system

Abstract

We provide the system. [Solution] A means of receiving user inquiries, A method that utilizes generative artificial intelligence to analyze received inquiries, A means of obtaining necessary information by calling an API of an external system based on the analysis results, A means by which a generative artificial intelligence generates a response to the user based on the acquired information, A means of providing the generated answer 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, including 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 recent years, many companies have introduced various digital tools to obtain the effects of digital transformation (DX). However, the operation and management of these digital tools require manpower, resulting in increased costs, which is a particularly heavy burden for small and medium-sized enterprises. In addition, it is difficult to respond quickly with conventional customer support methods, which is a factor reducing user satisfaction. Against this background, there is a demand for a new system to reduce operation costs and improve user support efficiency.

Means for Solving the Problems

[0005] This invention provides a system that includes the steps of receiving a user inquiry and having a generative artificial intelligence analyze the inquiry, calling an API of an external system to obtain necessary information based on the analysis results, and having the generative artificial intelligence generate an answer to the user based on the obtained information. This system can provide rapid and accurate support for user inquiries and reduce operating costs. Furthermore, by utilizing the API of a mobile device management system, it can also handle inquiries related to device management.

[0006] A "user" is an individual or organization that makes an inquiry to the chatbot.

[0007] "Inquiry" refers to the act of a user asking questions or making requests regarding operations or support through a chatbot.

[0008] "Generative artificial intelligence" refers to artificial intelligence that uses natural language processing technology to analyze user inquiries and generate appropriate answers.

[0009] "API" stands for Application Programming Interface, and it is a means of exchanging data and functions between different software systems.

[0010] "External systems" refer to systems that provide information related to user inquiries, such as mobile device management systems for managing user devices and networks.

[0011] "Answer" refers to the information or instructions that a generative artificial intelligence generates and provides to the user based on the user's inquiry.

[0012] A "chatbot" is an automated response system that can interact with users, receiving user inquiries and providing appropriate information and answers. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a 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, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system that efficiently processes user inquiries and provides quick and accurate responses. By linking generative artificial intelligence with APIs of external systems, this system automates user support, reduces operating costs, and improves user satisfaction.

[0035] The system consists of the following main components:

[0036] 1. Means for receiving user inquiries

[0037] 2. Means of analyzing inquiries using generative artificial intelligence

[0038] 3. Means of obtaining information by calling an API of an external system

[0039] 4. Means by which generative artificial intelligence generates responses to users

[0040] 5. Means of providing the generated response to the user

[0041] To understand how this system works, the program's processing will be explained with concrete examples.

[0042] Specific example

[0043] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[0044] 1. Receiving a user inquiry

[0045] The user sends a message to the chatbot saying, "I want to add a new device."

[0046] The terminal (user's device) sends this message to the server.

[0047] The server receives the message and begins processing it.

[0048] 2. Analysis using generative artificial intelligence

[0049] The server sends the received message to a generative artificial intelligence (for example, GPT-4®).

[0050] The generative artificial intelligence analyzes the message and determines its intent to be "instructions for adding a device."

[0051] 3. Information acquisition via API integration

[0052] Based on the analysis results, the server calls the mobile device management system's API and sends a request to retrieve the necessary information.

[0053] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[0054] 4. Answer generation using generative artificial intelligence

[0055] The server passes the acquired information to a generative artificial intelligence system and requests it to generate specific steps that the user should take.

[0056] Generative artificial intelligence generates "specific steps for adding a device."

[0057] For example, the instructions might say, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0058] 5. Providing responses to users

[0059] The server sends the generated response to the user via the chatbot.

[0060] The user follows the instructions from the chatbot to add the device.

[0061] This system allows users to receive instant, specific support. Furthermore, by combining generative artificial intelligence with external system APIs, accuracy and efficiency are improved, and operating costs are reduced. This system will significantly contribute to reducing operating costs and streamlining customer support, particularly for medium and small businesses.

[0062] The following describes the processing flow.

[0063] Step 1:

[0064] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[0065] The terminal (user's device) sends this message to the server.

[0066] Step 2:

[0067] The server sends the message received from the user to a generative artificial intelligence. For example, GPT-4 is used as the generative AI.

[0068] The generative artificial intelligence analyzes the message and determines the user's intent to be "procedures for adding a device."

[0069] Step 3:

[0070] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[0071] The server includes user authentication information and related device information in the API request.

[0072] Step 4:

[0073] The server sends the API request to the MDM system.

[0074] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[0075] The MDM system returns this information to the server as an API response.

[0076] Step 5:

[0077] The server receives a response from the MDM system and resends the acquired information to the generative artificial intelligence.

[0078] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[0079] Step 6:

[0080] The server receives the response generated by the generative artificial intelligence and responds to the user through the chatbot interface.

[0081] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[0082] Step 7 (Optional):

[0083] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[0084] Users provide feedback and contribute to improving the quality of the service.

[0085] (Example 1)

[0086] 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."

[0087] Conventional user support systems suffer from problems such as delayed and inaccurate responses to user inquiries. Furthermore, manual support is costly to operate, especially for small and medium-sized enterprises. This invention aims to solve these problems, improve user satisfaction, and reduce operating costs.

[0088] 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.

[0089] In this invention, the server includes means for receiving user inquiries, means for registering the received inquiries in a message queue, means for requesting a generative artificial intelligence to analyze the messages, means for the generative artificial intelligence to call an API of an external system to obtain necessary information based on the analysis results, means for requesting the generative artificial intelligence to analyze the obtained information again to generate a response to the user, and means for providing the generated response to the user. This enables a rapid and accurate response to user inquiries, resulting in reduced operating costs and improved user satisfaction.

[0090] A "user" refers to a person who makes a request to the system.

[0091] An "inquiry" refers to a question or request that a user sends to a system.

[0092] "Means of receiving" refers to the function that allows the server to receive inquiries sent by users.

[0093] A "message queue" refers to a data structure used to temporarily store received inquiries and process them in order.

[0094] "Generative artificial intelligence" refers to artificial intelligence technologies (such as natural language processing technologies) that analyze received inquiries and understand their intent.

[0095] "Means of analysis" refers to a function that uses generative artificial intelligence to analyze the content of received inquiries and identify their intent and requirements.

[0096] "External systems" refer to third-party systems or services that the server uses to acquire information in cooperation with it.

[0097] An "API" refers to an application programming interface provided by an external system, offering a method for a server to communicate with that external system.

[0098] "Means of acquiring information" refers to the function of acquiring necessary information from external systems via APIs based on the analysis results of generative artificial intelligence.

[0099] "Means for generating answers" refers to a function that allows a generative artificial intelligence to generate specific answers for the user based on the acquired information.

[0100] "Means of delivery" refers to functions for communicating generated responses to users through chatbots or similar means.

[0101] This invention is a system that efficiently processes user inquiries and provides quick and accurate answers. By linking generative artificial intelligence with APIs of external systems, the system automates user support, reduces operating costs, and improves user satisfaction.

[0102] The system consists of the following main hardware and software components:

[0103] 1. A means of receiving user inquiries (e.g., a chatbot)

[0104] 2. Methods for analyzing queries using generative artificial intelligence (e.g., GPT-4)

[0105] 3. Means of obtaining information by calling APIs of external systems (e.g., APIs of mobile device management systems (MDM))

[0106] 4. Means by which generative artificial intelligence generates responses to users

[0107] 5. Means of providing the generated response to the user

[0108] The following describes the specific processing steps of this system's program.

[0109] 1. Receiving a user inquiry

[0110] The user sends a message to the chatbot saying, "I want to add a new device." The user's device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0111] 2. Analysis using generative artificial intelligence

[0112] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent as "device addition procedure."

[0113] 3. Information acquisition via API integration

[0114] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0115] 4. Answer generation using generative artificial intelligence

[0116] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI generates "specific steps for adding a device." For example, it might show steps such as, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0117] 5. Providing responses to users

[0118] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a new device to the network.

[0119] Specific example

[0120] When a user wants to add a new device to the company network, the following prompt is entered into the generative artificial intelligence.

[0121] Example of a prompt:

[0122] "Please tell me how to add a new device to the company network."

[0123] The generative artificial intelligence generates instructions based on this prompt, and these instructions are provided to the user from the server via a chatbot. This process allows the user to quickly receive specific instructions and add devices. This system will greatly contribute to reducing operational costs and improving the efficiency of customer support, especially for small and medium-sized enterprises.

[0124] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0125] The processing flow of this system's program

[0126] Step 1:

[0127] The user enters and sends the message "I want to add a new device" to the chatbot. The device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0128] Input: User inquiry message

[0129] Output: Registered to message queue

[0130] Specific actions:

[0131] The user enters a message using the chatbot and clicks the "Send" button.

[0132] The device sends a message to the server using an HTTP POST request.

[0133] The server receives the message and stores it in the message queue.

[0134] Step 2:

[0135] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent to be "device addition instructions."

[0136] Input: User inquiry retrieved from the message queue

[0137] Output: Analysis results (for example, the intent behind "Procedure for adding a device")

[0138] Specific actions:

[0139] The server retrieves the message from the queue.

[0140] The server sends a request to GPT-4 using a pre-configured prompt.

[0141] GPT-4 analyzes the message and identifies its intent.

[0142] Step 3:

[0143] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0144] Input: Request to retrieve information based on analysis results

[0145] Output: Network configuration information and procedure information from the MDM system.

[0146] Specific actions:

[0147] The server generates an HTTP request and sends it to a specific endpoint in the MDM system.

[0148] The MDM system receives the request and returns network configuration information to the server as a response.

[0149] Step 4:

[0150] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI then generates "specific steps for adding a device."

[0151] Input: Network configuration information and procedure information obtained from the API.

[0152] Output: Specific steps the user should take

[0153] Specific actions:

[0154] The server includes the information it has obtained in the prompt message and passes it to GPT-4.

[0155] GPT-4 generates specific procedures based on this information.

[0156] For example: "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0157] Step 5:

[0158] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a device.

[0159] Input: Generated specific steps

[0160] Output: Displayed as a response to the user

[0161] Specific actions:

[0162] The server sends the generated steps to the chatbot's API, which then displays them in the user's chat window.

[0163] The user adds a device by following the instructions: "Log in to the XX portal and click the 'Add New Device' button."

[0164] In this way, by performing the necessary data processing and calculations at each step, we can respond quickly and accurately to user inquiries.

[0165] (Application Example 1)

[0166] 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."

[0167] Responding to user inquiries on modern e-commerce sites is often time-consuming and labor-intensive, leading to decreased user satisfaction and increased operational costs. Furthermore, there is a demand for quick and accurate responses to frequent inquiries such as inventory checks and purchase procedures. Traditional systems have struggled to efficiently address these challenges.

[0168] 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.

[0169] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, and, if the user's inquiry concerns checking product inventory or purchasing procedures, means for obtaining inventory information of the relevant product through an API of an external system and for the generative artificial intelligence to generate an answer including the inventory status of the relevant product. As a result, users can receive quick and accurate support, reducing operating costs and improving user satisfaction.

[0170] "Means for receiving user inquiries" refers to an interface for receiving questions and requests that users make to the system.

[0171] "Methods of utilizing generative artificial intelligence" refers to the process of using generative artificial intelligence to analyze user inquiries and understand their intent and content.

[0172] "A means of obtaining necessary information by calling an external system's API" refers to the process of using an external information system's API based on the analysis results to retrieve data and information related to the inquiry.

[0173] "A means by which generative artificial intelligence generates responses to users" refers to the process by which generative artificial intelligence creates appropriate responses to user inquiries based on acquired information.

[0174] "Means of providing generated answers to users" refers to an interface for conveying answers and information generated by generative artificial intelligence to users.

[0175] "Inquiries regarding product stock availability and purchase procedures" refer to inquiries from users asking about the stock status of a specific product or seeking information on how to purchase it.

[0176] "Means of obtaining inventory information for the relevant product through an external system's API" refers to the process of obtaining inventory data for a specific product from an external system using an API.

[0177] "Means for generating a response that includes the inventory status of the relevant product" refers to a process for generating an appropriate response for the user, including the inventory status, based on acquired inventory information.

[0178] This invention is a system that provides quick and accurate responses to user inquiries. This system is particularly intended for inquiries regarding product inventory checks and purchase procedures on e-commerce websites, and is designed to improve user satisfaction and reduce operating costs. The following describes specific embodiments for implementing this invention.

[0179] The server utilizes technologies such as generative artificial intelligence (GPT-4), RESTful APIs, and mobile application frameworks (e.g., React Native). This system operates through an application installed on the user's smartphone.

[0180] When a user makes an inquiry via their smartphone, the following processes take place.

[0181] When a user submits an inquiry, it is first sent to the server. The server then passes this inquiry to a generative artificial intelligence (AI) for analysis. The AI ​​understands the intent and content of the inquiry, and based on the analysis results, it calls an API of an external system to obtain the necessary information.

[0182] For example, if a user sends a prompt such as "Do you have this item in stock? Item ID: 12345," the server analyzes this inquiry and calls an API of an external e-commerce platform to check the stock of the relevant item. Based on the stock information obtained from the API, generative artificial intelligence generates an answer for the user.

[0183] The generated responses are provided to the user in an easy-to-understand format. This process allows users to check inventory accurately and quickly, supporting their purchasing decisions.

[0184] This system can handle a wide range of complex inquiries and significantly improves the user experience, as demonstrated by the specific examples below.

[0185] Adding specific examples

[0186] Example of a prompt

[0187] 1. "Is this T-shirt in stock? Product ID: 98765"

[0188] 2. "Please leave a review for this product. Product ID: 12345"

[0189] 3. "Please tell me how to return this backpack."

[0190] By using these prompts, generative artificial intelligence can quickly generate and provide accurate answers to users. This allows users to obtain product information from the comfort of their homes, improving their online shopping experience.

[0191] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0192] Step 1:

[0193] A user makes an inquiry through a smartphone app. The user enters the prompt message "Is this product in stock? Product ID: 12345" and presses the submit button. The entered inquiry is sent from the device to the server. The input is the user's inquiry, and the output is the inquiry data received by the server.

[0194] Step 2:

[0195] The server sends the received inquiry data to a generative artificial intelligence (GPT-4). The generative AI analyzes the inquiry and determines its intent to be "check product inventory." Natural language processing is used for this analysis; the input is the inquiry data, and the output is the analysis result data.

[0196] Step 3:

[0197] The server calls an API of an external system based on the analysis results and sends a request to retrieve inventory information for the specified product ID. Here, an HTTP request is made to the API endpoint. The input is the analysis result data, and the output is the product inventory information returned from the API.

[0198] Step 4:

[0199] The server receives product inventory information returned from the API. This inventory information includes the availability status (in stock or out of stock) corresponding to the product ID. The input is the inventory information returned by the API, and the output is the storage of the inventory information within the server.

[0200] Step 5:

[0201] The server passes the acquired inventory information back to the generative artificial intelligence (AI) to generate a specific response to provide to the user. The generative AI generates a response such as, "The inventory for product ID: 12345 is AA." The input is inventory information, and the output is the generated specific response.

[0202] Step 6:

[0203] The server sends the generated response to the user's smartphone app. The device receives the response message and displays it to the user. The user can then view the response regarding the inventory status on their smartphone screen. The input is the generated response, and the output is the response message displayed to the user.

[0204] This processing flow allows users to quickly and accurately obtain product inventory information, supporting their purchasing decisions.

[0205] 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.

[0206] This invention provides a system that efficiently processes user inquiries and delivers quick and accurate responses by combining it with an emotion engine, thereby providing optimal responses tailored to the user's emotions. This system automates user support by linking generative artificial intelligence with APIs of external systems, reducing operational costs while achieving high user satisfaction that takes user emotions into consideration.

[0207] The system consists of the following main components:

[0208] 1. Means for receiving user inquiries

[0209] 2. Means of analyzing inquiries using generative artificial intelligence

[0210] 3. Means of obtaining information by calling an API of an external system

[0211] 4. Means by which generative artificial intelligence generates responses to users

[0212] 5. Means of providing the generated response to the user

[0213] 6. A means of using an emotion engine to recognize the emotions of users when receiving their inquiries.

[0214] 7. Means by which the emotion engine recognizes the user's emotions and provides additional contextual information to the generative artificial intelligence based on those emotions.

[0215] 8. Means for adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[0216] 9. A means by which the emotion engine analyzes not only the content of the inquiry but also the entire user interaction in order to regularly monitor the user's emotions.

[0217] To understand how this system works, the program's processing will be explained with concrete examples.

[0218] Specific example

[0219] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[0220] 1. Receiving a user inquiry

[0221] The user sends a message to the chatbot saying, "I want to add a new device."

[0222] The terminal (user's device) sends this message to the server.

[0223] 2. Emotion recognition by an emotion engine

[0224] The server sends the message received from the user to the emotion engine.

[0225] The emotion engine analyzes the message and recognizes the user's emotions (e.g., excitement, frustration, confusion, etc.).

