System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving image data transmitted from a user; means for analyzing the received image data and recognizing a specific element in a screen; means for receiving and analyzing text data transmitted from the user and extracting a specific keyword or situation description; means for specifying missing information based on an analysis result of the image data and the text data and presenting additional information to the user; and means for generating a hearing item based on the analysis result and the acquired additional information and providing the hearing item to a responder.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, responding to inquiries about problems and questions places a heavy workload on both the asker and the respondent. Many check items and information are unknown or incomplete in advance, making the process cumbersome and reducing efficiency. Specifically, users often fail to adequately explain the problem, and the missing information is not provided, forcing the respondent to make the inquiry again. A method is needed to resolve these issues and improve operational efficiency. [Means for solving the problem]

[0005] The present invention provides a system that automatically analyzes image data and text data sent by a user, identifies missing information, and presents additional information to the user. Specifically, the system includes a means for receiving and analyzing image data sent by the user, a means for analyzing the received text data to extract specific keywords and situation descriptions, a means for identifying missing information based on the analysis results and presenting additional information to the user, and a means for generating final interview items from the acquired information and providing them to the respondent. This reduces the burden on both the user and the respondent and improves the efficiency of inquiry response. Furthermore, the use of multimodal generation AI enables highly accurate analysis and information completion even for different data formats.

[0006] "Image data" refers to visual information stored in digital format that is used as a visual confirmation for inquiries.

[0007] "Text data" refers to digital data containing textual information, and is used to respond to user inquiries and explain situations.

[0008] "Analysis" refers to analyzing input data and identifying its content and characteristics; specifically, it is the act of extracting meaning from image and text information.

[0009] A "specific element" refers to an element that exists within the data to be analyzed and indicates particularly important information or features, such as an error message or a UI element.

[0010] "Missing information" refers to information that is necessary to respond to an inquiry but that the user did not provide the first time, such as an error log or a detailed explanation of the situation.

[0011] "Presentation" refers to the act of displaying necessary information or requests from the system to the user.

[0012] "Hearing items" refer to questions and confirmation items that are set to organize inquiries from users and collect necessary information.

[0013] "Multimodal generative AI" refers to artificial intelligence technology that simultaneously analyzes different types of data formats (e.g., images and text) and generates meaning.

[0014] "Responder" refers to the engineer or support staff who handles inquiries and solves the user's problem based on the hearing items generated by the system. [Brief explanation of the drawings]

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

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

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

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

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

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

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

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

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

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0036] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0037] System configuration and operation

[0038] User

[0039] The user checks the app for a problem and prepares data (such as screenshots and text) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0040] Terminal

[0041] The terminal is responsible for receiving data sent by the user and sending it to the server. The received screenshots and text data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[0042] server

[0043] The server plays a central role in the system by executing the following series of processes.

[0044] 1. Data Receipt and Analysis

[0045] The server receives screenshots and text data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen, such as error messages and important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (such as "crash").

[0046] 2. Identifying and providing missing information

[0047] The server identifies missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and presents it to the user via the terminal.

[0048] 3. Receiving additional information and reanalyzing

[0049] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing item and provides it to the responder.

[0050] 4. Generating and providing interview items

[0051] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0052] Specific examples

[0053] For example, when a user inquires about an app crashing, the specific process is as follows:

[0054] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0055] 2. Terminal: Sends the data to the server.

[0056] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0057] 4. Terminal: Displays requests from the server to the user.

[0058] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0059] 6. Terminal: Re-send the error log to the server.

[0060] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0061] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user checks the application for a problem and prepares screenshots and text data to show the situation. Specifically, the user takes a screenshot of the moment the application crashes and writes a description that reads, "The application crashes."

[0065] Step 2:

[0066] The user inputs the screenshot and text data prepared using the terminal into the inquiry form and sends it to the system.

[0067] Step 3:

[0068] The terminal receives the screenshot and text data sent by the user.

[0069] Step 4:

[0070] The terminal uploads the received data via the network to send it to the server.

[0071] Step 5:

[0072] The server receives the screenshot and text data sent from the terminal.

[0073] Step 6:

[0074] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[0075] Step 7:

[0076] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[0077] Step 8:

[0078] The server identifies missing information based on the analysis of the image data and text data, for example, if an error log is not provided.

[0079] Step 9:

[0080] The server generates a message to ask the user for missing information, for example, making a specific request such as "Please provide the error log from the crash."

[0081] Step 10:

[0082] The terminal receives the request message from the server and displays it to the user.

[0083] Step 11:

[0084] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[0085] Step 12:

[0086] The terminal receives additional information from the user and retransmits it to the server.

[0087] Step 13:

[0088] The server receives the additional information sent by the terminal and analyzes all the data again.

[0089] Step 14:

[0090] The server generates the final hearing items based on the reanalysis results, such as "the error code and detailed description of the situation that is likely to have caused the crash."

[0091] Step 15:

[0092] The server prepares the generated final hearing items to be provided to the responder.

