1295] As a concrete example, the following inquiries are possible:

[1296] "Please explain the procedure for cross-connecting."

[1297] "What should I do if a connection problem occurs?"

[1298] "How do I use the remote hand service?"

[1299] By combining generative AI and an emotion engine, this system can provide more accurate and emotionally resonant responses to these inquiries. This system is highly effective in providing consistent support to users, even when multiple departments or individuals are involved.

[1300] The following describes the processing flow.

[1301] Step 1:

[1302] The user enters their inquiry on their device. The user accesses the Maruyama Customer Portal, enters "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" into the inquiry form, and clicks the submit button.

[1303] Step 2:

[1304] The terminal converts the query into JSON format, adds the user's authentication information, and sends it. The terminal securely sends this data to the server using the HTTPS protocol.

[1305] Step 3:

[1306] The server receives the query. The server analyzes the received query content in JSON format and authentication information, and checks against the database to confirm whether the user is authenticated.

[1307] Step 4:

[1308] The server passes the query details to the sentiment engine. If authentication is successful, the server sends the query details to the sentiment recognition engine to analyze the user's emotions.

[1309] Step 5:

[1310] The emotion engine recognizes the user's emotions and sends the emotion data back to the server. For example, from the phrase "I am in a lot of trouble," the emotion engine recognizes the urgency and dissatisfaction and sends that information to the server.

[1311] Step 6:

[1312] The server adds emotional data to the analysis results and sends them to the generative AI. The server adds the received emotional data to the analysis results and sends a request to the generative AI's API endpoint.

[1313] Step 7:

[1314] The generative AI generates a response. Based on the analysis results and sentiment data, the generative AI generates a response saying, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately," and sends it back to the server.

[1315] Step 8:

[1316] The server receives the generated response. The server receives the response from the generative AI, converts it to the appropriate format, and prepares to send it to the user's terminal.

[1317] Step 9:

[1318] The server sends a response to the terminal. The server sends the generated response to the user's terminal using the HTTPS protocol.

[1319] Step 10:

[1320] The device receives the response and displays it on the screen. The user's device displays the response received from the server, which may say something like, "We are very sorry. Could you please try the following steps to resolve the issue? If the problem persists, please contact our support team immediately." This allows the user to receive quick and appropriate information.

[1321] (Example 2)

[1322] 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".

[1323] Existing inquiry response systems fail to adequately consider user emotions and urgency, making it difficult to provide prompt and accurate responses. Furthermore, delays can occur during the process of properly formatting and resubmitting user inquiries, leading to decreased user satisfaction.

[1324] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for recognizing the emotion of the user's inquiry, response adjustment means for adjusting the response content based on the results of the emotion recognition means, and AI generation means for causing a generative AI to generate a response. This enables a quick and accurate response that takes into account the user's emotions and urgency.

[1325] "Input means" refers to devices or interfaces used by users to input inquiries.

[1326] A "server system" is a computer system that has the function of receiving and analyzing inquiries from users.

[1327] The "AI generation means" is a function that automatically generates an appropriate response using a generative AI based on the results analyzed by the server means.

[1328] "Output means" refers to a device or interface for reformatting the generated response and displaying it to the user.

[1329] "Emotion recognition means" refers to software or a device that has the function of analyzing emotions from a user's inquiry and recognizing those emotions.

[1330] "Response adjustment means" refers to software or a device that has the function of adjusting the generated response content based on the results of emotion recognition means.

[1331] "Authentication means" refers to software or a device that has the function of verifying a user's authentication information and confirming their identity.

[1332] "Transmission means" refers to a device or interface for formatting the generated response and sending it to the user's terminal.

[1333] The present invention relates to a system that combines a generative AI and an emotion engine to provide a rapid and accurate response to a user's inquiry. The system includes a terminal in which the user inputs an inquiry, a server that receives and processes the inquiry, a generative AI that generates an appropriate response, a terminal that displays the response to the user, and an emotion engine.