[0226] 3. Analysis using generative artificial intelligence

[0227] The server sends the emotion recognition results from the emotion engine to the generative artificial intelligence.

[0228] The generative artificial intelligence analyzes the message and emotion recognition results to determine the user's intention is "procedures for adding a device."

[0229] 4. Information acquisition via API integration

[0230] Based on the analysis results, the server calls the API of the mobile device management system (MDM system) and sends a request to retrieve the necessary information.

[0231] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[0232] 5. Answer generation using generative artificial intelligence

[0233] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[0234] Generative artificial intelligence generates "specific steps for adding a device." These steps are generated with consideration for the user's emotions and tone. For example, if the user is frustrated, the explanation will be more detailed and polite.

[0235] 6. Providing responses to users

[0236] The server sends the generated response back to the user through the chatbot interface.

[0237] The user adds the device by following the instructions given by the chatbot.

[0238] This system allows users to receive instant, specific, and emotionally sensitive support. Furthermore, by combining generative artificial intelligence with an emotion engine, accuracy and efficiency are improved, leading to increased user satisfaction. This system will significantly contribute to reducing operational costs and streamlining customer support, particularly for medium and small businesses.

[0239] The following describes the processing flow.

[0240] Step 1:

[0241] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[0242] The terminal (user's device) sends this message to the server.

[0243] Step 2:

[0244] The server sends the message received from the user to the emotion engine.

[0245] The emotion engine analyzes messages and recognizes the user's emotions.

[0246] Step 3:

[0247] The emotion engine sends the analysis results back to the server. These results include information about the user's emotions (e.g., excitement, frustration, confusion).

[0248] Step 4:

[0249] The server sends the received emotion recognition results and the user's message to the generative artificial intelligence.

[0250] Based on this information, the generative artificial intelligence determines the user's intention to be "procedures for adding a device."

[0251] Step 5:

[0252] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[0253] API requests include user authentication information and associated device information.

[0254] Step 6:

[0255] The server sends the API request to the MDM system.

[0256] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[0257] The MDM system returns this information to the server as an API response.

[0258] Step 7:

[0259] The server receives a response from the MDM system and sends the acquired information and emotion recognition results back to the generative artificial intelligence.

[0260] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[0261] The generated instructions are adjusted in content and tone to take the user's emotions into consideration. For example, if the user is frustrated, a more detailed and polite explanation will be generated.

[0262] Step 8:

[0263] The server sends the generated response back to the user through the chatbot interface.

[0264] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[0265] Step 9 (Optional):

[0266] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[0267] Users provide feedback and contribute to improving the quality of the service.

[0268] (Example 2)

[0269] 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".

[0270] Traditional customer support systems suffered from problems such as insensitive responses to user emotions and cumbersome procedures, leading to decreased user satisfaction. In particular, the inability to appropriately understand user emotions resulted in a decline in response quality. Furthermore, while prompt and accurate responses to inquiries were required, efficient information gathering and appropriate response generation proved difficult.

[0271] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0272] In this invention, the server includes means for receiving user inquiries, means for transmitting the received inquiries to an emotion analysis engine and recognizing the user's emotions, means for transmitting the results of the emotion analysis engine to a generative artificial intelligence and analyzing the received inquiries, means for calling an API of an external system based on the analysis results to obtain necessary information, means for the generative artificial intelligence to generate a response to the user in an emotion-sensitive tone based on the acquired information, and means for providing the generated response to the user. This enables a rapid and accurate response that takes the user's emotions into consideration.

[0273] "Means for receiving user inquiries" refers to devices or systems for receiving inquiries sent by users via communication.

[0274] "A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions" refers to a device or system that sends the content of received inquiries to a program or device for performing emotion analysis, thereby identifying the user's emotional state.

[0275] "A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence and analyzing the received inquiry" refers to a program or device that transmits the results obtained from emotion analysis to a generative artificial intelligence and analyzes and understands the content of the inquiry.

[0276] "Means of calling an external system's API based on analysis results to obtain necessary information" refers to a program or device that operates an external system's API based on analysis results to obtain the necessary information.

[0277] "A means by which generative artificial intelligence generates responses to users in an emotionally sensitive tone based on acquired information" refers to a device or system in which generative artificial intelligence considers acquired information and the user's emotional state to create the optimal response, taking into account tone and content.

[0278] The means for "providing the generated answer to the user" refers to a device or system for providing an answer created by a generative artificial intelligence to the user.

[0279] The present invention is a system for providing an efficient and appropriate response to a user's inquiry. This system utilizes a generative artificial intelligence and a sentiment analysis engine to take into account the user's emotions and generate a quick and accurate answer.

[0280] This system is composed of several main components. Each component and its function are shown below.

[0281] Hardware and software configuration

[0282] 1. Means for receiving the user's inquiry

[0283] This means usually includes a web-based chatbot interface and a mobile application. The content of the inquiry entered by the user is sent to the server in real time.

[0284] 2. Means for sending the received inquiry to the sentiment analysis engine and recognizing the user's emotion

[0285] The server sends the received inquiry to the sentiment analysis engine. The sentiment analysis engine analyzes the sentiment in the text using a sentiment recognition API such as Affectiva. In this step, it is determined whether the user is excited, frustrated, or confused.

[0286] 3. Means for sending the result of the sentiment analysis engine to the generative artificial intelligence and analyzing the received inquiry

[0287] The server sends the result obtained from the sentiment analysis engine to the generative artificial intelligence (e.g., GPT-4). This generative artificial intelligence analyzes the user's intention based on the content of the inquiry and the sentiment data.

[0288] 4. A means of obtaining necessary information by calling an API of an external system based on the analysis results.

[0289] Based on the analysis results, the server calls APIs of external systems (e.g., mobile device management systems) to collect necessary information. For example, the MICROSOFT® INTUNE® API is used to obtain the current network configuration and necessary procedural information.

[0290] 5. A method by which a generative artificial intelligence generates responses to the user in an emotionally sensitive tone based on the acquired information.

[0291] The server retransmits the acquired information and sentiment analysis results to a generative artificial intelligence system to generate a response for the user. The generated response is crafted in a tone that takes the user's emotions into consideration. For example, if the user is irritated, the response will include a more polite and detailed explanation.

[0292] 6. Means of providing the generated response to the user

[0293] The server provides the generated response to the user through the chatbot interface. The user then solves the problem according to this response.

[0294] Examples of specific cases and prompt statements

[0295] Specific example

[0296] When a user wants to add a new device to the company network, the following steps are taken:

[0297] The user sends a message to the chatbot saying, "I want to add a new device."

[0298] The terminal (user's device) sends this message to the server.

[0299] The server sends the message to the sentiment analysis engine and recognizes that the user is confused.

[0300] The server sends the result of the sentiment analysis engine to the generative artificial intelligence (GPT-4) and determines that the user's intention is the "procedure for adding a device".

[0301] The server calls the Microsoft Intune API and obtains the necessary information.

[0302] Based on the obtained information and the sentiment recognition result, the server generates specific procedures using generative artificial intelligence.

[0303] The server provides the generated procedures to the user through the chatbot, and the user adds the device according to the provided procedures.

[0304] Examples of prompt sentences

[0305] "Please teach me the procedure for adding a new device to the company network."

[0306] "Please show the appropriate support procedures when the user is confused."

[0307] With this system, users can receive support efficiently and obtain appropriate answers according to the content of their inquiries. This improves user satisfaction and reduces the company's operating costs.

[0308] The flow of the specific process in Example 2 will be described using FIG. 13.

[0309] Step 1:

[0310] The user sends a message "I want to add a new device" to the chatbot.

[0311] Input: The message entered by the user into the chatbot.

[0312] Output: The message is sent from the terminal to the server.

[0313] Specific operation: When a user uses a device (e.g., a smartphone or computer) to type a message into the chatbot and presses the send button, the device sends this message to the server.

[0314] Step 2:

[0315] The server sends the received message to the sentiment analysis engine.

[0316] Input: Message received from the user.

[0317] Output: The message is passed to the sentiment analysis engine.

[0318] Specific operation: The server analyzes the received message, converts it to an appropriate format, and then sends it to the sentiment analysis engine. At this time, the text data is sent to the sentiment recognition API, and the analysis begins.

[0319] Step 3:

[0320] The emotion analysis engine analyzes the message and recognizes the user's emotions.

[0321] Input: The message text sent from the server.

[0322] Output: User emotion information (e.g., excitement, frustration, confusion, etc.).

[0323] Specific operation: The sentiment analysis engine analyzes the text and uses a language model to determine the user's emotions. The emotion recognition results are converted into a data format and sent back to the server.

[0324] Step 4:

[0325] The server transmits the emotion recognition results obtained from the emotion analysis engine to the generative artificial intelligence.

[0326] Input: User message and sentiment recognition result.

[0327] Output: Data sent to a generative artificial intelligence system as an analysis request.

[0328] Specific operation: The server converts the emotion recognition results into an appropriate format for sending to a generative artificial intelligence (e.g., GPT-4) and sends a request to the generative artificial intelligence.

[0329] Step 5:

[0330] Generative artificial intelligence analyzes user inquiries based on messages and emotion recognition results.

[0331] Input: User message and sentiment recognition result.

[0332] Output: Analysis results regarding user intent (e.g., "Steps to add a device").

[0333] Specific operation: Generative artificial intelligence uses natural language processing techniques to analyze messages and identify the user's intent. The analysis results are sent to the server as data.

[0334] Step 6:

[0335] Based on the analysis results, the server calls an API of an external system (e.g., a mobile device management system) to obtain the necessary information.

[0336] Input: Analysis results from a generative artificial intelligence.

[0337] Output: Information obtained from external systems (e.g., network configuration, procedure information).

[0338] Specific operation: The server creates an API request based on the analysis results of the generative artificial intelligence, and calls the appropriate external system's API to retrieve information. The retrieved information is stored on the server.

[0339] Step 7:

[0340] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[0341] Input: Acquired information and emotion recognition results.

[0342] Output: Detailed user instructions.

[0343] Specific operation: The server sends the acquired information and emotion recognition results to the generative artificial intelligence in an appropriate format and requests it to generate a response that takes the user's emotions into consideration.

[0344] Step 8:

[0345] Generative artificial intelligence generates "specific steps for adding a device."

[0346] Input: Acquired information and emotion recognition results.

[0347] Output: A detailed instruction manual provided to the user.

[0348] Specific operation: Generative artificial intelligence takes user emotions into consideration and generates detailed and careful instructions. For example, if the user is frustrated, the instructions will be provided in detail and with images.

[0349] Step 9:

[0350] The server responds to the user with the generated instructions through the chatbot interface.

[0351] Input: Specific instructions from a generative artificial intelligence.

[0352] Output: Instructional information provided to the user.

[0353] Specific operation: The server sends the generated instructions to the chatbot, which then displays them to the user. The user adds a device following the provided instructions.

[0354] (Application Example 2)

[0355] 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".

[0356] With the proliferation of autonomous vehicles, users are increasingly making real-time inquiries and giving instructions while driving. However, conventional systems provide uniform responses without considering user emotions, making it difficult to ensure user satisfaction and safety. In particular, in emergencies and high-stress situations where a quick and appropriate response is required, it is crucial to provide responses that are sensitive to the user's emotions.

[0357] 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.

[0358] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, means for utilizing an emotion engine to analyze the user's emotions, means for adjusting the content and tone of the answer based on the emotions recognized by the emotion engine, and means for processing user inquiries and instructions in real time while the autonomous vehicle is in operation. This enables quick and appropriate responses to inquiries that take into account the user's emotions, even while the autonomous vehicle is in operation.

[0359] "Means for receiving user inquiries" refers to the interface used to receive messages when a user sends voice or text messages to the system.

[0360] "Methods of using generative artificial intelligence to analyze received inquiries" refers to processes that use generative artificial intelligence to analyze messages received from users in order to understand the user's intent.

[0361] "A means of obtaining necessary information by calling an external system's API based on the analysis results" refers to the process of obtaining necessary data and information by calling an external system's API based on the results analyzed by generative artificial intelligence.

[0362] "A means by which generative artificial intelligence generates a response to the user based on acquired information" refers to the process by which generative artificial intelligence generates an appropriate response to the user based on information acquired from an external system.

[0363] "Means of providing generated answers to users" refers to an interface and processing method for presenting answers generated by generative artificial intelligence to users.

[0364] "Using an emotion engine to analyze user emotions" refers to a process that uses an engine to understand the user's emotional state based on the content of user inquiries and instructions.

[0365] "Means for adjusting the content and tone of responses based on emotions recognized by the emotion engine" refers to the process of appropriately adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[0366] "Means for processing user inquiries and instructions in real time while an autonomous vehicle is in operation" refers to a system and process that allows an autonomous vehicle to respond immediately to real-time inquiries and instructions from users while it is in operation.

[0367] Patent Specification

[0368] This invention is a system for efficiently and emotionally processing user inquiries and instructions in real time while an autonomous vehicle is in operation. Specifically, it receives user inquiries, analyzes the user's emotions using an emotion engine, and then uses generative artificial intelligence to generate and provide appropriate answers based on the results.

[0369] Hardware and software to be used

[0370] hardware

[0371] Smartphone: A device in which users input inquiries and instructions via voice or text.

[0372] Autonomous vehicles: Connect to a smartphone via Bluetooth or Wi-Fi and send driving information to a server.

[0373] Server: A central system for analysis and data processing.

[0374] software

[0375] Generative artificial intelligence: Software used to analyze user inquiries using natural language processing. (Examples: Google Cloud Natural Language API, IBM Watson)

[0376] Emotion engine: Software used to analyze user emotions. (Example: Amazon Comprehend)

[0377] API Integration Module: A library for calling APIs of external systems (e.g., mobile device management systems). (e.g., Requests library)

[0378] Program Processing Description

[0379] Recording and transmitting audio data

[0380] The user gives voice commands using their smartphone. The smartphone records the voice data and sends it to the server.

[0381] Emotional analysis using an emotion engine

[0382] The server passes the received audio data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions from the audio content and returns the result.

[0383] Response generation by generative artificial intelligence

[0384] The server passes the voice data, along with the results from the emotion engine, to the generative artificial intelligence (AI) to analyze the user's intent. The generative AI then generates an appropriate response based on the analysis results.

[0385] API integration and information retrieval

[0386] If necessary, the server calls APIs of external systems to obtain the data and information required for operation. The obtained information is passed to a generative artificial intelligence and used to generate the final answer.

[0387] Providing answers to users

[0388] The server sends the generated response back to the smartphone, providing it to the user. The user then decides on their next action based on that response.

[0389] Specific examples and prompt statements

[0390] Specific example

[0391] For example, consider a scenario where a user in an autonomous vehicle asks, "How long will it take to get to the next gas station?"

[0392] Voice: "How far is it to the next gas station?"

[0393] Prompt to the AI ​​engine: "User question: How long until the next gas station? User's mood: A little impatient."

[0394] This allows the system to provide responses that are appropriate to the user's emotions, enabling them to reach their destination comfortably and safely, even while driving autonomously.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1: The user gives a voice command.

[0397] The user, while inside the autonomous vehicle, gives a voice command into their smartphone's microphone, such as, "How long will it take to get to the next gas station?" This voice data becomes the input.

[0398] Step 2: The device records the audio data.

[0399] The device (smartphone) records the user's voice and saves it as an audio file in its internal data. The output obtained here is an audio file.

[0400] Step 3: The device sends the audio data to the server.

[0401] The terminal sends the recorded audio file to the server. In this step, the terminal takes an audio file as input and performs the procedure (communication processing) to send it to the server. The output is the audio data stored on the server.

[0402] Step 4: The server passes the voice data to the emotion engine.

[0403] The server inputs the received audio data into the emotion engine, which analyzes the user's emotions. The emotion engine then outputs text data and emotion recognition results based on the audio data.

[0404] Step 5: The server passes the emotion analysis results to the generative artificial intelligence.

[0405] The server passes the speech text data, along with the emotion recognition results from the emotion engine, to the generative artificial intelligence. The generative AI takes this as input, analyzes the user's intent, and generates an appropriate response. The generated response becomes the output.

[0406] Step 6: The server calls the API to retrieve the necessary information.

[0407] Based on the analysis results, the server calls APIs of external systems such as mobile device management systems to obtain necessary information (for example, the location information of nearby gas stations). The API calls are the input, and the information obtained from the external systems is the output.

[0408] Step 7: The server generates the final answer.

[0409] The server then passes the acquired information and emotion analysis results back to the generative artificial intelligence to generate the final response. Based on this, the generative AI outputs the optimal response that takes the user's emotions into consideration.

[0410] Step 8: The server provides the answer to the user.

[0411] The server sends the generated response to the terminal (smartphone) and provides it to the user. In this step, the server takes the generated response as input and sends it to the user's terminal as output. The user receives the response and decides on their next action.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] [Second Embodiment]

[0416] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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".