[0093] Step 16:

[0094] The responder responds quickly and accurately based on the hearing items provided by the server.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In conventional inquiry response systems, the information about the problem reported by the user is often insufficient, which forces the responder to request additional information each time, resulting in delayed responses. Furthermore, when the problem is complex, simple text data alone does not provide sufficient information, making it difficult for the responder to grasp the details. This increases the amount of back-and-forth communication between the user and the responder, resulting in reduced response efficiency.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder, means for receiving and reanalyzing the additional information from the user, and means for generating final hearing items and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate final hearing items.

[0100] "Image data" refers to data containing visual information such as screenshots that are sent by a user when reporting a problem with an application.

[0101] "Text data" is data containing character information that is sent when a user writes an explanation or detailed information about a problem in an application.

[0102] A "specific element" is an important part contained in image data, such as an error message or an important user interface element.

[0103] "Keywords" are important words or phrases that a user writes in text data, such as "crash" or "error message."

[0104] A "multimodal generative AI model" is an artificial intelligence model for analyzing both image data and text data, and has the ability to extract and analyze information from these data.

[0105] "Insufficient information" refers to information that is not sufficient for the person in charge to understand the details of the problem from the data initially provided by the user, and that must be provided additionally.

[0106] "Additional information" refers to detailed information, such as an error log or further explanation, that the server provides in response to a user's request for missing information.

[0107] "Hearing items" refers to a series of questions and confirmations that are generated by the server based on analysis data and that are required by the responder to respond to the problem.

[0108] The term "responder" refers to an agent or system administrator who responds to inquiries from users and provides support to resolve problems.

[0109] "Re-analysis" refers to the process in which the server re-analyzes the additional information provided by the user, thereby reconfirming the overall situation and generating the final hearing items.

[0110] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0111] System configuration and operation

[0112] User

[0113] The user prepares image data (e.g., screenshots) and text data (e.g., detailed description of the problem) to report an app malfunction. The user enters this data into an inquiry form via their device and sends it to the system. As a specific example of the malfunction, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0114] Terminal

[0115] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the Internet. The device also has the function of displaying requests and notifications from the server to the user.

[0116] server

[0117] The server plays a central role in the system and performs the following series of processes.

[0118] 1. Data Receipt and Analysis

[0119] The server receives the screenshot and text data sent from the device. It then uses a multimodal generative AI model to analyze the image data and recognize specific elements on the screen (e.g., error messages or important UI elements). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[0120] 2. Identifying and providing missing information

[0121] The server identifies missing information based on the received and analyzed information. For example, if an error log is not provided, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and displays it to the user via the terminal.

[0122] 3. Receiving additional information and reanalyzing

[0123] If the user provides additional information (e.g., error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing items and provides them to the responder.

[0124] 4. Generating and providing interview items

[0125] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0126] Specific examples

[0127] As a concrete example, the flow when a user makes an inquiry about "my app crashes" is shown below.

[0128] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0129] 2. Terminal: Sends the data to the server.

[0130] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0131] 4. Terminal: Displays requests from the server to the user.

[0132] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0133] 6. Terminal: Re-send the error log to the server.

[0134] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0135] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] To report an app malfunction, a user prepares a screenshot and text data describing the situation. Specifically, the user captures a screenshot of the moment the app crashes and writes an explanation such as "The app crashes" in the input form. After entering the necessary information in this form, the user presses the send button to send the data to the device.

[0139] Step 2:

[0140] The device receives the screenshot and text data sent by the user. This received data is uploaded to a server via the Internet. Specifically, an HTTP request is generated, the user's sent data is attached to it, and it is sent to the server. The input is the user's screenshot and text data, and the output is an HTTP request to the server.

[0141] Step 3:

[0142] The server receives data sent from the device. It classifies the received data and uses a multimodal generative AI model to analyze image data. The AI ​​model identifies error messages and important UI elements from screenshots. It also analyzes text data using natural language processing techniques to extract situation descriptions and keywords. The input is image data and text data from the device, and the output is error messages and keywords as the analysis results.

[0143] Step 4:

[0144] The server identifies missing information based on the analysis results. For example, if the analysis does not provide an error log, it determines that it is necessary. The server generates a request message saying, "Please provide the error log at the time of the crash," and sends it to the terminal. The input is the analysis result, and the output is a request message requesting additional information.

[0145] Step 5:

[0146] The terminal receives the request from the server and displays the contents to the user. Specifically, it presents the user with a pop-up notification or a prompt message on the screen saying "Please provide the error log in the event of a crash." The input is the request statement from the server, and the output is the notification to the user.

[0147] Step 6:

[0148] The user obtains the error log according to the instructions and sends it again via the terminal. The user selects the error log file and uploads it to the inquiry form as additional information. The user presses the send button again to send the data to the terminal. The input is the error log file, and the output is the data sent to the terminal.

[0149] Step 7:

[0150] The terminal receives additional information (error log) sent by the user again and uploads it to the server again. The input is the error log from the user, and the output is an HTTP request to the server.