[1334] composition

[1335] 1. User's terminal

[1336] Users enter their inquiries using their own computers, smartphones, or other devices. The device provides an input interface (e.g., a web form or chat box). This input is securely transmitted to the server using HTTPS. Specifically, JavaScript is used to validate the input, and the inquiry content is sent to the server using the HTTPS protocol.

[1337] 2. Server

[1338] The server handles multiple functions, including receiving queries and verifying user authentication information. It also analyzes the received query content and passes it on to a generative AI for processing. Furthermore, it receives responses from the generative AI, converts them to the appropriate format, and sends them to the user's terminal. User authentication is performed using methods such as OAuth 2.0 or JWT (JSON Web Token). A natural language processing engine (e.g., spaCy) is used for text analysis.

[1339] 3. Generative AI

[1340] The generative AI generates an appropriate response based on the analysis results received from the server. For example, in response to the inquiry, "Please tell me how to perform a cross-connect," it generates a specific example such as, "To perform a cross-connect, first access the dedicated page, fill in the designated form, and submit it." This response is sent back to the server. The generative AI can use OpenAI's GPT-3.

[1341] 4. Emotional Engine

[1342] The emotion engine recognizes emotions from user input. For example, if a user inputs "I'm in a lot of trouble. Please resolve the connection problem immediately!", the emotion engine recognizes the complaint and urgency. This recognition result is reflected in the analysis results. Python libraries such as TextBlob are used for emotion recognition.

[1343] 5. Response adjustment

[1344] The emotion engine recognizes emotions, and the generative AI adjusts the content of the response it generates based on those emotions. For example, if the user is in trouble, it will generate a more empathetic and prompt response. It might generate a response like, "We are very sorry. First, could you please try the following steps to resolve the issue? If that doesn't work, please contact our support team immediately."

[1345] 6. Response Display

[1346] Once the server sends a reformatted response, the user's terminal receives it and displays it on the screen. This allows the user to smoothly obtain clues to solve the problem. JavaScript or a front-end framework (e.g., React, Vue.js) is used for display.

[1347] Specific example

[1348] Let's say a user types and submits an inquiry asking, "Please tell me how to do cross-connect." This inquiry is converted to JSON format by the device and sent to the server. The server receives the inquiry, verifies the authentication information, and then passes the inquiry content to a natural language processing engine for analysis. The emotion engine recognizes the emotion from the text and sends a prompt to the generative AI based on the user's emotional state.

[1349] Specific examples of prompt statements are as follows:

[1350] "User Inquiry: Please explain the procedure for cross-connecting."

[1351] "Emotional Engine Result: No particular emotional expression."

[1352] "Prompt to the generative AI: The user wants to know the procedure for cross-connecting. Please explain the procedure in detail."

[1353] The generative AI generates a response based on this prompt, providing a response such as, "To proceed with the cross-connect procedure, first access the dedicated page, fill in the designated form, and submit it." The server reformats this response and sends it to the user's terminal. Finally, the terminal receives the response and displays it to the user. This allows the user to quickly learn the necessary procedures.

[1354] This system allows users to receive prompt and accurate support, as well as comprehensive responses that address their emotional needs.

[1355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1356] Step 1:

[1357] The user enters an inquiry.

[1358] The user opens the inquiry form on their device (computer or smartphone). The user enters an inquiry message such as, "I'm in a lot of trouble. Please resolve this connection problem as soon as possible!" and presses the "Send" button. The input data is converted to JSON format.

[1359] Input: User's inquiry (Example: "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!")

[1360] Output: Query data in JSON format (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345"})

[1361] Step 2:

[1362] The terminal sends a query to the server.

[1363] The terminal sends the user-entered query data in JSON format and authentication information to the server using the HTTPS protocol. The authentication information includes the user ID and token.

[1364] Input: JSON format query data, authentication information (Example: {"message": "I'm in a lot of trouble. Please resolve the connection problem as soon as possible!", "user_id": "12345", "token": "abcdef"})

[1365] Output: HTTPS request

[1366] Step 3:

[1367] The server receives and analyzes the query.