[0428] This invention provides a system that efficiently processes user inquiries and provides quick and accurate responses. By linking generative artificial intelligence with APIs of external systems, this system automates user support, reduces operating costs, and improves user satisfaction.

[0429] The system consists of the following main components:

[0430] 1. Means for receiving user inquiries

[0431] 2. Means of analyzing inquiries using generative artificial intelligence

[0432] 3. Means of obtaining information by calling an API of an external system

[0433] 4. Means by which generative artificial intelligence generates responses to users

[0434] 5. Means of providing the generated response to the user

[0435] To understand how this system works, the program's processing will be explained with concrete examples.

[0436] Specific example

[0437] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[0438] 1. Receiving a user inquiry

[0439] The user sends a message to the chatbot saying, "I want to add a new device."

[0440] The terminal (user's device) sends this message to the server.

[0441] The server receives the message and begins processing it.

[0442] 2. Analysis using generative artificial intelligence

[0443] The server sends the received message to a generative artificial intelligence (e.g., GPT-4).

[0444] The generative artificial intelligence analyzes the message and determines its intent to be "instructions for adding a device."

[0445] 3. Information acquisition via API integration

[0446] Based on the analysis results, the server calls the mobile device management system's API and sends a request to retrieve the necessary information.

[0447] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[0448] 4. Answer generation using generative artificial intelligence

[0449] The server passes the acquired information to a generative artificial intelligence system and requests it to generate specific steps that the user should take.

[0450] Generative artificial intelligence generates "specific steps for adding a device."

[0451] For example, the instructions might say, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0452] 5. Providing responses to users

[0453] The server sends the generated response to the user via the chatbot.

[0454] The user follows the instructions from the chatbot to add the device.

[0455] This system allows users to receive instant, specific support. Furthermore, by combining generative artificial intelligence with external system APIs, accuracy and efficiency are improved, and operating costs are reduced. This system will significantly contribute to reducing operating costs and streamlining customer support, particularly for medium and small businesses.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[0459] The terminal (user's device) sends this message to the server.

[0460] Step 2:

[0461] The server sends the message received from the user to a generative artificial intelligence. For example, GPT-4 is used as the generative AI.

[0462] The generative artificial intelligence analyzes the message and determines the user's intent to be "procedures for adding a device."

[0463] Step 3:

[0464] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[0465] The server includes user authentication information and related device information in the API request.

[0466] Step 4:

[0467] The server sends the API request to the MDM system.

[0468] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[0469] The MDM system returns this information to the server as an API response.

[0470] Step 5:

[0471] The server receives a response from the MDM system and resends the acquired information to the generative artificial intelligence.

[0472] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[0473] Step 6:

[0474] The server receives the response generated by the generative artificial intelligence and responds to the user through the chatbot interface.

[0475] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[0476] Step 7 (Optional):

[0477] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[0478] Users provide feedback and contribute to improving the quality of the service.

[0479] (Example 1)

[0480] 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."

[0481] Conventional user support systems suffer from problems such as delayed and inaccurate responses to user inquiries. Furthermore, manual support is costly to operate, especially for small and medium-sized enterprises. This invention aims to solve these problems, improve user satisfaction, and reduce operating costs.

[0482] 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.

[0483] In this invention, the server includes means for receiving user inquiries, means for registering the received inquiries in a message queue, means for requesting a generative artificial intelligence to analyze the messages, means for the generative artificial intelligence to call an API of an external system to obtain necessary information based on the analysis results, means for requesting the generative artificial intelligence to analyze the obtained information again to generate a response to the user, and means for providing the generated response to the user. This enables a rapid and accurate response to user inquiries, resulting in reduced operating costs and improved user satisfaction.

[0484] A "user" refers to a person who makes a request to the system.

[0485] An "inquiry" refers to a question or request that a user sends to a system.

[0486] "Means of receiving" refers to the function that allows the server to receive inquiries sent by users.

[0487] A "message queue" refers to a data structure used to temporarily store received inquiries and process them in order.

[0488] "Generative artificial intelligence" refers to artificial intelligence technologies (such as natural language processing technologies) that analyze received inquiries and understand their intent.

[0489] "Means of analysis" refers to a function that uses generative artificial intelligence to analyze the content of received inquiries and identify their intent and requirements.

[0490] "External systems" refer to third-party systems or services that the server uses to acquire information in cooperation with it.

[0491] An "API" refers to an application programming interface provided by an external system, offering a method for a server to communicate with that external system.

[0492] "Means of acquiring information" refers to the function of acquiring necessary information from external systems via APIs based on the analysis results of generative artificial intelligence.

[0493] "Means for generating answers" refers to a function that allows a generative artificial intelligence to generate specific answers for the user based on the acquired information.

[0494] "Means of delivery" refers to functions for communicating generated responses to users through chatbots or similar means.

[0495] This invention is a system that efficiently processes user inquiries and provides quick and accurate answers. By linking generative artificial intelligence with APIs of external systems, the system automates user support, reduces operating costs, and improves user satisfaction.

[0496] The system consists of the following main hardware and software components:

[0497] 1. A means of receiving user inquiries (e.g., a chatbot)

[0498] 2. Methods for analyzing queries using generative artificial intelligence (e.g., GPT-4)

[0499] 3. Means of obtaining information by calling APIs of external systems (e.g., APIs of mobile device management systems (MDM))

[0500] 4. Means by which generative artificial intelligence generates responses to users

[0501] 5. Means of providing the generated response to the user

[0502] The following describes the specific processing steps of this system's program.

[0503] 1. Receiving a user inquiry

[0504] The user sends a message to the chatbot saying, "I want to add a new device." The user's device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0505] 2. Analysis using generative artificial intelligence

[0506] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent as "device addition procedure."

[0507] 3. Information acquisition via API integration

[0508] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0509] 4. Answer generation using generative artificial intelligence

[0510] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI generates "specific steps for adding a device." For example, it might show steps such as, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0511] 5. Providing responses to users

[0512] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a new device to the network.

[0513] Specific example

[0514] When a user wants to add a new device to the company network, the following prompt is entered into the generative artificial intelligence.

[0515] Example of a prompt:

[0516] "Please tell me how to add a new device to the company network."

[0517] The generative artificial intelligence generates instructions based on this prompt, and these instructions are provided to the user from the server via a chatbot. This process allows the user to quickly receive specific instructions and add devices. This system will greatly contribute to reducing operational costs and improving the efficiency of customer support, especially for small and medium-sized enterprises.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] The processing flow of this system's program

[0520] Step 1:

[0521] The user enters and sends the message "I want to add a new device" to the chatbot. The device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0522] Input: User inquiry message

[0523] Output: Registered to message queue

[0524] Specific actions:

[0525] The user enters a message using the chatbot and clicks the "Send" button.

[0526] The device sends a message to the server using an HTTP POST request.

[0527] The server receives the message and stores it in the message queue.

[0528] Step 2:

[0529] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent to be "device addition instructions."

[0530] Input: User inquiry retrieved from the message queue

[0531] Output: Analysis results (for example, the intent behind "Procedure for adding a device")

[0532] Specific actions:

[0533] The server retrieves the message from the queue.

[0534] The server sends a request to GPT-4 using a pre-configured prompt.

[0535] GPT-4 analyzes the message and identifies its intent.

[0536] Step 3:

[0537] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0538] Input: Request to retrieve information based on analysis results

[0539] Output: Network configuration information and procedure information from the MDM system.

[0540] Specific actions:

[0541] The server generates an HTTP request and sends it to a specific endpoint in the MDM system.

[0542] The MDM system receives the request and returns network configuration information to the server as a response.

[0543] Step 4:

[0544] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI then generates "specific steps for adding a device."

[0545] Input: Network configuration information and procedure information obtained from the API.

[0546] Output: Specific steps the user should take

[0547] Specific actions:

[0548] The server includes the information it has obtained in the prompt message and passes it to GPT-4.

[0549] GPT-4 generates specific procedures based on this information.

[0550] For example: "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0551] Step 5:

[0552] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a device.

[0553] Input: Generated specific steps

[0554] Output: Displayed as a response to the user

[0555] Specific actions:

[0556] The server sends the generated steps to the chatbot's API, which then displays them in the user's chat window.

[0557] The user adds a device by following the instructions: "Log in to the XX portal and click the 'Add New Device' button."

[0558] In this way, by performing the necessary data processing and calculations at each step, we can respond quickly and accurately to user inquiries.

[0559] (Application Example 1)

[0560] 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."

[0561] Responding to user inquiries on modern e-commerce sites is often time-consuming and labor-intensive, leading to decreased user satisfaction and increased operational costs. Furthermore, there is a demand for quick and accurate responses to frequent inquiries such as inventory checks and purchase procedures. Traditional systems have struggled to efficiently address these challenges.

[0562] 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.

[0563] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, and, if the user's inquiry concerns checking product inventory or purchasing procedures, means for obtaining inventory information of the relevant product through an API of an external system and for the generative artificial intelligence to generate an answer including the inventory status of the relevant product. As a result, users can receive quick and accurate support, reducing operating costs and improving user satisfaction.

[0564] "Means for receiving user inquiries" refers to an interface for receiving questions and requests that users make to the system.

[0565] "Methods of utilizing generative artificial intelligence" refers to the process of using generative artificial intelligence to analyze user inquiries and understand their intent and content.

[0566] "A means of obtaining necessary information by calling an external system's API" refers to the process of using an external information system's API based on the analysis results to retrieve data and information related to the inquiry.

[0567] "A means by which generative artificial intelligence generates responses to users" refers to the process by which generative artificial intelligence creates appropriate responses to user inquiries based on acquired information.

[0568] "Means of providing generated answers to users" refers to an interface for conveying answers and information generated by generative artificial intelligence to users.

[0569] "Inquiries regarding product stock availability and purchase procedures" refer to inquiries from users asking about the stock status of a specific product or seeking information on how to purchase it.

[0570] "Means of obtaining inventory information for the relevant product through an external system's API" refers to the process of obtaining inventory data for a specific product from an external system using an API.

[0571] "Means for generating a response that includes the inventory status of the relevant product" refers to a process for generating an appropriate response for the user, including the inventory status, based on acquired inventory information.

[0572] This invention is a system that provides quick and accurate responses to user inquiries. This system is particularly intended for inquiries regarding product inventory checks and purchase procedures on e-commerce websites, and is designed to improve user satisfaction and reduce operating costs. The following describes specific embodiments for implementing this invention.

[0573] The server utilizes technologies such as generative artificial intelligence (GPT-4), RESTful APIs, and mobile application frameworks (e.g., React Native). This system operates through an application installed on the user's smartphone.

[0574] When a user makes an inquiry via their smartphone, the following processes take place.

[0575] When a user submits an inquiry, it is first sent to the server. The server then passes this inquiry to a generative artificial intelligence (AI) for analysis. The AI ​​understands the intent and content of the inquiry, and based on the analysis results, it calls an API of an external system to obtain the necessary information.

[0576] For example, if a user sends a prompt such as "Do you have this item in stock? Item ID: 12345," the server analyzes this inquiry and calls an API of an external e-commerce platform to check the stock of the relevant item. Based on the stock information obtained from the API, generative artificial intelligence generates an answer for the user.

[0577] The generated responses are provided to the user in an easy-to-understand format. This process allows users to check inventory accurately and quickly, supporting their purchasing decisions.

[0578] This system can handle a wide range of complex inquiries and significantly improves the user experience, as demonstrated by the specific examples below.

[0579] Adding specific examples

[0580] Example of a prompt

[0581] 1. "Is this T-shirt in stock? Product ID: 98765"

[0582] 2. "Please leave a review for this product. Product ID: 12345"

[0583] 3. "Please tell me how to return this backpack."

[0584] By using these prompts, generative artificial intelligence can quickly generate and provide accurate answers to users. This allows users to obtain product information from the comfort of their homes, improving their online shopping experience.

[0585] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0586] Step 1:

[0587] A user makes an inquiry through a smartphone app. The user enters the prompt message "Is this product in stock? Product ID: 12345" and presses the submit button. The entered inquiry is sent from the device to the server. The input is the user's inquiry, and the output is the inquiry data received by the server.

[0588] Step 2:

[0589] The server sends the received inquiry data to a generative artificial intelligence (GPT-4). The generative AI analyzes the inquiry and determines its intent to be "check product inventory." Natural language processing is used for this analysis; the input is the inquiry data, and the output is the analysis result data.

[0590] Step 3:

[0591] The server calls an API of an external system based on the analysis results and sends a request to retrieve inventory information for the specified product ID. Here, an HTTP request is made to the API endpoint. The input is the analysis result data, and the output is the product inventory information returned from the API.

[0592] Step 4:

[0593] The server receives product inventory information returned from the API. This inventory information includes the availability status (in stock or out of stock) corresponding to the product ID. The input is the inventory information returned by the API, and the output is the storage of the inventory information within the server.

[0594] Step 5:

[0595] The server passes the acquired inventory information back to the generative artificial intelligence (AI) to generate a specific response to provide to the user. The generative AI generates a response such as, "The inventory for product ID: 12345 is AA." The input is inventory information, and the output is the generated specific response.

[0596] Step 6:

[0597] The server sends the generated response to the user's smartphone app. The device receives the response message and displays it to the user. The user can then view the response regarding the inventory status on their smartphone screen. The input is the generated response, and the output is the response message displayed to the user.

[0598] This processing flow allows users to quickly and accurately obtain product inventory information, supporting their purchasing decisions.

[0599] 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.

[0600] This invention provides a system that efficiently processes user inquiries and delivers quick and accurate responses by combining it with an emotion engine, thereby providing optimal responses tailored to the user's emotions. This system automates user support by linking generative artificial intelligence with APIs of external systems, reducing operational costs while achieving high user satisfaction that takes user emotions into consideration.

[0601] The system consists of the following main components:

[0602] 1. Means for receiving user inquiries

[0603] 2. Means of analyzing inquiries using generative artificial intelligence

[0604] 3. Means of obtaining information by calling an API of an external system

[0605] 4. Means by which generative artificial intelligence generates responses to users

[0606] 5. Means of providing the generated response to the user

[0607] 6. A means of using an emotion engine to recognize the emotions of users when receiving their inquiries.

[0608] 7. Means by which the emotion engine recognizes the user's emotions and provides additional contextual information to the generative artificial intelligence based on those emotions.

[0609] 8. Means for adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[0610] 9. A means by which the emotion engine analyzes not only the content of the inquiry but also the entire user interaction in order to regularly monitor the user's emotions.

[0611] To understand how this system works, the program's processing will be explained with concrete examples.

[0612] Specific example

[0613] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[0614] 1. Receiving a user inquiry

[0615] The user sends a message to the chatbot saying, "I want to add a new device."

[0616] The terminal (user's device) sends this message to the server.

[0617] 2. Emotion recognition by an emotion engine

[0618] The server sends the message received from the user to the emotion engine.

[0619] The emotion engine analyzes the message and recognizes the user's emotions (e.g., excitement, frustration, confusion, etc.).

[0620] 3. Analysis using generative artificial intelligence

[0621] The server sends the emotion recognition results from the emotion engine to the generative artificial intelligence.

[0622] The generative artificial intelligence analyzes the message and emotion recognition results to determine the user's intention is "procedures for adding a device."

[0623] 4. Information acquisition via API integration

[0624] Based on the analysis results, the server calls the API of the mobile device management system (MDM system) and sends a request to retrieve the necessary information.

[0625] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[0626] 5. Answer generation using generative artificial intelligence

[0627] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[0628] Generative artificial intelligence generates "specific steps for adding a device." These steps are generated with consideration for the user's emotions and tone. For example, if the user is frustrated, the explanation will be more detailed and polite.

[0629] 6. Providing responses to users

[0630] The server sends the generated response back to the user through the chatbot interface.

[0631] The user adds the device by following the instructions given by the chatbot.

[0632] This system allows users to receive instant, specific, and emotionally sensitive support. Furthermore, by combining generative artificial intelligence with an emotion engine, accuracy and efficiency are improved, leading to increased user satisfaction. This system will significantly contribute to reducing operational costs and streamlining customer support, particularly for medium and small businesses.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[0636] The terminal (user's device) sends this message to the server.

[0637] Step 2:

[0638] The server sends the message received from the user to the emotion engine.

[0639] The emotion engine analyzes messages and recognizes the user's emotions.

[0640] Step 3:

[0641] The emotion engine sends the analysis results back to the server. These results include information about the user's emotions (e.g., excitement, frustration, confusion).

[0642] Step 4:

[0643] The server sends the received emotion recognition results and the user's message to the generative artificial intelligence.

[0644] Based on this information, the generative artificial intelligence determines the user's intention to be "procedures for adding a device."

[0645] Step 5:

[0646] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[0647] API requests include user authentication information and associated device information.

[0648] Step 6:

[0649] The server sends the API request to the MDM system.