[0151] Step 8:

[0152] The server receives the additional information and re-analyzes the data, including the results of the previous analysis. Using a multimodal generative AI model, it re-analyzes all data, including the added error log, and reconfirms the overall situation. The input is the additional information and the initial data, and the output is the re-analysis results.

[0153] Step 9:

[0154] The server generates hearing items based on the final analysis results. Specifically, it integrates the error message, error log, crash description, etc. provided by the user, and compiles all the information required by the responder into a single list. The input is the reanalysis results, and the output is a list of hearing items.

[0155] Step 10:

[0156] The server provides the final hearing items to the responder, who can then respond quickly and accurately based on the hearing items. The input is a list of hearing items, and the output is information provided to the responder.

[0157] This series of processes enables the system to automatically present missing information in response to user inquiries and efficiently generate final interview items, resulting in a fast and accurate response.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] In conventional inquiry response systems, if the information sent by the user is insufficient, the responder must request additional information each time, which is inefficient and tends to result in long response times. Furthermore, when supporting security devices, analyzing image data and text data is particularly time-consuming, which also hinders prompt responses. The present invention aims to solve these problems and improve the efficiency of inquiry responses.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating interview items based on the analysis results and the acquired additional information and providing them to a responder, and means installed on a smart device and applied to inquiries regarding security equipment support. This enables efficient processing of inquiries regarding security equipment and fast and accurate support.

[0163] "User" means an individual or organization that uses the system.

[0164] "Image data" is data containing visual information sent by a user.

[0165] "Text data" refers to data containing text information sent by a user.

[0166] The "receiving means" is a device or software that has the function of acquiring data sent from a user.

[0167] The "analyzing means" is a device or software that has the function of analyzing received data and recognizing specific elements or keywords.

[0168] The "specific elements" are important information elements contained in the image data and text data.

[0169] "Missing information" is information that is needed to answer a user's inquiry but that the user has not provided.

[0170] "Additional information" is information that the user is asked to provide to supplement the missing information.

[0171] "Hearing items" are questions and confirmations that are necessary for the responder to answer the user's inquiry.

[0172] A "responder" is a person or system that provides an answer to a user's inquiry.

[0173] The term "system" refers to a collection of hardware and software that constitutes the entire present invention.

[0174] "Analysis results" are information obtained from the analysis of received data.

[0175] A "smart device" is a device with internet connectivity, such as a phone, tablet, or smart glasses.

[0176] "Security equipment" refers to devices such as cameras and sensors that are installed to prevent fraud and accidents.

[0177] "Support" is the activity of providing assistance and solutions to user inquiries and problems.

[0178] The present invention provides a system for efficiently responding to inquiries regarding security device support by utilizing image data and text data sent by users. This system is comprised of three entities: a server, a terminal, and a user.

[0179] User

[0180] A user checks for a problem with a security device (e.g., a home security camera) and prepares data (e.g., screenshots and error messages) to explain the situation. The user enters this data into an inquiry form via a smart device and sends it to the system. For example, the user sends a description of the situation, such as "The camera cannot connect," along with a screenshot of the connection error.

[0181] Terminal

[0182] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user. Smartphones and tablets are used as the hardware for this purpose.

[0183] server

[0184] The server plays a central role in the system by executing the following series of processes: To analyze the received data, the server uses TENSORFLOW (registered trademark) for image recognition and NLTK (Natural Language Toolkit) for text analysis.

[0185] 1. Data Receipt and Analysis

[0186] The server receives the screenshot and text data sent from the device. It then uses a generative AI model to analyze the image data and recognize specific elements on the screen, such as error messages or important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "Connection Error").

[0187] 2. Identifying and providing missing information

[0188] The server identifies any missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log for the connection error," and presents it to the user via the terminal. An example of a generated prompt sentence is as follows:

[0189] Please upload a screenshot of the problem.

[0190] Enter the text of the error message.

[0191] Press "Next" and provide any additional information required.

[0192] 3. Receiving additional information and reanalyzing

[0193] If the user provides additional information (for example, an error log), the terminal sends it again to the server, which receives the additional information and analyzes the entire data again.

[0194] 4. Generating and providing interview items

[0195] The server generates a questionnaire based on the final analysis results, including details of the security camera connection error, error logs, and a description of the connection status. These questionnaires are provided to support personnel to assist in a quick and accurate response.

[0196] In this way, the present invention is a system that can automatically present missing information in response to inquiries about security equipment and efficiently generate final hearing items, thereby speeding up inquiry responses and improving user satisfaction.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] A user uses a smart device to report a security equipment malfunction. Specifically, the user inputs and sends a screenshot of the security camera's connection error screen and text data such as "Camera cannot connect." The input data is the screenshot image and the error message text.

[0200] Step 2:

[0201] The terminal receives screenshots and text data sent by the user. The input data is the screenshot image and text data provided by the user. After receiving this data, the terminal uploads it to the server via the network. The output data is the data transmitted to the server.

[0202] Step 3:

[0203] The server receives image data and text data sent from the device. The input data is the image data and text data sent from the device. The server uses TensorFlow to analyze the image data and recognize specific elements on the screen (e.g., error messages and UI elements). It also uses NLTK to analyze the text data and extract important keywords and situation descriptions. The output data are the image analysis results and text analysis results.