[1368] The server receives the query and verifies the user's authentication information. Once authentication is complete, the query content is passed to a natural language processing (NLP) engine. Here, spaCy is used as an example NLP engine.

[1369] Input: HTTPS request data (inquiry data in JSON format, authentication information)

[1370] Data processing / calculations: Authentication process, NLP analysis (e.g., text analysis of the "message" field)

[1371] Output: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[1372] Step 4:

[1373] The emotion engine recognizes emotions

[1374] The server invokes an emotion engine (e.g., TextBlob) to recognize emotions from the text. The emotion engine extracts urgency and frustration from "I'm in a lot of trouble."

[1375] Input: Parsed text data (e.g., {"intent": "troubleshoot_connection", "sentiment": "negative"})

[1376] Data processing / calculation: Sentiment analysis

[1377] Output: Emotion recognition data (Example: {"emotion": "urgent_and_dissatisfied"})

[1378] Step 5:

[1379] Generative AI generates responses.

[1380] The server sends emotion recognition data and a prompt message to a generative AI (e.g., GPT-3) to generate a response. The prompt message would be: "The user is experiencing connection problems and wants to resolve them as quickly as possible. Please generate a response that shows empathy and prompt assistance."

[1381] Input: emotion recognition data, prompt text

[1382] Data processing / calculation: Response generation by generative AI

[1383] Output: Generated response (Example: "We are very sorry. Please try the following steps to resolve the issue. If the problem persists, please contact our support team immediately.")

[1384] Step 6:

[1385] The server receives the generated response and sends it to the terminal.

[1386] The server receives the response from the generative AI and converts it into a format suitable for the user's device (e.g., HTML or text). A template engine (e.g., Jinja2) can be used for this conversion process. After conversion, the server sends the response back to the device using HTTPS.

[1387] Input: Generated response

[1388] Data processing / calculations: Format conversion (e.g., JSON to HTML)

[1389] Output: HTTPS response (Example: " We sincerely apologize. First, please try to resolve the issue by following the steps below. If the problem persists, please contact our support team immediately. ")

[1390] Step 7:

[1391] The terminal receives and displays a response.

[1392] The terminal receives a response from the server and displays it to the user using JavaScript or a front-end framework (e.g., React, Vue.js). This allows the user to smoothly obtain clues to solve the problem on the screen.

[1393] Input: HTTPS response (formatted response)

[1394] Output: Screen display (e.g., the response is displayed on a web page)

[1395] (Application Example 2)

[1396] 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".

[1397] Conventional inquiry systems generate uniform responses that do not take into account the user's emotions, which is problematic because they cannot adequately address user dissatisfaction or urgency. The present invention aims to improve user satisfaction by recognizing the user's emotions and generating appropriate responses based on those emotions.

[1398] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for the user to input an inquiry, an emotion recognition means for receiving the inquiry and recognizing the emotion, an AI generation means for causing a generative AI to generate a response based on the result of the emotion recognition means, and an output means for receiving the generated response and displaying it to the user. This enables flexible and appropriate responses that are attuned to the user's emotions.

[1399] An "input method" refers to a device or interface used by a user to input inquiries or information.

[1400] An "emotion recognition system" is a mechanism for analyzing and recognizing emotions from text and information entered by the user.

[1401] "AI generation means" refers to the function of artificial intelligence that generates appropriate responses based on the results of emotion recognition means.

[1402] "Output means" refers to a device or interface for displaying the generated response to the user.

[1403] An "authentication method" is a system used to verify a user's authentication information and confirm whether that user has legitimate access rights.

[1404] A "response adjustment mechanism" is a system that adjusts the generated response based on the user's emotions to make it more appropriate and emotionally resonant.

[1405] In order to implement this invention, it is necessary to construct a system that includes the following means: an input means for a user to input an inquiry; an emotion recognition means for receiving the inquiry and recognizing the emotion; an AI generation means for generating a response based on the results of the emotion recognition means; and an output means for displaying the generated response to the user.