[0650] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[0651] The MDM system returns this information to the server as an API response.

[0652] Step 7:

[0653] The server receives a response from the MDM system and sends the acquired information and emotion recognition results back to the generative artificial intelligence.

[0654] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[0655] The generated instructions are adjusted in content and tone to take the user's emotions into consideration. For example, if the user is frustrated, a more detailed and polite explanation will be generated.

[0656] Step 8:

[0657] The server sends the generated response back to the user through the chatbot interface.

[0658] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[0659] Step 9 (Optional):

[0660] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[0661] Users provide feedback and contribute to improving the quality of the service.

[0662] (Example 2)

[0663] 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".

[0664] Traditional customer support systems suffered from problems such as insensitive responses to user emotions and cumbersome procedures, leading to decreased user satisfaction. In particular, the inability to appropriately understand user emotions resulted in a decline in response quality. Furthermore, while prompt and accurate responses to inquiries were required, efficient information gathering and appropriate response generation proved difficult.

[0665] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0666] In this invention, the server includes means for receiving user inquiries, means for transmitting the received inquiries to an emotion analysis engine and recognizing the user's emotions, means for transmitting the results of the emotion analysis engine to a generative artificial intelligence and analyzing the received inquiries, means for calling an API of an external system based on the analysis results to obtain necessary information, means for the generative artificial intelligence to generate a response to the user in an emotion-sensitive tone based on the acquired information, and means for providing the generated response to the user. This enables a rapid and accurate response that takes the user's emotions into consideration.

[0667] "Means for receiving user inquiries" refers to devices or systems for receiving inquiries sent by users via communication.

[0668] "A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions" refers to a device or system that sends the content of received inquiries to a program or device for performing emotion analysis, thereby identifying the user's emotional state.

[0669] "A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence and analyzing the received inquiry" refers to a program or device that transmits the results obtained from emotion analysis to a generative artificial intelligence and analyzes and understands the content of the inquiry.

[0670] "Means of calling an external system's API based on analysis results to obtain necessary information" refers to a program or device that operates an external system's API based on analysis results to obtain the necessary information.

[0671] "A means by which generative artificial intelligence generates responses to users in an emotionally sensitive tone based on acquired information" refers to a device or system in which generative artificial intelligence considers acquired information and the user's emotional state to create the optimal response, taking into account tone and content.

[0672] "Means of providing generated answers to users" refers to devices or systems that provide users with answers created by generative artificial intelligence.

[0673] This invention is a system for providing efficient and appropriate responses to user inquiries. This system utilizes generative artificial intelligence and an emotion analysis engine to generate quick and accurate answers while taking user emotions into consideration.

[0674] This system consists of several main components. Each component and its function are described below.

[0675] Hardware and software configuration

[0676] 1. Means for receiving user inquiries

[0677] This method typically includes web-based chatbot interfaces or mobile applications. The user's inquiry is sent to the server in real time.

[0678] 2. A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions.

[0679] The server sends the received query to the sentiment analysis engine. The sentiment analysis engine analyzes the emotions in the text using an emotion recognition API, such as Affectiva. This step determines whether the user is agitated, irritated, or confused.

[0680] 3. A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence system and analyzing the received inquiry.

[0681] The server sends the results obtained from the emotion analysis engine to a generative artificial intelligence (e.g., GPT-4). This generative AI analyzes the user's intent based on the inquiry content and emotion data.

[0682] 4. A means of obtaining necessary information by calling an API of an external system based on the analysis results.

[0683] Based on the analysis results, the server calls APIs of external systems (e.g., mobile device management systems) to collect necessary information. For example, it uses the Microsoft Intune API to obtain the current network configuration and necessary procedural information.

[0684] 5. A method by which a generative artificial intelligence generates responses to the user in an emotionally sensitive tone based on the acquired information.

[0685] The server retransmits the acquired information and sentiment analysis results to a generative artificial intelligence system to generate a response for the user. The generated response is crafted in a tone that takes the user's emotions into consideration. For example, if the user is irritated, the response will include a more polite and detailed explanation.

[0686] 6. Means of providing the generated response to the user

[0687] The server provides the generated response to the user through the chatbot interface. The user then solves the problem according to this response.

[0688] Examples of specific cases and prompt statements

[0689] Specific example

[0690] When a user wants to add a new device to the company network, the following steps are taken:

[0691] The user sends a message to the chatbot saying, "I want to add a new device."

[0692] The terminal (user's device) sends this message to the server.

[0693] The server sends the message to the sentiment analysis engine, which recognizes that the user is confused.

[0694] The server sends the results of the emotion analysis engine to a generative artificial intelligence (GPT-4) to determine the user's intent in the "device addition procedure".

[0695] The server calls the Microsoft Intune API to retrieve the necessary information.

[0696] Based on the acquired information and emotion recognition results, the server generates specific steps using generative artificial intelligence.

[0697] The server provides the generated instructions to the user via a chatbot, and the user adds the device by following the provided instructions.

[0698] Example of a prompt

[0699] "Please tell me how to add a new device to the company network."

[0700] "Please provide appropriate support procedures for when a user is confused."

[0701] This system allows users to receive efficient support and appropriate answers tailored to their inquiries. This improves user satisfaction and reduces the company's operating costs.

[0702] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0703] Step 1:

[0704] The user sends a message to the chatbot saying, "I want to add a new device."

[0705] Input: The message entered by the user into the chatbot.

[0706] Output: The message is sent from the terminal to the server.

[0707] Specific operation: When a user uses a device (e.g., a smartphone or computer) to type a message into the chatbot and presses the send button, the device sends this message to the server.

[0708] Step 2:

[0709] The server sends the received message to the sentiment analysis engine.

[0710] Input: Message received from the user.

[0711] Output: The message is passed to the sentiment analysis engine.

[0712] Specific operation: The server analyzes the received message, converts it to an appropriate format, and then sends it to the sentiment analysis engine. At this time, the text data is sent to the sentiment recognition API, and the analysis begins.

[0713] Step 3:

[0714] The emotion analysis engine analyzes the message and recognizes the user's emotions.

[0715] Input: The message text sent from the server.

[0716] Output: User emotion information (e.g., excitement, frustration, confusion, etc.).

[0717] Specific operation: The sentiment analysis engine analyzes the text and uses a language model to determine the user's emotions. The emotion recognition results are converted into a data format and sent back to the server.

[0718] Step 4:

[0719] The server transmits the emotion recognition results obtained from the emotion analysis engine to the generative artificial intelligence.

[0720] Input: User message and sentiment recognition result.

[0721] Output: Data sent to a generative artificial intelligence system as an analysis request.

[0722] Specific operation: The server converts the emotion recognition results into an appropriate format for sending to a generative artificial intelligence (e.g., GPT-4) and sends a request to the generative artificial intelligence.

[0723] Step 5:

[0724] Generative artificial intelligence analyzes user inquiries based on messages and emotion recognition results.

[0725] Input: User message and sentiment recognition result.

[0726] Output: Analysis results regarding user intent (e.g., "Steps to add a device").

[0727] Specific operation: Generative artificial intelligence uses natural language processing techniques to analyze messages and identify the user's intent. The analysis results are sent to the server as data.

[0728] Step 6:

[0729] Based on the analysis results, the server calls an API of an external system (e.g., a mobile device management system) to obtain the necessary information.

[0730] Input: Analysis results from a generative artificial intelligence.

[0731] Output: Information obtained from external systems (e.g., network configuration, procedure information).

[0732] Specific operation: The server creates an API request based on the analysis results of the generative artificial intelligence, and calls the appropriate external system's API to retrieve information. The retrieved information is stored on the server.

[0733] Step 7:

[0734] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[0735] Input: Acquired information and emotion recognition results.

[0736] Output: Detailed user instructions.

[0737] Specific operation: The server sends the acquired information and emotion recognition results to the generative artificial intelligence in an appropriate format and requests it to generate a response that takes the user's emotions into consideration.

[0738] Step 8:

[0739] Generative artificial intelligence generates "specific steps for adding a device."

[0740] Input: Acquired information and emotion recognition results.

[0741] Output: A detailed instruction manual provided to the user.

[0742] Specific operation: Generative artificial intelligence takes user emotions into consideration and generates detailed and careful instructions. For example, if the user is frustrated, the instructions will be provided in detail and with images.

[0743] Step 9:

[0744] The server responds to the user with the generated instructions through the chatbot interface.

[0745] Input: Specific instructions from a generative artificial intelligence.

[0746] Output: Instructional information provided to the user.

[0747] Specific operation: The server sends the generated instructions to the chatbot, which then displays them to the user. The user adds a device following the provided instructions.

[0748] (Application Example 2)

[0749] 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."

[0750] With the proliferation of autonomous vehicles, users are increasingly making real-time inquiries and giving instructions while driving. However, conventional systems provide uniform responses without considering user emotions, making it difficult to ensure user satisfaction and safety. In particular, in emergencies and high-stress situations where a quick and appropriate response is required, it is crucial to provide responses that are sensitive to the user's emotions.

[0751] 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.

[0752] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, means for utilizing an emotion engine to analyze the user's emotions, means for adjusting the content and tone of the answer based on the emotions recognized by the emotion engine, and means for processing user inquiries and instructions in real time while the autonomous vehicle is in operation. This enables quick and appropriate responses to inquiries that take into account the user's emotions, even while the autonomous vehicle is in operation.

[0753] "Means for receiving user inquiries" refers to the interface used to receive messages when a user sends voice or text messages to the system.

[0754] "Methods of using generative artificial intelligence to analyze received inquiries" refers to processes that use generative artificial intelligence to analyze messages received from users in order to understand the user's intent.

[0755] "A means of obtaining necessary information by calling an external system's API based on the analysis results" refers to the process of obtaining necessary data and information by calling an external system's API based on the results analyzed by generative artificial intelligence.

[0756] "A means by which generative artificial intelligence generates a response to the user based on acquired information" refers to the process by which generative artificial intelligence generates an appropriate response to the user based on information acquired from an external system.

[0757] "Means of providing generated answers to users" refers to an interface and processing method for presenting answers generated by generative artificial intelligence to users.

[0758] "Using an emotion engine to analyze user emotions" refers to a process that uses an engine to understand the user's emotional state based on the content of user inquiries and instructions.

[0759] "Means for adjusting the content and tone of responses based on emotions recognized by the emotion engine" refers to the process of appropriately adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[0760] "Means for processing user inquiries and instructions in real time while an autonomous vehicle is in operation" refers to a system and process that allows an autonomous vehicle to respond immediately to real-time inquiries and instructions from users while it is in operation.

[0761] Patent Specification

[0762] This invention is a system for efficiently and emotionally processing user inquiries and instructions in real time while an autonomous vehicle is in operation. Specifically, it receives user inquiries, analyzes the user's emotions using an emotion engine, and then uses generative artificial intelligence to generate and provide appropriate answers based on the results.

[0763] Hardware and software to be used

[0764] hardware

[0765] Smartphone: A device in which users input inquiries and instructions via voice or text.

[0766] Autonomous vehicles: Connect to a smartphone via Bluetooth or Wi-Fi and send driving information to a server.

[0767] Server: A central system for analysis and data processing.

[0768] software

[0769] Generative artificial intelligence: Software used to analyze user inquiries using natural language processing. (Examples: Google Cloud Natural Language API, IBM Watson)

[0770] Emotion engine: Software used to analyze user emotions. (Example: Amazon Comprehend)

[0771] API Integration Module: A library for calling APIs of external systems (e.g., mobile device management systems). (e.g., Requests library)

[0772] Program Processing Description

[0773] Recording and transmitting audio data

[0774] The user gives voice commands using their smartphone. The smartphone records the voice data and sends it to the server.

[0775] Emotional analysis using an emotion engine

[0776] The server passes the received audio data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions from the audio content and returns the result.

[0777] Response generation by generative artificial intelligence

[0778] The server passes the voice data, along with the results from the emotion engine, to the generative artificial intelligence (AI) to analyze the user's intent. The generative AI then generates an appropriate response based on the analysis results.

[0779] API integration and information retrieval

[0780] If necessary, the server calls APIs of external systems to obtain the data and information required for operation. The obtained information is passed to a generative artificial intelligence and used to generate the final answer.

[0781] Providing answers to users

[0782] The server sends the generated response back to the smartphone, providing it to the user. The user then decides on their next action based on that response.

[0783] Specific examples and prompt statements

[0784] Specific example

[0785] For example, consider a scenario where a user in an autonomous vehicle asks, "How long will it take to get to the next gas station?"

[0786] Voice: "How far is it to the next gas station?"

[0787] Prompt to the AI ​​engine: "User question: How long until the next gas station? User's mood: A little impatient."

[0788] This allows the system to provide responses that are appropriate to the user's emotions, enabling them to reach their destination comfortably and safely, even while driving autonomously.

[0789] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0790] Step 1: The user gives a voice command.

[0791] The user, while inside the autonomous vehicle, gives a voice command into their smartphone's microphone, such as, "How long will it take to get to the next gas station?" This voice data becomes the input.

[0792] Step 2: The device records the audio data.

[0793] The device (smartphone) records the user's voice and saves it as an audio file in its internal data. The output obtained here is an audio file.

[0794] Step 3: The device sends the audio data to the server.

[0795] The terminal sends the recorded audio file to the server. In this step, the terminal takes an audio file as input and performs the procedure (communication processing) to send it to the server. The output is the audio data stored on the server.

[0796] Step 4: The server passes the voice data to the emotion engine.

[0797] The server inputs the received audio data into the emotion engine, which analyzes the user's emotions. The emotion engine then outputs text data and emotion recognition results based on the audio data.

[0798] Step 5: The server passes the emotion analysis results to the generative artificial intelligence.

[0799] The server passes the speech text data, along with the emotion recognition results from the emotion engine, to the generative artificial intelligence. The generative AI takes this as input, analyzes the user's intent, and generates an appropriate response. The generated response becomes the output.

[0800] Step 6: The server calls the API to retrieve the necessary information.

[0801] Based on the analysis results, the server calls APIs of external systems such as mobile device management systems to obtain necessary information (for example, the location information of nearby gas stations). The API calls are the input, and the information obtained from the external systems is the output.

[0802] Step 7: The server generates the final answer.

[0803] The server then passes the acquired information and emotion analysis results back to the generative artificial intelligence to generate the final response. Based on this, the generative AI outputs the optimal response that takes the user's emotions into consideration.

[0804] Step 8: The server provides the answer to the user.

[0805] The server sends the generated response to the terminal (smartphone) and provides it to the user. In this step, the server takes the generated response as input and sends it to the user's terminal as output. The user receives the response and decides on their next action.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] [Third Embodiment]

[0810] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0811] 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.

[0812] 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).

[0813] 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.

[0814] 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.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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".

[0822] This invention provides a system that efficiently processes user inquiries and provides quick and accurate responses. By linking generative artificial intelligence with APIs of external systems, this system automates user support, reduces operating costs, and improves user satisfaction.

[0823] The system consists of the following main components:

[0824] 1. Means for receiving user inquiries

[0825] 2. Means of analyzing inquiries using generative artificial intelligence

[0826] 3. Means of obtaining information by calling an API of an external system

[0827] 4. Means by which generative artificial intelligence generates responses to users

[0828] 5. Means of providing the generated response to the user

[0829] To understand how this system works, the program's processing will be explained with concrete examples.

[0830] Specific example

[0831] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[0832] 1. Receiving a user inquiry

[0833] The user sends a message to the chatbot saying, "I want to add a new device."

[0834] The terminal (user's device) sends this message to the server.

[0835] The server receives the message and begins processing it.

[0836] 2. Analysis using generative artificial intelligence

[0837] The server sends the received message to a generative artificial intelligence (e.g., GPT-4).

[0838] The generative artificial intelligence analyzes the message and determines its intent to be "instructions for adding a device."

[0839] 3. Information acquisition via API integration

[0840] Based on the analysis results, the server calls the mobile device management system's API and sends a request to retrieve the necessary information.

[0841] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[0842] 4. Answer generation using generative artificial intelligence

[0843] The server passes the acquired information to a generative artificial intelligence system and requests it to generate specific steps that the user should take.

[0844] Generative artificial intelligence generates "specific steps for adding a device."

[0845] For example, the instructions might say, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0846] 5. Providing responses to users

[0847] The server sends the generated response to the user via the chatbot.

[0848] The user follows the instructions from the chatbot to add the device.

[0849] This system allows users to receive instant, specific support. Furthermore, by combining generative artificial intelligence with external system APIs, accuracy and efficiency are improved, and operating costs are reduced. This system will significantly contribute to reducing operating costs and streamlining customer support, particularly for medium and small businesses.

[0850] The following describes the processing flow.

[0851] Step 1:

[0852] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[0853] The terminal (user's device) sends this message to the server.

[0854] Step 2:

[0855] The server sends the message received from the user to a generative artificial intelligence. For example, GPT-4 is used as the generative AI.