[0204] Step 4:

[0205] The server identifies missing information based on the analysis results of the image data and text data. The input data are the image analysis results and the text analysis results. Specifically, it recognizes that an error log has not been provided and generates a prompt to obtain additional information, such as "Please provide the error log in the event of a connection error." The output data is the generated prompt.

[0206] Step 5:

[0207] The terminal displays the request from the server to the user. The input data is the prompt received from the server. The terminal displays the prompt to the user, requesting additional information. The output data is the prompt displayed to the user.

[0208] Step 6:

[0209] Based on the request from the server, the user obtains the necessary additional information (for example, an error log), enters it into the terminal again, and transmits it. The input data is the error log obtained by the user.

[0210] Step 7:

[0211] The terminal receives additional information sent by the user and sends it back to the server. The input data is the error log sent by the user. The output data is the data sent to the server.

[0212] Step 8:

[0213] The server receives the data again and performs re-analysis. The input data is the error log provided as additional information. The server analyzes the entire data and generates the final hearing item. The output data is the final hearing item.

[0214] Step 9:

[0215] The server provides the generated hearing items to the responder. The input data is the final hearing items. The server provides this to the support staff to help the responder solve the user's problem quickly and accurately. The output data is the final hearing items shared between the user and the responder.

[0216] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0217] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing the user's emotions. It automatically analyzes image data and text data sent by the user, identifies missing information, presents additional information to the user, and generates final interview items to provide to the responder. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and improves the quality of inquiry responses based on those emotions.

[0218] System configuration and operation

[0219] User

[0220] The user checks the problem with the app and prepares data (for example, screenshots, text data, or audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[0221] Terminal

[0222] The terminal is responsible for receiving data sent by the user and sending it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[0223] server

[0224] The server executes the following series of processes.

[0225] 1. Data Receipt and Analysis

[0226] The server receives screenshots, text data, and audio data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[0227] 2. Use of Emotion Engine

[0228] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0229] 3. Identifying and Presenting Missing Information

[0230] The server identifies missing information based on the image data, text data, and the results of emotion analysis. For example, if an error log is not provided, it determines that it is needed. To obtain the missing information, the server generates a message such as "Please provide the error log from the crash" and displays it to the user via the device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0231] 4. Receiving additional information and reanalyzing

[0232] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and re-analyzes all the data. This re-analysis generates the final hearing item and provides it to the responder.

[0233] 5. Generating and providing interview items

[0234] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and the user's emotional state." These hearing items are provided to support personnel to help them respond quickly and flexibly. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a prompt response is required.

[0235] Specific examples

[0236] For example, when a user inquires about an app crashing, the specific process is as follows:

[0237] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[0238] 2. Terminal: Sends the data to the server.

[0239] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[0240] 4. Terminal: Displays requests from the server to the user.

[0241] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0242] 6. Terminal: Re-send the error log to the server.

[0243] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[0244] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final interview items, thereby improving the efficiency and quality of inquiry responses.In addition, by analyzing user emotions, it is possible to provide more appropriate responses.

[0245] The processing flow will be explained below.

[0246] Step 1:

[0247] The user checks the application for a problem and prepares a screenshot, text data, and audio data to show the situation. For example, the user takes a screenshot of the moment the application crashes, and creates an explanatory message saying "The application is crashing" and an audio message saying "I'm having trouble using the application."

[0248] Step 2:

[0249] The user inputs the screenshot, text data, and voice data prepared using the terminal into the inquiry form and sends them to the system.

[0250] Step 3:

[0251] The terminal receives the screenshot, text data, and audio data sent by the user.

[0252] Step 4:

[0253] The terminal uploads the received data via the network to send it to the server.

[0254] Step 5:

[0255] The server receives the screenshot, text data, and audio data sent from the terminal.

[0256] Step 6:

[0257] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[0258] Step 7:

[0259] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[0260] Step 8:

[0261] The server analyzes the voice data and uses an emotion engine to recognize the user's emotions, for example, identifying that the user is feeling anxious.

[0262] Step 9:

[0263] The server identifies missing information based on the image data, text data, and sentiment analysis results, for example, if an error log is not provided, and additional information is required.

[0264] Step 10:

[0265] The server generates a message requesting the user for missing information, such as "Please provide the error log of the crash." If the emotion engine detects negative emotions from the user, the message is more polite.

[0266] Step 11:

[0267] The terminal receives the request message from the server and displays it to the user.

[0268] Step 12:

[0269] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[0270] Step 13:

[0271] The terminal receives the additional information sent by the user and retransmits it to the server.

[0272] Step 14:

[0273] The server receives the additional information sent by the terminal and re-analyzes all the data.

[0274] Step 15:

[0275] The server generates the final hearing items based on the reanalysis results, for example, items including "error message, error log, crash description, and user's emotional state."

[0276] Step 16:

[0277] The server prepares to provide the generated final hearing items to the responder, including a notification to prompt a response, especially if the user's sentiment is negative.