[1406] Hardware and software configuration

[1407] Hardware configuration

[1408] 1. User terminal: A device used by a user to enter inquiries, such as a smartphone or computer.

[1409] 2. Server: A computer system that performs multiple functions (receiving queries, parsing, sentiment recognition, and response generation).

[1410] Software Configuration

[1411] 1. Input Interface: A web form or chat box for users to enter inquiries.

[1412] 2. Server program: Uses a framework such as FastAPI to receive and properly parse queries.

[1413] 3. Emotion Recognition Engine: Software used for emotion analysis, such as "EmotionEngine".

[1414] 4. Generative AI Models: Artificial intelligence models such as "AIModel" that generate appropriate responses while taking user emotions into consideration.

[1415] 5. Response Adjustment Program: A program to adjust responses from generative AI based on emotions.

[1416] 6. Output Interface: A screen display interface for showing the generated response to the user.

[1417] Specific usage examples

[1418] How to use the system

[1419] 1. Inquiry Input: Users enter questions or problems through a smartphone app. Alternatively, they may use a web form or chat box. Example: "My home alarm seems to be malfunctioning. What should I do?"

[1420] 2. Sending the inquiry: The entered inquiry is securely sent to the server using HTTPS.

[1421] 3. Emotion Recognition: The server analyzes the received inquiry using emotion recognition tools to recognize the user's emotions (anxiety, impatience, etc.).

[1422] 4. Response Generation: Based on the emotion recognition results, a generative AI model generates the optimal response. For example, "We are very sorry. Please try resetting the alarm first. If that does not resolve the issue, please contact our support team immediately."

[1423] 5. Response adjustment: Ensure that generated responses are appropriately adjusted based on emotions and are user-friendly.

[1424] 6. Display of response: Finally, the adjusted response sent from the server is displayed on the user's terminal.

[1425] This allows users to receive appropriate responses based on their emotions, leading to quicker and smoother problem resolution.

[1426] Example prompt statements

[1427] "It seems my home alarm is malfunctioning. What should I do?"

[1428] "We are in a very difficult situation. Please resolve the connection problem as soon as possible!"

[1429] Regardless of the type of inquiry a user makes, this system aims to consider the user's feelings and provide a prompt, appropriate, and empathetic response.

[1430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1431] Step 1:

[1432] The user enters their inquiry. The user uses a smartphone app, web form, or chat box to enter their inquiry. For example, they might enter, "My home alarm seems to be malfunctioning. What should I do?" This input is recorded as text data on the device.

[1433] Step 2:

[1434] The terminal sends the query to the server. The user's input query is converted to JSON format and securely sent to the server. The HTTPS protocol is used to ensure data security. The input is a text-based query, and the output is a secure JSON-formatted request.

[1435] Step 3:

[1436] The server receives the query and performs emotion recognition. The server parses the received JSON data and extracts the text data. Then, it uses an emotion recognition engine (EmotionEngine) to analyze the text data and recognize the user's emotions (anxiety, impatience, anger, etc.). The input is the text data of the query, and the output is the emotion analysis result.

[1437] Step 4:

[1438] The server generates responses using a generative AI model (AIModel). The server creates a response generation prompt based on the results of the emotion recognition engine and passes it to the generative AI. For example, if the prompt "It seems my home alarm is malfunctioning. What should I do?" and the recognized emotion are input, the server will generate the response "We are very sorry. First, please try resetting the alarm. If that does not resolve the issue, please contact our support team immediately." The input is the prompt text and the emotion analysis result, and the output is the generated response.

[1439] Step 5:

[1440] The server adjusts the generated response. The response from the generative AI is appropriately adjusted based on the analysis results of the emotion recognition engine. For example, if the user is particularly anxious, it will include more empathetic and reassuring words. This adjustment is performed, and the optimized response is output. The input is the generated response, and the output is the adjusted response.

[1441] Step 6:

[1442] The server sends a refined response to the user's terminal. The optimized response is converted back into JSON format and sent to the user's terminal. The input is the refined response text data, and the output is the response data in secure JSON format.