[0856] The generative artificial intelligence analyzes the message and determines the user's intent to be "procedures for adding a device."

[0857] Step 3:

[0858] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[0859] The server includes user authentication information and related device information in the API request.

[0860] Step 4:

[0861] The server sends the API request to the MDM system.

[0862] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[0863] The MDM system returns this information to the server as an API response.

[0864] Step 5:

[0865] The server receives a response from the MDM system and resends the acquired information to the generative artificial intelligence.

[0866] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[0867] Step 6:

[0868] The server receives the response generated by the generative artificial intelligence and responds to the user through the chatbot interface.

[0869] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[0870] Step 7 (Optional):

[0871] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[0872] Users provide feedback and contribute to improving the quality of the service.

[0873] (Example 1)

[0874] 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."

[0875] Conventional user support systems suffer from problems such as delayed and inaccurate responses to user inquiries. Furthermore, manual support is costly to operate, especially for small and medium-sized enterprises. This invention aims to solve these problems, improve user satisfaction, and reduce operating costs.

[0876] 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.

[0877] In this invention, the server includes means for receiving user inquiries, means for registering the received inquiries in a message queue, means for requesting a generative artificial intelligence to analyze the messages, means for the generative artificial intelligence to call an API of an external system to obtain necessary information based on the analysis results, means for requesting the generative artificial intelligence to analyze the obtained information again to generate a response to the user, and means for providing the generated response to the user. This enables a rapid and accurate response to user inquiries, resulting in reduced operating costs and improved user satisfaction.

[0878] A "user" refers to a person who makes a request to the system.

[0879] An "inquiry" refers to a question or request that a user sends to a system.

[0880] "Means of receiving" refers to the function that allows the server to receive inquiries sent by users.

[0881] A "message queue" refers to a data structure used to temporarily store received inquiries and process them in order.

[0882] "Generative artificial intelligence" refers to artificial intelligence technologies (such as natural language processing technologies) that analyze received inquiries and understand their intent.

[0883] "Means of analysis" refers to a function that uses generative artificial intelligence to analyze the content of received inquiries and identify their intent and requirements.

[0884] "External systems" refer to third-party systems or services that the server uses to acquire information in cooperation with it.

[0885] An "API" refers to an application programming interface provided by an external system, offering a method for a server to communicate with that external system.

[0886] "Means of acquiring information" refers to the function of acquiring necessary information from external systems via APIs based on the analysis results of generative artificial intelligence.

[0887] "Means for generating answers" refers to a function that allows a generative artificial intelligence to generate specific answers for the user based on the acquired information.

[0888] "Means of delivery" refers to functions for communicating generated responses to users through chatbots or similar means.

[0889] This invention is a system that efficiently processes user inquiries and provides quick and accurate answers. By linking generative artificial intelligence with APIs of external systems, the system automates user support, reduces operating costs, and improves user satisfaction.

[0890] The system consists of the following main hardware and software components:

[0891] 1. A means of receiving user inquiries (e.g., a chatbot)

[0892] 2. Methods for analyzing queries using generative artificial intelligence (e.g., GPT-4)

[0893] 3. Means of obtaining information by calling APIs of external systems (e.g., APIs of mobile device management systems (MDM))

[0894] 4. Means by which generative artificial intelligence generates responses to users

[0895] 5. Means of providing the generated response to the user

[0896] The following describes the specific processing steps of this system's program.

[0897] 1. Receiving a user inquiry

[0898] The user sends a message to the chatbot saying, "I want to add a new device." The user's device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0899] 2. Analysis using generative artificial intelligence

[0900] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent as "device addition procedure."

[0901] 3. Information acquisition via API integration

[0902] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0903] 4. Answer generation using generative artificial intelligence

[0904] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI generates "specific steps for adding a device." For example, it might show steps such as, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0905] 5. Providing responses to users

[0906] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a new device to the network.

[0907] Specific example

[0908] When a user wants to add a new device to the company network, the following prompt is entered into the generative artificial intelligence.

[0909] Example of a prompt:

[0910] "Please tell me how to add a new device to the company network."

[0911] The generative artificial intelligence generates instructions based on this prompt, and these instructions are provided to the user from the server via a chatbot. This process allows the user to quickly receive specific instructions and add devices. This system will greatly contribute to reducing operational costs and improving the efficiency of customer support, especially for small and medium-sized enterprises.

[0912] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0913] The processing flow of this system's program

[0914] Step 1:

[0915] The user enters and sends the message "I want to add a new device" to the chatbot. The device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[0916] Input: User inquiry message

[0917] Output: Registered to message queue

[0918] Specific actions:

[0919] The user enters a message using the chatbot and clicks the "Send" button.

[0920] The device sends a message to the server using an HTTP POST request.

[0921] The server receives the message and stores it in the message queue.

[0922] Step 2:

[0923] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent to be "device addition instructions."

[0924] Input: User inquiry retrieved from the message queue

[0925] Output: Analysis results (for example, the intent behind "Procedure for adding a device")

[0926] Specific actions:

[0927] The server retrieves the message from the queue.

[0928] The server sends a request to GPT-4 using a pre-configured prompt.

[0929] GPT-4 analyzes the message and identifies its intent.

[0930] Step 3:

[0931] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[0932] Input: Request to retrieve information based on analysis results

[0933] Output: Network configuration information and procedure information from the MDM system.

[0934] Specific actions:

[0935] The server generates an HTTP request and sends it to a specific endpoint in the MDM system.

[0936] The MDM system receives the request and returns network configuration information to the server as a response.

[0937] Step 4:

[0938] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI then generates "specific steps for adding a device."

[0939] Input: Network configuration information and procedure information obtained from the API.

[0940] Output: Specific steps the user should take

[0941] Specific actions:

[0942] The server includes the information it has obtained in the prompt message and passes it to GPT-4.

[0943] GPT-4 generates specific procedures based on this information.

[0944] For example: "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[0945] Step 5:

[0946] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a device.

[0947] Input: Generated specific steps

[0948] Output: Displayed as a response to the user

[0949] Specific actions:

[0950] The server sends the generated steps to the chatbot's API, which then displays them in the user's chat window.

[0951] The user adds a device by following the instructions: "Log in to the XX portal and click the 'Add New Device' button."

[0952] In this way, by performing the necessary data processing and calculations at each step, we can respond quickly and accurately to user inquiries.

[0953] (Application Example 1)

[0954] 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."

[0955] Responding to user inquiries on modern e-commerce sites is often time-consuming and labor-intensive, leading to decreased user satisfaction and increased operational costs. Furthermore, there is a demand for quick and accurate responses to frequent inquiries such as inventory checks and purchase procedures. Traditional systems have struggled to efficiently address these challenges.

[0956] 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.

[0957] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, and, if the user's inquiry concerns checking product inventory or purchasing procedures, means for obtaining inventory information of the relevant product through an API of an external system and for the generative artificial intelligence to generate an answer including the inventory status of the relevant product. As a result, users can receive quick and accurate support, reducing operating costs and improving user satisfaction.

[0958] "Means for receiving user inquiries" refers to an interface for receiving questions and requests that users make to the system.

[0959] "Methods of utilizing generative artificial intelligence" refers to the process of using generative artificial intelligence to analyze user inquiries and understand their intent and content.

[0960] "A means of obtaining necessary information by calling an external system's API" refers to the process of using an external information system's API based on the analysis results to retrieve data and information related to the inquiry.

[0961] "A means by which generative artificial intelligence generates responses to users" refers to the process by which generative artificial intelligence creates appropriate responses to user inquiries based on acquired information.

[0962] "Means of providing generated answers to users" refers to an interface for conveying answers and information generated by generative artificial intelligence to users.

[0963] "Inquiries regarding product stock availability and purchase procedures" refer to inquiries from users asking about the stock status of a specific product or seeking information on how to purchase it.

[0964] "Means of obtaining inventory information for the relevant product through an external system's API" refers to the process of obtaining inventory data for a specific product from an external system using an API.

[0965] "Means for generating a response that includes the inventory status of the relevant product" refers to a process for generating an appropriate response for the user, including the inventory status, based on acquired inventory information.

[0966] This invention is a system that provides quick and accurate responses to user inquiries. This system is particularly intended for inquiries regarding product inventory checks and purchase procedures on e-commerce websites, and is designed to improve user satisfaction and reduce operating costs. The following describes specific embodiments for implementing this invention.

[0967] The server utilizes technologies such as generative artificial intelligence (GPT-4), RESTful APIs, and mobile application frameworks (e.g., React Native). This system operates through an application installed on the user's smartphone.

[0968] When a user makes an inquiry via their smartphone, the following processes take place.

[0969] When a user submits an inquiry, it is first sent to the server. The server then passes this inquiry to a generative artificial intelligence (AI) for analysis. The AI ​​understands the intent and content of the inquiry, and based on the analysis results, it calls an API of an external system to obtain the necessary information.

[0970] For example, if a user sends a prompt such as "Do you have this item in stock? Item ID: 12345," the server analyzes this inquiry and calls an API of an external e-commerce platform to check the stock of the relevant item. Based on the stock information obtained from the API, generative artificial intelligence generates an answer for the user.

[0971] The generated responses are provided to the user in an easy-to-understand format. This process allows users to check inventory accurately and quickly, supporting their purchasing decisions.

[0972] This system can handle a wide range of complex inquiries and significantly improves the user experience, as demonstrated by the specific examples below.

[0973] Adding specific examples

[0974] Example of a prompt

[0975] 1. "Is this T-shirt in stock? Product ID: 98765"

[0976] 2. "Please leave a review for this product. Product ID: 12345"

[0977] 3. "Please tell me how to return this backpack."

[0978] By using these prompts, generative artificial intelligence can quickly generate and provide accurate answers to users. This allows users to obtain product information from the comfort of their homes, improving their online shopping experience.

[0979] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0980] Step 1:

[0981] A user makes an inquiry through a smartphone app. The user enters the prompt message "Is this product in stock? Product ID: 12345" and presses the submit button. The entered inquiry is sent from the device to the server. The input is the user's inquiry, and the output is the inquiry data received by the server.

[0982] Step 2:

[0983] The server sends the received inquiry data to a generative artificial intelligence (GPT-4). The generative AI analyzes the inquiry and determines its intent to be "check product inventory." Natural language processing is used for this analysis; the input is the inquiry data, and the output is the analysis result data.

[0984] Step 3:

[0985] The server calls an API of an external system based on the analysis results and sends a request to retrieve inventory information for the specified product ID. Here, an HTTP request is made to the API endpoint. The input is the analysis result data, and the output is the product inventory information returned from the API.

[0986] Step 4:

[0987] The server receives product inventory information returned from the API. This inventory information includes the availability status (in stock or out of stock) corresponding to the product ID. The input is the inventory information returned by the API, and the output is the storage of the inventory information within the server.

[0988] Step 5:

[0989] The server passes the acquired inventory information back to the generative artificial intelligence (AI) to generate a specific response to provide to the user. The generative AI generates a response such as, "The inventory for product ID: 12345 is AA." The input is inventory information, and the output is the generated specific response.

[0990] Step 6:

[0991] The server sends the generated response to the user's smartphone app. The device receives the response message and displays it to the user. The user can then view the response regarding the inventory status on their smartphone screen. The input is the generated response, and the output is the response message displayed to the user.

[0992] This processing flow allows users to quickly and accurately obtain product inventory information, supporting their purchasing decisions.

[0993] 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.

[0994] This invention provides a system that efficiently processes user inquiries and delivers quick and accurate responses by combining it with an emotion engine, thereby providing optimal responses tailored to the user's emotions. This system automates user support by linking generative artificial intelligence with APIs of external systems, reducing operational costs while achieving high user satisfaction that takes user emotions into consideration.

[0995] The system consists of the following main components:

[0996] 1. Means for receiving user inquiries

[0997] 2. Means of analyzing inquiries using generative artificial intelligence

[0998] 3. Means of obtaining information by calling an API of an external system

[0999] 4. Means by which generative artificial intelligence generates responses to users

[1000] 5. Means of providing the generated response to the user

[1001] 6. A means of using an emotion engine to recognize the emotions of users when receiving their inquiries.

[1002] 7. Means by which the emotion engine recognizes the user's emotions and provides additional contextual information to the generative artificial intelligence based on those emotions.

[1003] 8. Means for adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[1004] 9. A means by which the emotion engine analyzes not only the content of the inquiry but also the entire user interaction in order to regularly monitor the user's emotions.

[1005] To understand how this system works, the program's processing will be explained with concrete examples.

[1006] Specific example

[1007] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[1008] 1. Receiving a user inquiry

[1009] The user sends a message to the chatbot saying, "I want to add a new device."

[1010] The terminal (user's device) sends this message to the server.

[1011] 2. Emotion recognition by an emotion engine

[1012] The server sends the message received from the user to the emotion engine.

[1013] The emotion engine analyzes the message and recognizes the user's emotions (e.g., excitement, frustration, confusion, etc.).

[1014] 3. Analysis using generative artificial intelligence

[1015] The server sends the emotion recognition results from the emotion engine to the generative artificial intelligence.

[1016] The generative artificial intelligence analyzes the message and emotion recognition results to determine the user's intention is "procedures for adding a device."

[1017] 4. Information acquisition via API integration

[1018] Based on the analysis results, the server calls the API of the mobile device management system (MDM system) and sends a request to retrieve the necessary information.

[1019] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[1020] 5. Answer generation using generative artificial intelligence

[1021] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[1022] Generative artificial intelligence generates "specific steps for adding a device." These steps are generated with consideration for the user's emotions and tone. For example, if the user is frustrated, the explanation will be more detailed and polite.

[1023] 6. Providing responses to users

[1024] The server sends the generated response back to the user through the chatbot interface.

[1025] The user adds the device by following the instructions given by the chatbot.

[1026] This system allows users to receive instant, specific, and emotionally sensitive support. Furthermore, by combining generative artificial intelligence with an emotion engine, accuracy and efficiency are improved, leading to increased user satisfaction. This system will significantly contribute to reducing operational costs and streamlining customer support, particularly for medium and small businesses.

[1027] The following describes the processing flow.

[1028] Step 1:

[1029] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[1030] The terminal (user's device) sends this message to the server.

[1031] Step 2:

[1032] The server sends the message received from the user to the emotion engine.

[1033] The emotion engine analyzes messages and recognizes the user's emotions.

[1034] Step 3:

[1035] The emotion engine sends the analysis results back to the server. These results include information about the user's emotions (e.g., excitement, frustration, confusion).

[1036] Step 4:

[1037] The server sends the received emotion recognition results and the user's message to the generative artificial intelligence.

[1038] Based on this information, the generative artificial intelligence determines the user's intention to be "procedures for adding a device."

[1039] Step 5:

[1040] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[1041] API requests include user authentication information and associated device information.

[1042] Step 6:

[1043] The server sends the API request to the MDM system.

[1044] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[1045] The MDM system returns this information to the server as an API response.

[1046] Step 7:

[1047] The server receives a response from the MDM system and sends the acquired information and emotion recognition results back to the generative artificial intelligence.

[1048] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[1049] The generated instructions are adjusted in content and tone to take the user's emotions into consideration. For example, if the user is frustrated, a more detailed and polite explanation will be generated.

[1050] Step 8:

[1051] The server sends the generated response back to the user through the chatbot interface.

[1052] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[1053] Step 9 (Optional):

[1054] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[1055] Users provide feedback and contribute to improving the quality of the service.

[1056] (Example 2)

[1057] 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."

[1058] Traditional customer support systems suffered from problems such as insensitive responses to user emotions and cumbersome procedures, leading to decreased user satisfaction. In particular, the inability to appropriately understand user emotions resulted in a decline in response quality. Furthermore, while prompt and accurate responses to inquiries were required, efficient information gathering and appropriate response generation proved difficult.

[1059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1060] In this invention, the server includes means for receiving user inquiries, means for transmitting the received inquiries to an emotion analysis engine and recognizing the user's emotions, means for transmitting the results of the emotion analysis engine to a generative artificial intelligence and analyzing the received inquiries, means for calling an API of an external system based on the analysis results to obtain necessary information, means for the generative artificial intelligence to generate a response to the user in an emotion-sensitive tone based on the acquired information, and means for providing the generated response to the user. This enables a rapid and accurate response that takes the user's emotions into consideration.

[1061] "Means for receiving user inquiries" refers to devices or systems for receiving inquiries sent by users via communication.

[1062] "A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions" refers to a device or system that sends the content of received inquiries to a program or device for performing emotion analysis, thereby identifying the user's emotional state.

[1063] "A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence and analyzing the received inquiry" refers to a program or device that transmits the results obtained from emotion analysis to a generative artificial intelligence and analyzes and understands the content of the inquiry.

[1064] "Means of calling an external system's API based on analysis results to obtain necessary information" refers to a program or device that operates an external system's API based on analysis results to obtain the necessary information.