[0278] Step 17:

[0279] The responder responds quickly and accurately based on the interview items provided by the server, and communicates appropriately after understanding the user's emotional state.

[0280] Example 2

[0281] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] In many modern systems, responding to user inquiries is done manually and is inefficient. Furthermore, responses are often made without considering the user's feelings, making it difficult to provide appropriate support. Furthermore, necessary information is often not provided at the time of inquiry, resulting in multiple exchanges and delays in response.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0284] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for receiving voice data and analyzing it to recognize the user's emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate hearing items while responding appropriately to the user's emotions.

[0285] "User" refers to an individual or corporation that uses the system to make an inquiry.

[0286] "Image data" refers to visual information such as screenshots and photo data sent by users.

[0287] "Text data" refers to sentences and character information entered by the user.

[0288] "Audio Data" refers to audio recordings or speech data that a user transmits to the system.

[0289] "Multimodal generation AI" refers to artificial intelligence that can simultaneously analyze and generate multiple modalities, such as image data and text data.

[0290] "Specific elements" refer to parts or information that play an important role in image data, such as error messages or specific icons.

[0291] An "emotion engine" refers to a software module that analyzes voice and text data to recognize the user's emotions.

[0292] "Analysis" refers to the act of processing data and extracting specific information or features.

[0293] "Hearing items" refer to important information and questions that the support staff should collect from the user.

[0294] "Additional information" refers to any additional data or information that was not included in the initial enquiry but is necessary to provide effective support.

[0295] "Responder" refers to a support staff member or engineer who responds to inquiries from users.

[0296] The present invention provides a system for improving the efficiency of user inquiry responses and providing appropriate support by recognizing the user's emotions. This system receives image data, text data, and voice data sent by the user, analyzes them to identify necessary information, and generates final hearing items to provide to the responder.

[0297] System configuration

[0298] This system mainly consists of users, terminals, and servers. Details of each component are as follows:

[0299] User

[0300] The user checks the problem with the app and prepares data (e.g., screenshots, text data, and audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[0301] Terminal

[0302] The device receives data sent by the user and sends it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user.

[0303] server

[0304] The server uses a multimodal generation AI (e.g., OpenAI's GPT-3 (registered trademark) or DALL-E) to perform the following series of processes.

[0305] 1. Data Receipt and Analysis

[0306] The server receives screenshots, text data, and audio data sent from the device, analyzes the image data, recognizes specific elements on the screen (e.g., error messages), and extracts situation descriptions and keywords from the received text data.

[0307] 2. Use of Emotion Engine

[0308] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0309] 3. Identifying and Presenting Missing Information

[0310] The server identifies missing information based on image data, text data, and the results of emotion analysis. For example, if it determines that an error log has not been provided, it generates a request saying, "Please provide the error log from the crash." If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0311] 4. Receiving additional information and reanalyzing

[0312] If the user provides additional information (e.g., an error log), the terminal resends it to the server, which receives the additional information and re-analyzes all data. This re-analysis generates the final hearing item and provides it to the support staff.

[0313] 5. Generating and providing interview items

[0314] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and user's emotional state." These hearing items are provided to support personnel to support a fast and flexible response. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a fast response is required.

[0315] Specific examples

[0316] For example, when a user inquires about an app crashing, the specific process is as follows:

[0317] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[0318] 2. Terminal: Sends the data to the server.

[0319] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[0320] 4. Terminal: Displays requests from the server to the user.

[0321] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0322] 6. Terminal: Re-send the error log to the server.

[0323] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[0324] Through this process, the system automatically presents missing information in response to user inquiries, enabling a prompt and appropriate response.

[0325] An example of a prompt to be input to the generative AI model could be, "Please analyze the screenshot of the crash, the text message 'The app is crashing,' and the audio data 'I'm having trouble using the app,' to identify any additional information that is needed and provide the missing information to the user."

[0326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0327] Step 1:

[0328] The user checks the app for a problem and prepares data to explain the situation. For example, they could prepare a screenshot of the crash, text data such as "The app keeps crashing," and a voice message such as "I'm having trouble using the app." The user then enters this data into the device's inquiry form and submits it.

[0329] Input: Screenshots, text data, audio data

[0330] Output: User input data is sent

[0331] Step 2:

[0332] The device receives screenshots, text data, and audio data sent by the user. The device uploads the received data to the server via the network. It also has the function of displaying requests and notifications from the server to the user.

[0333] Input: Data submitted by the user

[0334] Output: Upload data to server, display notification to user

[0335] Step 3:

[0336] The server receives screenshots, text data, and audio data sent from the device. Using multimodal generative AI, the server analyzes the image data and recognizes specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords.

[0337] Input: Screenshots, text data, audio data

[0338] Output: Specific elements of image data, contextual descriptions and keywords of text data

[0339] Step 4:

[0340] The server analyzes the received text and voice data using an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0341] Input: Text data, audio data

[0342] Output: Recognition of the user's emotional state

[0343] Step 5:

[0344] The server identifies missing information based on the image data, text data, and the results of emotion analysis. If an error log is not provided, it determines that it is missing information and generates a request saying, "Please provide the error log from the crash." The server then presents this request to the user via their device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0345] Input: Image data, text data, emotion analysis results

[0346] Output: Missing information request message

[0347] Step 6:

[0348] The user provides additional information (for example, an error log), which the terminal then transmits to the server again. The user obtains the error log, enters it into the terminal, and transmits it.