[1443] Step 7:

[1444] The terminal receives and displays the response. The user's terminal receives the response data sent from the server and displays it on the screen. This allows the user to receive a quick and appropriate response. The input is the response data from the server, and the output is the text displayed on the user's screen.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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."

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1466] The following is further disclosed regarding the embodiments described above.

[1467] (Claim 1)

[1468] An input method for users to enter inquiries,

[1469] A server means for receiving and analyzing the query,

[1470] An AI generation means that causes a generative AI to generate a response based on the analysis results,

[1471] Output means for receiving the generated response and displaying it to the user,

[1472] A system that includes this.

[1473] (Claim 2)

[1474] The system according to claim 1, further comprising authentication means for verifying user authentication information.

[1475] (Claim 3)

[1476] The system according to claim 1, further comprising a transmission means for formatting the generated response and sending it to a user's terminal.

[1477] "Example 1"

[1478] (Claim 1)

[1479] An input method for users to enter inquiries,

[1480] A server means for receiving and analyzing the query,

[1481] A generation means that causes a generative AI to generate a response based on the analysis results,

[1482] Output means for receiving the generated response and displaying it to the user,

[1483] A formatting means for converting the response into an appropriate format,

[1484] A system that includes this.

[1485] (Claim 2)

[1486] The system according to claim 1, further comprising authentication means for verifying user authentication information.

[1487] (Claim 3)

[1488] The system according to claim 1, further comprising conversion means for formatting the generated response and sending it to the user's terminal.

[1489] "Application Example 1"

[1490] (Claim 1)

[1491] An input method for users to enter inquiries,

[1492] A server means for receiving and analyzing the query,

[1493] An AI generation means that causes a generative AI to generate a response based on the analysis results,

[1494] A means for generating responses to provide solutions for security-related problems,

[1495] Output means for receiving the generated response and displaying it to the user,

[1496] A system that includes this.

[1497] (Claim 2)

[1498] The system according to claim 1, further comprising authentication means for verifying user authentication information.

[1499] (Claim 3)

[1500] The system according to claim 1, further comprising a transmission means for formatting the generated response and sending it to a user's terminal.

[1501] "Example 2 of combining an emotion engine"

[1502] (Claim 1)

[1503] An input method for users to enter inquiries,

[1504] A server means for receiving and analyzing the query,

[1505] An AI generation means that causes a generative AI to generate a response based on the analysis results,

[1506] Output means for reformatting the generated response and displaying it to the user,

[1507] A sentiment recognition method for recognizing the sentiment of user inquiries,

[1508] A response adjustment means that adjusts the response content based on the results of the emotion recognition means,

[1509] A system that includes this.

[1510] (Claim 2)

[1511] The system according to claim 1, further comprising authentication means for verifying user authentication information.

[1512] (Claim 3)

[1513] The system according to claim 1, further comprising a transmission means for formatting the generated response and sending it to a user's terminal.

[1514] "Application example 2 when combining with an emotional engine"

[1515] (Claim 1)

[1516] An input method for users to enter inquiries,

[1517] An emotion recognition means for receiving the inquiry and recognizing the emotion,

[1518] An AI generation means that causes a generative AI to generate a response based on the results of the emotion recognition means,

[1519] Output means for receiving the generated response and displaying it to the user,

[1520] A system that includes this.

[1521] (Claim 2)

[1522] The system according to claim 1, further comprising authentication means for verifying user authentication information.

[1523] (Claim 3)

[1524] The system according to claim 1, further comprising response adjustment means for adjusting the generated response on an emotional basis. [Explanation of Symbols]

[1525] 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. An input method for users to enter inquiries, A server means for receiving and analyzing the query, An AI generation means that causes a generative AI to generate a response based on the analysis results, Output means for receiving the generated response and displaying it to the user, A system that includes this.

2. The system according to claim 1, further comprising authentication means for verifying user authentication information.

3. The system according to claim 1, further comprising transmission means for formatting the generated response and sending it to the user's terminal.

Images