[1065] "A means by which generative artificial intelligence generates responses to users in an emotionally sensitive tone based on acquired information" refers to a device or system in which generative artificial intelligence considers acquired information and the user's emotional state to create the optimal response, taking into account tone and content.

[1066] "Means of providing generated answers to users" refers to devices or systems that provide users with answers created by generative artificial intelligence.

[1067] This invention is a system for providing efficient and appropriate responses to user inquiries. This system utilizes generative artificial intelligence and an emotion analysis engine to generate quick and accurate answers while taking user emotions into consideration.

[1068] This system consists of several main components. Each component and its function are described below.

[1069] Hardware and software configuration

[1070] 1. Means for receiving user inquiries

[1071] This method typically includes web-based chatbot interfaces or mobile applications. The user's inquiry is sent to the server in real time.

[1072] 2. A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions.

[1073] The server sends the received query to the sentiment analysis engine. The sentiment analysis engine analyzes the emotions in the text using an emotion recognition API, such as Affectiva. This step determines whether the user is agitated, irritated, or confused.

[1074] 3. A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence system and analyzing the received inquiry.

[1075] The server sends the results obtained from the emotion analysis engine to a generative artificial intelligence (e.g., GPT-4). This generative AI analyzes the user's intent based on the inquiry content and emotion data.

[1076] 4. A means of obtaining necessary information by calling an API of an external system based on the analysis results.

[1077] Based on the analysis results, the server calls APIs of external systems (e.g., mobile device management systems) to collect necessary information. For example, it uses the Microsoft Intune API to obtain the current network configuration and necessary procedural information.

[1078] 5. A method by which a generative artificial intelligence generates responses to the user in an emotionally sensitive tone based on the acquired information.

[1079] The server retransmits the acquired information and sentiment analysis results to a generative artificial intelligence system to generate a response for the user. The generated response is crafted in a tone that takes the user's emotions into consideration. For example, if the user is irritated, the response will include a more polite and detailed explanation.

[1080] 6. Means of providing the generated response to the user

[1081] The server provides the generated response to the user through the chatbot interface. The user then solves the problem according to this response.

[1082] Examples of specific cases and prompt statements

[1083] Specific example

[1084] When a user wants to add a new device to the company network, the following steps are taken:

[1085] The user sends a message to the chatbot saying, "I want to add a new device."

[1086] The terminal (user's device) sends this message to the server.

[1087] The server sends the message to the sentiment analysis engine, which recognizes that the user is confused.

[1088] The server sends the results of the emotion analysis engine to a generative artificial intelligence (GPT-4) to determine the user's intent in the "device addition procedure".

[1089] The server calls the Microsoft Intune API to retrieve the necessary information.

[1090] Based on the acquired information and emotion recognition results, the server generates specific steps using generative artificial intelligence.

[1091] The server provides the generated instructions to the user via a chatbot, and the user adds the device by following the provided instructions.

[1092] Example of a prompt

[1093] "Please tell me how to add a new device to the company network."

[1094] "Please provide appropriate support procedures for when a user is confused."

[1095] This system allows users to receive efficient support and appropriate answers tailored to their inquiries. This improves user satisfaction and reduces the company's operating costs.

[1096] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1097] Step 1:

[1098] The user sends a message to the chatbot saying, "I want to add a new device."

[1099] Input: The message entered by the user into the chatbot.

[1100] Output: The message is sent from the terminal to the server.

[1101] Specific operation: When a user uses a device (e.g., a smartphone or computer) to type a message into the chatbot and presses the send button, the device sends this message to the server.

[1102] Step 2:

[1103] The server sends the received message to the sentiment analysis engine.

[1104] Input: Message received from the user.

[1105] Output: The message is passed to the sentiment analysis engine.

[1106] Specific operation: The server analyzes the received message, converts it to an appropriate format, and then sends it to the sentiment analysis engine. At this time, the text data is sent to the sentiment recognition API, and the analysis begins.

[1107] Step 3:

[1108] The emotion analysis engine analyzes the message and recognizes the user's emotions.

[1109] Input: The message text sent from the server.

[1110] Output: User emotion information (e.g., excitement, frustration, confusion, etc.).

[1111] Specific operation: The sentiment analysis engine analyzes the text and uses a language model to determine the user's emotions. The emotion recognition results are converted into a data format and sent back to the server.

[1112] Step 4:

[1113] The server transmits the emotion recognition results obtained from the emotion analysis engine to the generative artificial intelligence.

[1114] Input: User message and sentiment recognition result.

[1115] Output: Data sent to a generative artificial intelligence system as an analysis request.

[1116] Specific operation: The server converts the emotion recognition results into an appropriate format for sending to a generative artificial intelligence (e.g., GPT-4) and sends a request to the generative artificial intelligence.

[1117] Step 5:

[1118] Generative artificial intelligence analyzes user inquiries based on messages and emotion recognition results.

[1119] Input: User message and sentiment recognition result.

[1120] Output: Analysis results regarding user intent (e.g., "Steps to add a device").

[1121] Specific operation: Generative artificial intelligence uses natural language processing techniques to analyze messages and identify the user's intent. The analysis results are sent to the server as data.

[1122] Step 6:

[1123] Based on the analysis results, the server calls an API of an external system (e.g., a mobile device management system) to obtain the necessary information.

[1124] Input: Analysis results from a generative artificial intelligence.

[1125] Output: Information obtained from external systems (e.g., network configuration, procedure information).

[1126] Specific operation: The server creates an API request based on the analysis results of the generative artificial intelligence, and calls the appropriate external system's API to retrieve information. The retrieved information is stored on the server.

[1127] Step 7:

[1128] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[1129] Input: Acquired information and emotion recognition results.

[1130] Output: Detailed user instructions.

[1131] Specific operation: The server sends the acquired information and emotion recognition results to the generative artificial intelligence in an appropriate format and requests it to generate a response that takes the user's emotions into consideration.

[1132] Step 8:

[1133] Generative artificial intelligence generates "specific steps for adding a device."

[1134] Input: Acquired information and emotion recognition results.

[1135] Output: A detailed instruction manual provided to the user.

[1136] Specific operation: Generative artificial intelligence takes user emotions into consideration and generates detailed and careful instructions. For example, if the user is frustrated, the instructions will be provided in detail and with images.

[1137] Step 9:

[1138] The server responds to the user with the generated instructions through the chatbot interface.

[1139] Input: Specific instructions from a generative artificial intelligence.

[1140] Output: Instructional information provided to the user.

[1141] Specific operation: The server sends the generated instructions to the chatbot, which then displays them to the user. The user adds a device following the provided instructions.

[1142] (Application Example 2)

[1143] 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."

[1144] With the proliferation of autonomous vehicles, users are increasingly making real-time inquiries and giving instructions while driving. However, conventional systems provide uniform responses without considering user emotions, making it difficult to ensure user satisfaction and safety. In particular, in emergencies and high-stress situations where a quick and appropriate response is required, it is crucial to provide responses that are sensitive to the user's emotions.

[1145] 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.

[1146] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, means for utilizing an emotion engine to analyze the user's emotions, means for adjusting the content and tone of the answer based on the emotions recognized by the emotion engine, and means for processing user inquiries and instructions in real time while the autonomous vehicle is in operation. This enables quick and appropriate responses to inquiries that take into account the user's emotions, even while the autonomous vehicle is in operation.

[1147] "Means for receiving user inquiries" refers to the interface used to receive messages when a user sends voice or text messages to the system.

[1148] "Methods of using generative artificial intelligence to analyze received inquiries" refers to processes that use generative artificial intelligence to analyze messages received from users in order to understand the user's intent.

[1149] "A means of obtaining necessary information by calling an external system's API based on the analysis results" refers to the process of obtaining necessary data and information by calling an external system's API based on the results analyzed by generative artificial intelligence.

[1150] "A means by which generative artificial intelligence generates a response to the user based on acquired information" refers to the process by which generative artificial intelligence generates an appropriate response to the user based on information acquired from an external system.

[1151] "Means of providing generated answers to users" refers to an interface and processing method for presenting answers generated by generative artificial intelligence to users.

[1152] "Using an emotion engine to analyze user emotions" refers to a process that uses an engine to understand the user's emotional state based on the content of user inquiries and instructions.

[1153] "Means for adjusting the content and tone of responses based on emotions recognized by the emotion engine" refers to the process of appropriately adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[1154] "Means for processing user inquiries and instructions in real time while an autonomous vehicle is in operation" refers to a system and process that allows an autonomous vehicle to respond immediately to real-time inquiries and instructions from users while it is in operation.

[1155] Patent Specification

[1156] This invention is a system for efficiently and emotionally processing user inquiries and instructions in real time while an autonomous vehicle is in operation. Specifically, it receives user inquiries, analyzes the user's emotions using an emotion engine, and then uses generative artificial intelligence to generate and provide appropriate answers based on the results.

[1157] Hardware and software to be used

[1158] hardware

[1159] Smartphone: A device in which users input inquiries and instructions via voice or text.

[1160] Autonomous vehicles: Connect to a smartphone via Bluetooth or Wi-Fi and send driving information to a server.

[1161] Server: A central system for analysis and data processing.

[1162] software

[1163] Generative artificial intelligence: Software used to analyze user inquiries using natural language processing. (Examples: Google Cloud Natural Language API, IBM Watson)

[1164] Emotion engine: Software used to analyze user emotions. (Example: Amazon Comprehend)

[1165] API Integration Module: A library for calling APIs of external systems (e.g., mobile device management systems). (e.g., Requests library)

[1166] Program Processing Description

[1167] Recording and transmitting audio data

[1168] The user gives voice commands using their smartphone. The smartphone records the voice data and sends it to the server.

[1169] Emotional analysis using an emotion engine

[1170] The server passes the received audio data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions from the audio content and returns the result.

[1171] Response generation by generative artificial intelligence

[1172] The server passes the voice data, along with the results from the emotion engine, to the generative artificial intelligence (AI) to analyze the user's intent. The generative AI then generates an appropriate response based on the analysis results.

[1173] API integration and information retrieval

[1174] If necessary, the server calls APIs of external systems to obtain the data and information required for operation. The obtained information is passed to a generative artificial intelligence and used to generate the final answer.

[1175] Providing answers to users

[1176] The server sends the generated response back to the smartphone, providing it to the user. The user then decides on their next action based on that response.

[1177] Specific examples and prompt statements

[1178] Specific example

[1179] For example, consider a scenario where a user in an autonomous vehicle asks, "How long will it take to get to the next gas station?"

[1180] Voice: "How far is it to the next gas station?"

[1181] Prompt to the AI ​​engine: "User question: How long until the next gas station? User's mood: A little impatient."

[1182] This allows the system to provide responses that are appropriate to the user's emotions, enabling them to reach their destination comfortably and safely, even while driving autonomously.

[1183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1184] Step 1: The user gives a voice command.

[1185] The user, while inside the autonomous vehicle, gives a voice command into their smartphone's microphone, such as, "How long will it take to get to the next gas station?" This voice data becomes the input.

[1186] Step 2: The device records the audio data.

[1187] The device (smartphone) records the user's voice and saves it as an audio file in its internal data. The output obtained here is an audio file.

[1188] Step 3: The device sends the audio data to the server.

[1189] The terminal sends the recorded audio file to the server. In this step, the terminal takes an audio file as input and performs the procedure (communication processing) to send it to the server. The output is the audio data stored on the server.

[1190] Step 4: The server passes the voice data to the emotion engine.

[1191] The server inputs the received audio data into the emotion engine, which analyzes the user's emotions. The emotion engine then outputs text data and emotion recognition results based on the audio data.

[1192] Step 5: The server passes the emotion analysis results to the generative artificial intelligence.

[1193] The server passes the speech text data, along with the emotion recognition results from the emotion engine, to the generative artificial intelligence. The generative AI takes this as input, analyzes the user's intent, and generates an appropriate response. The generated response becomes the output.

[1194] Step 6: The server calls the API to retrieve the necessary information.

[1195] Based on the analysis results, the server calls APIs of external systems such as mobile device management systems to obtain necessary information (for example, the location information of nearby gas stations). The API calls are the input, and the information obtained from the external systems is the output.

[1196] Step 7: The server generates the final answer.

[1197] The server then passes the acquired information and emotion analysis results back to the generative artificial intelligence to generate the final response. Based on this, the generative AI outputs the optimal response that takes the user's emotions into consideration.

[1198] Step 8: The server provides the answer to the user.

[1199] The server sends the generated response to the terminal (smartphone) and provides it to the user. In this step, the server takes the generated response as input and sends it to the user's terminal as output. The user receives the response and decides on their next action.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] [Fourth Embodiment]

[1204] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1205] 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.

[1206] 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).

[1207] 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.

[1208] 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.

[1209] 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).

[1210] 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.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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".

[1217] This invention provides a system that efficiently processes user inquiries and provides quick and accurate responses. By linking generative artificial intelligence with APIs of external systems, this system automates user support, reduces operating costs, and improves user satisfaction.

[1218] The system consists of the following main components:

[1219] 1. Means for receiving user inquiries

[1220] 2. Means of analyzing inquiries using generative artificial intelligence

[1221] 3. Means of obtaining information by calling an API of an external system

[1222] 4. Means by which generative artificial intelligence generates responses to users

[1223] 5. Means of providing the generated response to the user

[1224] To understand how this system works, the program's processing will be explained with concrete examples.

[1225] Specific example

[1226] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[1227] 1. Receiving a user inquiry

[1228] The user sends a message to the chatbot saying, "I want to add a new device."

[1229] The terminal (user's device) sends this message to the server.

[1230] The server receives the message and begins processing it.

[1231] 2. Analysis using generative artificial intelligence

[1232] The server sends the received message to a generative artificial intelligence (e.g., GPT-4).

[1233] The generative artificial intelligence analyzes the message and determines its intent to be "instructions for adding a device."

[1234] 3. Information acquisition via API integration

[1235] Based on the analysis results, the server calls the mobile device management system's API and sends a request to retrieve the necessary information.

[1236] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[1237] 4. Answer generation using generative artificial intelligence

[1238] The server passes the acquired information to a generative artificial intelligence system and requests it to generate specific steps that the user should take.

[1239] Generative artificial intelligence generates "specific steps for adding a device."

[1240] For example, the instructions might say, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[1241] 5. Providing responses to users

[1242] The server sends the generated response to the user via the chatbot.

[1243] The user follows the instructions from the chatbot to add the device.

[1244] This system allows users to receive instant, specific support. Furthermore, by combining generative artificial intelligence with external system APIs, accuracy and efficiency are improved, and operating costs are reduced. This system will significantly contribute to reducing operating costs and streamlining customer support, particularly for medium and small businesses.

[1245] The following describes the processing flow.

[1246] Step 1:

[1247] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[1248] The terminal (user's device) sends this message to the server.

[1249] Step 2:

[1250] The server sends the message received from the user to a generative artificial intelligence. For example, GPT-4 is used as the generative AI.

[1251] The generative artificial intelligence analyzes the message and determines the user's intent to be "procedures for adding a device."

[1252] Step 3:

[1253] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[1254] The server includes user authentication information and related device information in the API request.

[1255] Step 4:

[1256] The server sends the API request to the MDM system.

[1257] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[1258] The MDM system returns this information to the server as an API response.

[1259] Step 5:

[1260] The server receives a response from the MDM system and resends the acquired information to the generative artificial intelligence.

[1261] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[1262] Step 6:

[1263] The server receives the response generated by the generative artificial intelligence and responds to the user through the chatbot interface.

[1264] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[1265] Step 7 (Optional):

[1266] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[1267] Users provide feedback and contribute to improving the quality of the service.

[1268] (Example 1)

[1269] 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".

[1270] Conventional user support systems suffer from problems such as delayed and inaccurate responses to user inquiries. Furthermore, manual support is costly to operate, especially for small and medium-sized enterprises. This invention aims to solve these problems, improve user satisfaction, and reduce operating costs.

[1271] 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.

[1272] In this invention, the server includes means for receiving user inquiries, means for registering the received inquiries in a message queue, means for requesting a generative artificial intelligence to analyze the messages, means for the generative artificial intelligence to call an API of an external system to obtain necessary information based on the analysis results, means for requesting the generative artificial intelligence to analyze the obtained information again to generate a response to the user, and means for providing the generated response to the user. This enables a rapid and accurate response to user inquiries, resulting in reduced operating costs and improved user satisfaction.

[1273] A "user" refers to a person who makes a request to the system.

[1274] An "inquiry" refers to a question or request that a user sends to a system.

[1275] "Means of receiving" refers to the function that allows the server to receive inquiries sent by users.

[1276] A "message queue" refers to a data structure used to temporarily store received inquiries and process them in order.

[1277] "Generative artificial intelligence" refers to artificial intelligence technologies (such as natural language processing technologies) that analyze received inquiries and understand their intent.