[0349] Input: User-provided error log

[0350] Output: Send additional information to the server

[0351] Step 7:

[0352] The server receives the additional information and re-analyzes all the data, generating the final hearing items to provide to the support representative, including the error message, error log, crash description, and the user's emotional state.

[0353] Input: Additional information (e.g. error log)

[0354] Output: Generate and deliver the final hearing items

[0355] Through the above processing steps, the system is able to respond quickly and appropriately to inquiries from users.

[0356] (Application example 2)

[0357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] Conventional systems were inefficient in responding to user inquiries, particularly due to a lack of emotion recognition, which prevented them from providing appropriate support. This increased user dissatisfaction and risked a decline in the company's credibility. Furthermore, identifying missing information and requesting additional information was done manually, which took time to respond and made it difficult to provide efficient support. Furthermore, in-factory equipment maintenance requires a fast and appropriate response, but current systems are unable to meet this demand.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0360] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data and voice data sent from the user and analyzing them to extract specific keywords and emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, means for generating an appropriate support message according to the user's emotions based on the analysis results and the acquired additional information, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This enables automatic identification of missing information and flexible response according to the user's emotions.

[0361] A "user" is a person who uses the system to make an inquiry.

[0362] "Image data" is visual information such as screenshots or photographs of devices or systems that users submit.

[0363] "Text data" is information such as textual explanations or comments sent by users.

[0364] "Voice data" refers to voice messages and recordings sent by users.

[0365] A "server" is a central computing device that analyzes and manages data.

[0366] "Analysis" is the process of understanding the transmitted data and extracting specific information or states.

[0367] A "specific element" is a particularly important part or piece of information in image data.

[0368] "Keywords" are important words or phrases within the text data.

[0369] "Emotion" refers to the feelings or state that a user is experiencing, and is extracted from voice data or text data.

[0370] "Additional information" is supplementary data that the server requests the user to provide based on the analysis.

[0371] "Hearing items" are questions or confirmation items that the responder should ultimately ask the user.

[0372] "Responder" refers to the staff or system that responds to inquiries from users.

[0373] "Emotion analysis" is a process of recognizing a user's emotional state from voice data and text data.

[0374] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing emotions. This system is mainly composed of three components: a server, a terminal, and a user. The specific operation of each component and the overall system flow are explained below.

[0375] User

[0376] The user is a worker who uses this system to perform equipment maintenance. When a worker discovers a malfunction in the equipment, they use the smart glasses to capture a picture of the situation and explain the problem in audio. As a specific example of a malfunction, the user sends a voice message explaining the situation, such as "The machine is crashing," along with a screenshot of the crash, to the system via the smart glasses.

[0377] Terminal

[0378] The smart glasses (e.g., Google® Glass® Enterprise Edition) used as the terminal are responsible for receiving image and audio data sent by the user and transmitting this data to the server. The terminal also has the function of displaying requests and notifications from the server to the user.

[0379] server

[0380] The server performs the following sequence of operations:

[0381] 1. Data Receipt and Analysis

[0382] The server receives image data and audio data sent from the device. It uses TensorFlow and OpenCV for image analysis, and IBM Watson(R) Speech to Text for audio analysis. It also uses Microsoft(R) Azure(R) Emotion API for emotion recognition. These tools are used to extract specific elements in images (e.g., error messages) and specific keywords from audio, as well as the user's emotions.

[0383] 2. Identifying and providing missing information

[0384] The server identifies missing information based on the analysis results. For example, if an error log has not been provided, it determines that it is necessary. In this case, it generates a prompt message such as "Please provide the error log from the crash" and presents it to the user via the device. If emotion recognition reveals that the user is expressing negative emotions such as anxiety or anger, it creates a message requesting a more polite response.

[0385] 3. Receiving additional information and reanalyzing

[0386] If the user provides additional information (e.g., error logs) in response to a request from the system, the terminal again sends the data to the server, which then re-analyzes the additional information and generates the final hearing items based on all the data.

[0387] Examples:

[0388] An example of a specific prompt for a factory worker asking "The machine is crashing" is:

[0389] Image: "Please take a picture of the screen where the machine stops."

[0390] Voice: "Please describe the crash in a voice message."

[0391] The server analyzes this data, and if it determines that there is missing information, it generates a request, for example, "Please provide the error log from the crash," and notifies the user again via the terminal. The user provides the error log and submits it again, and the server reanalyzes it and provides the final hearing items to the responder.

[0392] This makes it possible for the entire system to automatically identify missing information and respond flexibly according to emotions.

[0393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0394] Step 1:

[0395] The user uses the smart glasses to take a picture of the equipment malfunction and explain the situation by voice. The user's device receives the image and voice data and sends it to the server.

[0396] Input: Image data and audio data of the defect

[0397] Output: Send data to the server

[0398] Step 2:

[0399] The server receives the image data and audio data sent by the user and analyzes them, using TensorFlow and OpenCV for image analysis and IBM Watson Speech to Text for audio analysis to extract specific elements, keywords, and emotions.

[0400] Input: Received data (image data, audio data)

[0401] Output: Analysis results (specific elements in images, keywords and emotions from audio)

[0402] Operation: Received image data is processed using image analysis software to identify error messages and abnormalities. Voice data is converted into text using voice recognition software, and keywords and user sentiment are extracted.

[0403] Step 3:

[0404] The server identifies missing information based on the analysis results. For example, if an error log is missing, it automatically generates a prompt to ask the user for that information. If necessary, it also creates a corresponding message taking into account the results of sentiment analysis.

[0405] Input: Analysis results (specific elements in the image, keywords and emotions from the audio)

[0406] Output: prompt (message requesting additional information), response message according to emotion

[0407] What it does: Checks the analysis results, determines missing information, generates prompts, and adjusts the content based on the results of sentiment analysis.

[0408] Step 4:

[0409] The terminal displays the prompt sent from the server to the user and requests any additional information required from the user. The user follows the instructions and provides additional information, such as an error log.

[0410] Input: Prompt statement (message requesting additional information), response message

[0411] Output: Additional information from the user (such as error logs)

[0412] Behavior: Displays a prompt and corresponding message to the user, prompting them for additional information.

[0413] Step 5:

[0414] The user again enters the requested additional information into the terminal, which then transmits it to the server.

[0415] Input: Additional information (error log, etc.)

[0416] Output: Sending data to the server again

[0417] Operation: The device receives additional information provided by the user and uploads it to the server.

[0418] Step 6:

[0419] The server again analyzes the additional information received and combines all the data to generate a final hearing item, which is then provided to the responder.

[0420] Input: Received data again (additional information)

[0421] Output: Final hearing items

[0422] What it does: Analyzes the additional information and integrates it with existing data to create a comprehensive hearing item that is sent to responders to ensure a rapid response.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0424] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0426] [Second embodiment]

[0427] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0428] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0429] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0431] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0433] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0434] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0435] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0438] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0439] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0440] System configuration and operation

[0441] User

[0442] The user checks the app for a problem and prepares data (such as screenshots and text) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0443] Terminal

[0444] The terminal is responsible for receiving data sent by the user and sending it to the server. The received screenshots and text data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[0445] server

[0446] The server plays a central role in the system by executing the following series of processes.

[0447] 1. Data Receipt and Analysis

[0448] The server receives screenshots and text data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen, such as error messages and important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (such as "crash").

[0449] 2. Identifying and providing missing information

[0450] The server identifies missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and presents it to the user via the terminal.

[0451] 3. Receiving additional information and reanalyzing

[0452] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing item and provides it to the responder.

[0453] 4. Generating and providing interview items

[0454] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0455] Specific examples

[0456] For example, when a user inquires about an app crashing, the specific process is as follows:

[0457] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0458] 2. Terminal: Sends the data to the server.

[0459] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0460] 4. Terminal: Displays requests from the server to the user.

[0461] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0462] 6. Terminal: Re-send the error log to the server.

[0463] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0464] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0465] The processing flow will be explained below.

[0466] Step 1:

[0467] The user checks the application for a problem and prepares screenshots and text data to show the situation. Specifically, the user takes a screenshot of the moment the application crashes and writes a description that reads, "The application crashes."

[0468] Step 2:

[0469] The user inputs the screenshot and text data prepared using the terminal into the inquiry form and sends it to the system.

[0470] Step 3:

[0471] The terminal receives the screenshot and text data sent by the user.

[0472] Step 4:

[0473] The terminal uploads the received data via the network to send it to the server.

[0474] Step 5:

[0475] The server receives the screenshot and text data sent from the terminal.

[0476] Step 6:

[0477] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[0478] Step 7:

[0479] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[0480] Step 8:

[0481] The server identifies missing information based on the analysis of the image data and text data, for example, if an error log is not provided.

[0482] Step 9:

[0483] The server generates a message to ask the user for missing information, for example, making a specific request such as "Please provide the error log from the crash."

[0484] Step 10:

[0485] The terminal receives the request message from the server and displays it to the user.

[0486] Step 11:

[0487] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[0488] Step 12:

[0489] The terminal receives additional information from the user and retransmits it to the server.

[0490] Step 13:

[0491] The server receives the additional information sent by the terminal and analyzes all the data again.

[0492] Step 14:

[0493] The server generates the final hearing items based on the reanalysis results, such as "the error code and detailed description of the situation that is likely to have caused the crash."

[0494] Step 15:

[0495] The server prepares the generated final hearing items to be provided to the responder.

[0496] Step 16:

[0497] The responder responds quickly and accurately based on the hearing items provided by the server.