[1278] "Means of analysis" refers to a function that uses generative artificial intelligence to analyze the content of received inquiries and identify their intent and requirements.

[1279] "External systems" refer to third-party systems or services that the server uses to acquire information in cooperation with it.

[1280] An "API" refers to an application programming interface provided by an external system, offering a method for a server to communicate with that external system.

[1281] "Means of acquiring information" refers to the function of acquiring necessary information from external systems via APIs based on the analysis results of generative artificial intelligence.

[1282] "Means for generating answers" refers to a function that allows a generative artificial intelligence to generate specific answers for the user based on the acquired information.

[1283] "Means of delivery" refers to functions for communicating generated responses to users through chatbots or similar means.

[1284] This invention is a system that efficiently processes user inquiries and provides quick and accurate answers. By linking generative artificial intelligence with APIs of external systems, the system automates user support, reduces operating costs, and improves user satisfaction.

[1285] The system consists of the following main hardware and software components:

[1286] 1. A means of receiving user inquiries (e.g., a chatbot)

[1287] 2. Methods for analyzing queries using generative artificial intelligence (e.g., GPT-4)

[1288] 3. Means of obtaining information by calling APIs of external systems (e.g., APIs of mobile device management systems (MDM))

[1289] 4. Means by which generative artificial intelligence generates responses to users

[1290] 5. Means of providing the generated response to the user

[1291] The following describes the specific processing steps of this system's program.

[1292] 1. Receiving a user inquiry

[1293] The user sends a message to the chatbot saying, "I want to add a new device." The user's device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[1294] 2. Analysis using generative artificial intelligence

[1295] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent as "device addition procedure."

[1296] 3. Information acquisition via API integration

[1297] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[1298] 4. Answer generation using generative artificial intelligence

[1299] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI generates "specific steps for adding a device." For example, it might show steps such as, "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[1300] 5. Providing responses to users

[1301] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a new device to the network.

[1302] Specific example

[1303] When a user wants to add a new device to the company network, the following prompt is entered into the generative artificial intelligence.

[1304] Example of a prompt:

[1305] "Please tell me how to add a new device to the company network."

[1306] The generative artificial intelligence generates instructions based on this prompt, and these instructions are provided to the user from the server via a chatbot. This process allows the user to quickly receive specific instructions and add devices. This system will greatly contribute to reducing operational costs and improving the efficiency of customer support, especially for small and medium-sized enterprises.

[1307] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1308] The processing flow of this system's program

[1309] Step 1:

[1310] The user enters and sends the message "I want to add a new device" to the chatbot. The device sends this message to the server. The server receives the message at a specific API endpoint and registers it in the message queue.

[1311] Input: User inquiry message

[1312] Output: Registered to message queue

[1313] Specific actions:

[1314] The user enters a message using the chatbot and clicks the "Send" button.

[1315] The device sends a message to the server using an HTTP POST request.

[1316] The server receives the message and stores it in the message queue.

[1317] Step 2:

[1318] The server retrieves a new message from the message queue and sends an analysis request to a generative artificial intelligence (e.g., GPT-4) API. The generative artificial intelligence analyzes the received message and determines its intent to be "device addition instructions."

[1319] Input: User inquiry retrieved from the message queue

[1320] Output: Analysis results (for example, the intent behind "Procedure for adding a device")

[1321] Specific actions:

[1322] The server retrieves the message from the queue.

[1323] The server sends a request to GPT-4 using a pre-configured prompt.

[1324] GPT-4 analyzes the message and identifies its intent.

[1325] Step 3:

[1326] Based on the analysis results of the generative artificial intelligence, the server sends an information retrieval request to the mobile device management system (MDM) API. The MDM system responds to the server's request with the current network configuration and necessary procedural information.

[1327] Input: Request to retrieve information based on analysis results

[1328] Output: Network configuration information and procedure information from the MDM system.

[1329] Specific actions:

[1330] The server generates an HTTP request and sends it to a specific endpoint in the MDM system.

[1331] The MDM system receives the request and returns network configuration information to the server as a response.

[1332] Step 4:

[1333] The server passes the information obtained from the API to a generative artificial intelligence (AI) and requests it to generate specific steps that the user should take. The generative AI then generates "specific steps for adding a device."

[1334] Input: Network configuration information and procedure information obtained from the API.

[1335] Output: Specific steps the user should take

[1336] Specific actions:

[1337] The server includes the information it has obtained in the prompt message and passes it to GPT-4.

[1338] GPT-4 generates specific procedures based on this information.

[1339] For example: "To add a device, first log in to the XX portal and click the 'Add New Device' button."

[1340] Step 5:

[1341] The server sends the generated response to the user via the chatbot. The user follows the instructions from the chatbot to add a device.

[1342] Input: Generated specific steps

[1343] Output: Displayed as a response to the user

[1344] Specific actions:

[1345] The server sends the generated steps to the chatbot's API, which then displays them in the user's chat window.

[1346] The user adds a device by following the instructions: "Log in to the XX portal and click the 'Add New Device' button."

[1347] In this way, by performing the necessary data processing and calculations at each step, we can respond quickly and accurately to user inquiries.

[1348] (Application Example 1)

[1349] 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".

[1350] Responding to user inquiries on modern e-commerce sites is often time-consuming and labor-intensive, leading to decreased user satisfaction and increased operational costs. Furthermore, there is a demand for quick and accurate responses to frequent inquiries such as inventory checks and purchase procedures. Traditional systems have struggled to efficiently address these challenges.

[1351] 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.

[1352] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, and, if the user's inquiry concerns checking product inventory or purchasing procedures, means for obtaining inventory information of the relevant product through an API of an external system and for the generative artificial intelligence to generate an answer including the inventory status of the relevant product. As a result, users can receive quick and accurate support, reducing operating costs and improving user satisfaction.

[1353] "Means for receiving user inquiries" refers to an interface for receiving questions and requests that users make to the system.

[1354] "Methods of utilizing generative artificial intelligence" refers to the process of using generative artificial intelligence to analyze user inquiries and understand their intent and content.

[1355] "A means of obtaining necessary information by calling an external system's API" refers to the process of using an external information system's API based on the analysis results to retrieve data and information related to the inquiry.

[1356] "A means by which generative artificial intelligence generates responses to users" refers to the process by which generative artificial intelligence creates appropriate responses to user inquiries based on acquired information.

[1357] "Means of providing generated answers to users" refers to an interface for conveying answers and information generated by generative artificial intelligence to users.

[1358] "Inquiries regarding product stock availability and purchase procedures" refer to inquiries from users asking about the stock status of a specific product or seeking information on how to purchase it.

[1359] "Means of obtaining inventory information for the relevant product through an external system's API" refers to the process of obtaining inventory data for a specific product from an external system using an API.

[1360] "Means for generating a response that includes the inventory status of the relevant product" refers to a process for generating an appropriate response for the user, including the inventory status, based on acquired inventory information.

[1361] This invention is a system that provides quick and accurate responses to user inquiries. This system is particularly intended for inquiries regarding product inventory checks and purchase procedures on e-commerce websites, and is designed to improve user satisfaction and reduce operating costs. The following describes specific embodiments for implementing this invention.

[1362] The server utilizes technologies such as generative artificial intelligence (GPT-4), RESTful APIs, and mobile application frameworks (e.g., React Native). This system operates through an application installed on the user's smartphone.

[1363] When a user makes an inquiry via their smartphone, the following processes take place.

[1364] When a user submits an inquiry, it is first sent to the server. The server then passes this inquiry to a generative artificial intelligence (AI) for analysis. The AI ​​understands the intent and content of the inquiry, and based on the analysis results, it calls an API of an external system to obtain the necessary information.

[1365] For example, if a user sends a prompt such as "Do you have this item in stock? Item ID: 12345," the server analyzes this inquiry and calls an API of an external e-commerce platform to check the stock of the relevant item. Based on the stock information obtained from the API, generative artificial intelligence generates an answer for the user.

[1366] The generated responses are provided to the user in an easy-to-understand format. This process allows users to check inventory accurately and quickly, supporting their purchasing decisions.

[1367] This system can handle a wide range of complex inquiries and significantly improves the user experience, as demonstrated by the specific examples below.

[1368] Adding specific examples

[1369] Example of a prompt

[1370] 1. "Is this T-shirt in stock? Product ID: 98765"

[1371] 2. "Please leave a review for this product. Product ID: 12345"

[1372] 3. "Please tell me how to return this backpack."

[1373] By using these prompts, generative artificial intelligence can quickly generate and provide accurate answers to users. This allows users to obtain product information from the comfort of their homes, improving their online shopping experience.

[1374] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1375] Step 1:

[1376] A user makes an inquiry through a smartphone app. The user enters the prompt message "Is this product in stock? Product ID: 12345" and presses the submit button. The entered inquiry is sent from the device to the server. The input is the user's inquiry, and the output is the inquiry data received by the server.

[1377] Step 2:

[1378] The server sends the received inquiry data to a generative artificial intelligence (GPT-4). The generative AI analyzes the inquiry and determines its intent to be "check product inventory." Natural language processing is used for this analysis; the input is the inquiry data, and the output is the analysis result data.

[1379] Step 3:

[1380] The server calls an API of an external system based on the analysis results and sends a request to retrieve inventory information for the specified product ID. Here, an HTTP request is made to the API endpoint. The input is the analysis result data, and the output is the product inventory information returned from the API.

[1381] Step 4:

[1382] The server receives product inventory information returned from the API. This inventory information includes the availability status (in stock or out of stock) corresponding to the product ID. The input is the inventory information returned by the API, and the output is the storage of the inventory information within the server.

[1383] Step 5:

[1384] The server passes the acquired inventory information back to the generative artificial intelligence (AI) to generate a specific response to provide to the user. The generative AI generates a response such as, "The inventory for product ID: 12345 is AA." The input is inventory information, and the output is the generated specific response.

[1385] Step 6:

[1386] The server sends the generated response to the user's smartphone app. The device receives the response message and displays it to the user. The user can then view the response regarding the inventory status on their smartphone screen. The input is the generated response, and the output is the response message displayed to the user.

[1387] This processing flow allows users to quickly and accurately obtain product inventory information, supporting their purchasing decisions.

[1388] 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.

[1389] This invention provides a system that efficiently processes user inquiries and delivers quick and accurate responses by combining it with an emotion engine, thereby providing optimal responses tailored to the user's emotions. This system automates user support by linking generative artificial intelligence with APIs of external systems, reducing operational costs while achieving high user satisfaction that takes user emotions into consideration.

[1390] The system consists of the following main components:

[1391] 1. Means for receiving user inquiries

[1392] 2. Means of analyzing inquiries using generative artificial intelligence

[1393] 3. Means of obtaining information by calling an API of an external system

[1394] 4. Means by which generative artificial intelligence generates responses to users

[1395] 5. Means of providing the generated response to the user

[1396] 6. A means of using an emotion engine to recognize the emotions of users when receiving their inquiries.

[1397] 7. Means by which the emotion engine recognizes the user's emotions and provides additional contextual information to the generative artificial intelligence based on those emotions.

[1398] 8. Means for adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[1399] 9. A means by which the emotion engine analyzes not only the content of the inquiry but also the entire user interaction in order to regularly monitor the user's emotions.

[1400] To understand how this system works, the program's processing will be explained with concrete examples.

[1401] Specific example

[1402] Consider a scenario where a user wants to add a new device to the company network. In this case, the user would receive support through the following steps.

[1403] 1. Receiving a user inquiry

[1404] The user sends a message to the chatbot saying, "I want to add a new device."

[1405] The terminal (user's device) sends this message to the server.

[1406] 2. Emotion recognition by an emotion engine

[1407] The server sends the message received from the user to the emotion engine.

[1408] The emotion engine analyzes the message and recognizes the user's emotions (e.g., excitement, frustration, confusion, etc.).

[1409] 3. Analysis using generative artificial intelligence

[1410] The server sends the emotion recognition results from the emotion engine to the generative artificial intelligence.

[1411] The generative artificial intelligence analyzes the message and emotion recognition results to determine the user's intention is "procedures for adding a device."

[1412] 4. Information acquisition via API integration

[1413] Based on the analysis results, the server calls the API of the mobile device management system (MDM system) and sends a request to retrieve the necessary information.

[1414] The MDM system receives the request and replies with the current network configuration and necessary procedural information.

[1415] 5. Answer generation using generative artificial intelligence

[1416] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[1417] Generative artificial intelligence generates "specific steps for adding a device." These steps are generated with consideration for the user's emotions and tone. For example, if the user is frustrated, the explanation will be more detailed and polite.

[1418] 6. Providing responses to users

[1419] The server sends the generated response back to the user through the chatbot interface.

[1420] The user adds the device by following the instructions given by the chatbot.

[1421] This system allows users to receive instant, specific, and emotionally sensitive support. Furthermore, by combining generative artificial intelligence with an emotion engine, accuracy and efficiency are improved, leading to increased user satisfaction. This system will significantly contribute to reducing operational costs and streamlining customer support, particularly for medium and small businesses.

[1422] The following describes the processing flow.

[1423] Step 1:

[1424] A user sends a message to the chatbot saying, "I want to add a new device to the company network."

[1425] The terminal (user's device) sends this message to the server.

[1426] Step 2:

[1427] The server sends the message received from the user to the emotion engine.

[1428] The emotion engine analyzes messages and recognizes the user's emotions.

[1429] Step 3:

[1430] The emotion engine sends the analysis results back to the server. These results include information about the user's emotions (e.g., excitement, frustration, confusion).

[1431] Step 4:

[1432] The server sends the received emotion recognition results and the user's message to the generative artificial intelligence.

[1433] Based on this information, the generative artificial intelligence determines the user's intention to be "procedures for adding a device."

[1434] Step 5:

[1435] Based on the analysis results from the generative artificial intelligence, the server prepares to call the API of the mobile device management system (MDM system).

[1436] API requests include user authentication information and associated device information.

[1437] Step 6:

[1438] The server sends the API request to the MDM system.

[1439] The MDM system receives the request and retrieves the current network configuration and necessary procedural information.

[1440] The MDM system returns this information to the server as an API response.

[1441] Step 7:

[1442] The server receives a response from the MDM system and sends the acquired information and emotion recognition results back to the generative artificial intelligence.

[1443] Generative artificial intelligence generates specific steps for the user to add a device based on the provided data.

[1444] The generated instructions are adjusted in content and tone to take the user's emotions into consideration. For example, if the user is frustrated, a more detailed and polite explanation will be generated.

[1445] Step 8:

[1446] The server sends the generated response back to the user through the chatbot interface.

[1447] The user adds a device by following the instructions given by the chatbot. For example, the user logs into the XX portal and clicks the "Add New Device" button.

[1448] Step 9 (Optional):

[1449] The server sends a feedback request via the chatbot to confirm whether the user's action has been completed and to check their satisfaction level.

[1450] Users provide feedback and contribute to improving the quality of the service.

[1451] (Example 2)

[1452] 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".

[1453] Traditional customer support systems suffered from problems such as insensitive responses to user emotions and cumbersome procedures, leading to decreased user satisfaction. In particular, the inability to appropriately understand user emotions resulted in a decline in response quality. Furthermore, while prompt and accurate responses to inquiries were required, efficient information gathering and appropriate response generation proved difficult.

[1454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1455] In this invention, the server includes means for receiving user inquiries, means for transmitting the received inquiries to an emotion analysis engine and recognizing the user's emotions, means for transmitting the results of the emotion analysis engine to a generative artificial intelligence and analyzing the received inquiries, means for calling an API of an external system based on the analysis results to obtain necessary information, means for the generative artificial intelligence to generate a response to the user in an emotion-sensitive tone based on the acquired information, and means for providing the generated response to the user. This enables a rapid and accurate response that takes the user's emotions into consideration.

[1456] "Means for receiving user inquiries" refers to devices or systems for receiving inquiries sent by users via communication.

[1457] "A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions" refers to a device or system that sends the content of received inquiries to a program or device for performing emotion analysis, thereby identifying the user's emotional state.

[1458] "A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence and analyzing the received inquiry" refers to a program or device that transmits the results obtained from emotion analysis to a generative artificial intelligence and analyzes and understands the content of the inquiry.

[1459] "Means of calling an external system's API based on analysis results to obtain necessary information" refers to a program or device that operates an external system's API based on analysis results to obtain the necessary information.

[1460] "A means by which generative artificial intelligence generates responses to users in an emotionally sensitive tone based on acquired information" refers to a device or system in which generative artificial intelligence considers acquired information and the user's emotional state to create the optimal response, taking into account tone and content.

[1461] "Means of providing generated answers to users" refers to devices or systems that provide users with answers created by generative artificial intelligence.

[1462] This invention is a system for providing efficient and appropriate responses to user inquiries. This system utilizes generative artificial intelligence and an emotion analysis engine to generate quick and accurate answers while taking user emotions into consideration.

[1463] This system consists of several main components. Each component and its function are described below.

[1464] Hardware and software configuration

[1465] 1. Means for receiving user inquiries

[1466] This method typically includes web-based chatbot interfaces or mobile applications. The user's inquiry is sent to the server in real time.

[1467] 2. A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions.

[1468] The server sends the received query to the sentiment analysis engine. The sentiment analysis engine analyzes the emotions in the text using an emotion recognition API, such as Affectiva. This step determines whether the user is agitated, irritated, or confused.

[1469] 3. A means of transmitting the results of an emotion analysis engine to a generative artificial intelligence system and analyzing the received inquiry.

[1470] The server sends the results obtained from the emotion analysis engine to a generative artificial intelligence (e.g., GPT-4). This generative AI analyzes the user's intent based on the inquiry content and emotion data.

[1471] 4. A means of obtaining necessary information by calling an API of an external system based on the analysis results.

[1472] Based on the analysis results, the server calls APIs of external systems (e.g., mobile device management systems) to collect necessary information. For example, it uses the Microsoft Intune API to obtain the current network configuration and necessary procedural information.

[1473] 5. A method by which a generative artificial intelligence generates responses to the user in an emotionally sensitive tone based on the acquired information.

[1474] The server retransmits the acquired information and sentiment analysis results to a generative artificial intelligence system to generate a response for the user. The generated response is crafted in a tone that takes the user's emotions into consideration. For example, if the user is irritated, the response will include a more polite and detailed explanation.

[1475] 6. Means of providing the generated response to the user

[1476] The server provides the generated response to the user through the chatbot interface. The user then solves the problem according to this response.

[1477] Examples of specific cases and prompt statements

[1478] Specific example

[1479] When a user wants to add a new device to the company network, the following steps are taken:

[1480] The user sends a message to the chatbot saying, "I want to add a new device."

[1481] The terminal (user's device) sends this message to the server.

[1482] The server sends the message to the sentiment analysis engine, which recognizes that the user is confused.

[1483] The server sends the results of the emotion analysis engine to a generative artificial intelligence (GPT-4) to determine the user's intent in the "device addition procedure".

[1484] The server calls the Microsoft Intune API to retrieve the necessary information.

[1485] Based on the acquired information and emotion recognition results, the server generates specific steps using generative artificial intelligence.

[1486] The server provides the generated instructions to the user via a chatbot, and the user adds the device by following the provided instructions.

[1487] Example of a prompt

[1488] "Please tell me how to add a new device to the company network."

[1489] "Please provide appropriate support procedures for when a user is confused."

[1490] This system allows users to receive efficient support and appropriate answers tailored to their inquiries. This improves user satisfaction and reduces the company's operating costs.

[1491] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1492] Step 1:

[1493] The user sends a message to the chatbot saying, "I want to add a new device."

[1494] Input: The message entered by the user into the chatbot.

[1495] Output: The message is sent from the terminal to the server.

[1496] Specific operation: When a user uses a device (e.g., a smartphone or computer) to type a message into the chatbot and presses the send button, the device sends this message to the server.

[1497] Step 2:

[1498] The server sends the received message to the sentiment analysis engine.

[1499] Input: Message received from the user.

[1500] Output: The message is passed to the sentiment analysis engine.

[1501] Specific operation: The server analyzes the received message, converts it to an appropriate format, and then sends it to the sentiment analysis engine. At this time, the text data is sent to the sentiment recognition API, and the analysis begins.

[1502] Step 3:

[1503] The emotion analysis engine analyzes the message and recognizes the user's emotions.

[1504] Input: The message text sent from the server.

[1505] Output: User emotion information (e.g., excitement, frustration, confusion, etc.).

[1506] Specific operation: The sentiment analysis engine analyzes the text and uses a language model to determine the user's emotions. The emotion recognition results are converted into a data format and sent back to the server.

[1507] Step 4:

[1508] The server transmits the emotion recognition results obtained from the emotion analysis engine to the generative artificial intelligence.

[1509] Input: User message and sentiment recognition result.

[1510] Output: Data sent to a generative artificial intelligence system as an analysis request.

[1511] Specific operation: The server converts the emotion recognition results into an appropriate format for sending to a generative artificial intelligence (e.g., GPT-4) and sends a request to the generative artificial intelligence.

[1512] Step 5:

[1513] Generative artificial intelligence analyzes user inquiries based on messages and emotion recognition results.

[1514] Input: User message and sentiment recognition result.

[1515] Output: Analysis results regarding user intent (e.g., "Steps to add a device").

[1516] Specific operation: Generative artificial intelligence uses natural language processing techniques to analyze messages and identify the user's intent. The analysis results are sent to the server as data.

[1517] Step 6:

[1518] Based on the analysis results, the server calls an API of an external system (e.g., a mobile device management system) to obtain the necessary information.

[1519] Input: Analysis results from a generative artificial intelligence.

[1520] Output: Information obtained from external systems (e.g., network configuration, procedure information).

[1521] Specific operation: The server creates an API request based on the analysis results of the generative artificial intelligence, and calls the appropriate external system's API to retrieve information. The retrieved information is stored on the server.

[1522] Step 7:

[1523] The server then sends the acquired information and emotion recognition results back to the generative artificial intelligence, requesting it to generate specific steps that the user should take.

[1524] Input: Acquired information and emotion recognition results.

[1525] Output: Detailed user instructions.

[1526] Specific operation: The server sends the acquired information and emotion recognition results to the generative artificial intelligence in an appropriate format and requests it to generate a response that takes the user's emotions into consideration.

[1527] Step 8:

[1528] Generative artificial intelligence generates "specific steps for adding a device."

[1529] Input: Acquired information and emotion recognition results.

[1530] Output: A detailed instruction manual provided to the user.

[1531] Specific operation: Generative artificial intelligence takes user emotions into consideration and generates detailed and careful instructions. For example, if the user is frustrated, the instructions will be provided in detail and with images.

[1532] Step 9:

[1533] The server responds to the user with the generated instructions through the chatbot interface.

[1534] Input: Specific instructions from a generative artificial intelligence.

[1535] Output: Instructional information provided to the user.

[1536] Specific operation: The server sends the generated instructions to the chatbot, which then displays them to the user. The user adds a device following the provided instructions.

[1537] (Application Example 2)

[1538] 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".

[1539] With the proliferation of autonomous vehicles, users are increasingly making real-time inquiries and giving instructions while driving. However, conventional systems provide uniform responses without considering user emotions, making it difficult to ensure user satisfaction and safety. In particular, in emergencies and high-stress situations where a quick and appropriate response is required, it is crucial to provide responses that are sensitive to the user's emotions.

[1540] 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.

[1541] In this invention, the server includes means for receiving user inquiries, means for utilizing generative artificial intelligence to analyze the received inquiries, means for calling an API of an external system to obtain necessary information based on the analysis results, means for the generative artificial intelligence to generate an answer to the user based on the obtained information, means for providing the generated answer to the user, means for utilizing an emotion engine to analyze the user's emotions, means for adjusting the content and tone of the answer based on the emotions recognized by the emotion engine, and means for processing user inquiries and instructions in real time while the autonomous vehicle is in operation. This enables quick and appropriate responses to inquiries that take into account the user's emotions, even while the autonomous vehicle is in operation.

[1542] "Means for receiving user inquiries" refers to the interface used to receive messages when a user sends voice or text messages to the system.

[1543] "Methods of using generative artificial intelligence to analyze received inquiries" refers to processes that use generative artificial intelligence to analyze messages received from users in order to understand the user's intent.

[1544] "A means of obtaining necessary information by calling an external system's API based on the analysis results" refers to the process of obtaining necessary data and information by calling an external system's API based on the results analyzed by generative artificial intelligence.

[1545] "A means by which generative artificial intelligence generates a response to the user based on acquired information" refers to the process by which generative artificial intelligence generates an appropriate response to the user based on information acquired from an external system.

[1546] "Means of providing generated answers to users" refers to an interface and processing method for presenting answers generated by generative artificial intelligence to users.

[1547] "Using an emotion engine to analyze user emotions" refers to a process that uses an engine to understand the user's emotional state based on the content of user inquiries and instructions.

[1548] "Means for adjusting the content and tone of responses based on emotions recognized by the emotion engine" refers to the process of appropriately adjusting the content and tone of generated responses based on the user's emotions recognized by the emotion engine.

[1549] "Means for processing user inquiries and instructions in real time while an autonomous vehicle is in operation" refers to a system and process that allows an autonomous vehicle to respond immediately to real-time inquiries and instructions from users while it is in operation.

[1550] Patent Specification

[1551] This invention is a system for efficiently and emotionally processing user inquiries and instructions in real time while an autonomous vehicle is in operation. Specifically, it receives user inquiries, analyzes the user's emotions using an emotion engine, and then uses generative artificial intelligence to generate and provide appropriate answers based on the results.

[1552] Hardware and software to be used

[1553] hardware

[1554] Smartphone: A device in which users input inquiries and instructions via voice or text.

[1555] Autonomous vehicles: Connect to a smartphone via Bluetooth or Wi-Fi and send driving information to a server.

[1556] Server: A central system for analysis and data processing.

[1557] software

[1558] Generative artificial intelligence: Software used to analyze user inquiries using natural language processing. (Examples: Google Cloud Natural Language API, IBM Watson)

[1559] Emotion engine: Software used to analyze user emotions. (Example: Amazon Comprehend)

[1560] API Integration Module: A library for calling APIs of external systems (e.g., mobile device management systems). (e.g., Requests library)

[1561] Program Processing Description

[1562] Recording and transmitting audio data

[1563] The user gives voice commands using their smartphone. The smartphone records the voice data and sends it to the server.

[1564] Emotional analysis using an emotion engine

[1565] The server passes the received audio data to the emotion engine, which analyzes the user's emotions. The emotion engine recognizes the user's emotions from the audio content and returns the result.

[1566] Response generation by generative artificial intelligence

[1567] The server passes the voice data, along with the results from the emotion engine, to the generative artificial intelligence (AI) to analyze the user's intent. The generative AI then generates an appropriate response based on the analysis results.

[1568] API integration and information retrieval

[1569] If necessary, the server calls APIs of external systems to obtain the data and information required for operation. The obtained information is passed to a generative artificial intelligence and used to generate the final answer.

[1570] Providing answers to users

[1571] The server sends the generated response back to the smartphone, providing it to the user. The user then decides on their next action based on that response.

[1572] Specific examples and prompt statements

[1573] Specific example

[1574] For example, consider a scenario where a user in an autonomous vehicle asks, "How long will it take to get to the next gas station?"

[1575] Voice: "How far is it to the next gas station?"

[1576] Prompt to the AI ​​engine: "User question: How long until the next gas station? User's mood: A little impatient."

[1577] This allows the system to provide responses that are appropriate to the user's emotions, enabling them to reach their destination comfortably and safely, even while driving autonomously.

[1578] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1579] Step 1: The user gives a voice command.

[1580] The user, while inside the autonomous vehicle, gives a voice command into their smartphone's microphone, such as, "How long will it take to get to the next gas station?" This voice data becomes the input.

[1581] Step 2: The device records the audio data.

[1582] The device (smartphone) records the user's voice and saves it as an audio file in its internal data. The output obtained here is an audio file.

[1583] Step 3: The device sends the audio data to the server.

[1584] The terminal sends the recorded audio file to the server. In this step, the terminal takes an audio file as input and performs the procedure (communication processing) to send it to the server. The output is the audio data stored on the server.

[1585] Step 4: The server passes the voice data to the emotion engine.

[1586] The server inputs the received audio data into the emotion engine, which analyzes the user's emotions. The emotion engine then outputs text data and emotion recognition results based on the audio data.

[1587] Step 5: The server passes the emotion analysis results to the generative artificial intelligence.

[1588] The server passes the speech text data, along with the emotion recognition results from the emotion engine, to the generative artificial intelligence. The generative AI takes this as input, analyzes the user's intent, and generates an appropriate response. The generated response becomes the output.

[1589] Step 6: The server calls the API to retrieve the necessary information.

[1590] Based on the analysis results, the server calls APIs of external systems such as mobile device management systems to obtain necessary information (for example, the location information of nearby gas stations). The API calls are the input, and the information obtained from the external systems is the output.

[1591] Step 7: The server generates the final answer.

[1592] The server then passes the acquired information and emotion analysis results back to the generative artificial intelligence to generate the final response. Based on this, the generative AI outputs the optimal response that takes the user's emotions into consideration.

[1593] Step 8: The server provides the answer to the user.

[1594] The server sends the generated response to the terminal (smartphone) and provides it to the user. In this step, the server takes the generated response as input and sends it to the user's terminal as output. The user receives the response and decides on their next action.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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."

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1616] The following is further disclosed regarding the embodiments described above.

[1617] (Claim 1)

[1618] A means of receiving user inquiries,

[1619] A method that utilizes generative artificial intelligence to analyze received inquiries,

[1620] A means of obtaining necessary information by calling an API of an external system based on the analysis results,

[1621] A means by which a generative artificial intelligence generates a response to the user based on the acquired information,

[1622] A means of providing the generated answer to the user,

[1623] A system that includes this.

[1624] (Claim 2)

[1625] The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing.

[1626] (Claim 3)

[1627] The system according to claim 1, which uses the API of a mobile device management system as the API of an external system.

[1628] "Example 1"

[1629] (Claim 1)

[1630] A means of receiving user inquiries,

[1631] A means of registering received inquiries in the message queue,

[1632] A means of requesting a message to be analyzed by a generative artificial intelligence,

[1633] A means by which a generative artificial intelligence can call an API of an external system based on the analysis results to obtain the necessary information,

[1634] A means of generating a response to the user by again requesting the acquired information to be analyzed by a generative artificial intelligence,

[1635] A means of providing the generated answer to the user,

[1636] A system that includes this.

[1637] (Claim 2)

[1638] The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing.

[1639] (Claim 3)

[1640] The system according to claim 1, which uses the management system's API as an API for an external system.

[1641] "Application Example 1"

[1642] (Claim 1)

[1643] A means of receiving user inquiries,

[1644] A method that utilizes generative artificial intelligence to analyze received inquiries,

[1645] A means of obtaining necessary information by calling an API of an external system based on the analysis results,

[1646] A means by which a generative artificial intelligence generates a response to the user based on the acquired information,

[1647] A means of providing the generated answer to the user,

[1648] When the user's inquiry concerns checking product inventory or purchasing procedures, the means includes obtaining inventory information for the relevant product through an API of an external system, and generating an artificial intelligence that generates a response including the inventory status of the relevant product.

[1649] A system that includes this.

[1650] (Claim 2)

[1651] The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing.

[1652] (Claim 3)

[1653] The system according to claim 1, which uses the API of an e-commerce platform as the API of an external system.

[1654] "Example 2 of combining an emotion engine"

[1655] (Claim 1)

[1656] A means of receiving user inquiries,

[1657] A means of sending received inquiries to an emotion analysis engine to recognize the user's emotions,

[1658] A means for transmitting the results of an emotion analysis engine to a generative artificial intelligence system and analyzing the received inquiry,

[1659] A means of obtaining necessary information by calling an API of an external system based on the analysis results,

[1660] A method for a generative artificial intelligence to generate responses to the user in an emotionally sensitive tone based on acquired information,

[1661] A means of providing the generated answer to the user,

[1662] A system that includes this.

[1663] (Claim 2)

[1664] The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing.

[1665] (Claim 3)

[1666] The system according to claim 1, which uses the API of a mobile device management system as the API of an external system.

[1667] "Application example 2 when combining with an emotional engine"

[1668] (Claim 1)

[1669] A means of receiving user inquiries,

[1670] A method that utilizes generative artificial intelligence to analyze received inquiries,

[1671] A means of obtaining necessary information by calling an API of an external system based on the analysis results,

[1672] A means by which a generative artificial intelligence generates a response to the user based on the acquired information,

[1673] A means of providing the generated answer to the user,

[1674] A method that utilizes an emotion engine to analyze user emotions,

[1675] A means of adjusting the content and tone of responses based on the emotions recognized by the emotion engine,

[1676] A means of processing user inquiries and instructions in real time while an autonomous vehicle is in operation,

[1677] A system that includes this.

[1678] (Claim 2)

[1679] The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing and recognizes emotions using an emotion engine.

[1680] (Claim 3)

[1681] The system according to claim 1, which communicates with an autonomous vehicle using Bluetooth or Wi-Fi. [Explanation of Symbols]

[1682] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving user inquiries, A method that utilizes generative artificial intelligence to analyze received inquiries, A means of obtaining necessary information by calling an API of an external system based on the analysis results, A means by which a generative artificial intelligence generates a response to the user based on the acquired information, A means of providing the generated answer to the user, A system that includes this.

2. The system according to claim 1, wherein a generative artificial intelligence analyzes a query using natural language processing.

3. The system according to claim 1, which uses the API of a mobile device management system as the API of an external system.

Images