[0498] Example 1

[0499] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0500] In conventional inquiry response systems, the information about the problem reported by the user is often insufficient, which forces the responder to request additional information each time, resulting in delayed responses. Furthermore, when the problem is complex, simple text data alone does not provide sufficient information, making it difficult for the responder to grasp the details. This increases the amount of back-and-forth communication between the user and the responder, resulting in reduced response efficiency.

[0501] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0502] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder, means for receiving and reanalyzing the additional information from the user, and means for generating final hearing items and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate final hearing items.

[0503] "Image data" refers to data containing visual information such as screenshots that are sent by a user when reporting a problem with an application.

[0504] "Text data" is data containing character information that is sent when a user writes an explanation or detailed information about a problem in an application.

[0505] A "specific element" is an important part contained in image data, such as an error message or an important user interface element.

[0506] "Keywords" are important words or phrases that a user writes in text data, such as "crash" or "error message."

[0507] A "multimodal generative AI model" is an artificial intelligence model for analyzing both image data and text data, and has the ability to extract and analyze information from these data.

[0508] "Insufficient information" refers to information that is not sufficient for the person in charge to understand the details of the problem from the data initially provided by the user, and that must be provided additionally.

[0509] "Additional information" refers to detailed information, such as an error log or further explanation, that the server provides in response to a user's request for missing information.

[0510] "Hearing items" refers to a series of questions and confirmations that are generated by the server based on analysis data and that are required by the responder to respond to the problem.

[0511] The term "responder" refers to an agent or system administrator who responds to inquiries from users and provides support to resolve problems.

[0512] "Re-analysis" refers to the process in which the server re-analyzes the additional information provided by the user, thereby reconfirming the overall situation and generating the final hearing items.

[0513] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0514] System configuration and operation

[0515] User

[0516] The user prepares image data (e.g., screenshots) and text data (e.g., detailed description of the problem) to report an app malfunction. The user enters this data into an inquiry form via their device and sends it to the system. As a specific example of the malfunction, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0517] Terminal

[0518] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the Internet. The device also has the function of displaying requests and notifications from the server to the user.

[0519] server

[0520] The server plays a central role in the system and performs the following series of processes.

[0521] 1. Data Receipt and Analysis

[0522] The server receives the screenshot and text data sent from the device. It then uses a multimodal generative AI model to analyze the image data and recognize specific elements on the screen (e.g., error messages or important UI elements). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[0523] 2. Identifying and providing missing information

[0524] The server identifies missing information based on the received and analyzed information. For example, if an error log is not provided, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and displays it to the user via the terminal.

[0525] 3. Receiving additional information and reanalyzing

[0526] If the user provides additional information (e.g., error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing items and provides them to the responder.

[0527] 4. Generating and providing interview items

[0528] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0529] Specific examples

[0530] As a concrete example, the flow when a user makes an inquiry about "my app crashes" is shown below.

[0531] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0532] 2. Terminal: Sends the data to the server.

[0533] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0534] 4. Terminal: Displays requests from the server to the user.

[0535] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0536] 6. Terminal: Re-send the error log to the server.

[0537] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0538] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] To report an app malfunction, a user prepares a screenshot and text data describing the situation. Specifically, the user captures a screenshot of the moment the app crashes and writes an explanation such as "The app crashes" in the input form. After entering the necessary information in this form, the user presses the send button to send the data to the device.

[0542] Step 2:

[0543] The device receives the screenshot and text data sent by the user. This received data is uploaded to a server via the Internet. Specifically, an HTTP request is generated, the user's sent data is attached to it, and it is sent to the server. The input is the user's screenshot and text data, and the output is an HTTP request to the server.

[0544] Step 3:

[0545] The server receives data sent from the device. It classifies the received data and uses a multimodal generative AI model to analyze image data. The AI ​​model identifies error messages and important UI elements from screenshots. It also analyzes text data using natural language processing techniques to extract situation descriptions and keywords. The input is image data and text data from the device, and the output is error messages and keywords as the analysis results.

[0546] Step 4:

[0547] The server identifies missing information based on the analysis results. For example, if the analysis does not provide an error log, it determines that it is necessary. The server generates a request message saying, "Please provide the error log at the time of the crash," and sends it to the terminal. The input is the analysis result, and the output is a request message requesting additional information.

[0548] Step 5:

[0549] The terminal receives the request from the server and displays the contents to the user. Specifically, it presents the user with a pop-up notification or a prompt message on the screen saying "Please provide the error log in the event of a crash." The input is the request statement from the server, and the output is the notification to the user.

[0550] Step 6:

[0551] The user obtains the error log according to the instructions and sends it again via the terminal. The user selects the error log file and uploads it to the inquiry form as additional information. The user presses the send button again to send the data to the terminal. The input is the error log file, and the output is the data sent to the terminal.

[0552] Step 7:

[0553] The terminal receives additional information (error log) sent by the user again and uploads it to the server again. The input is the error log from the user, and the output is an HTTP request to the server.

[0554] Step 8:

[0555] The server receives the additional information and re-analyzes the data, including the results of the previous analysis. Using a multimodal generative AI model, it re-analyzes all data, including the added error log, and reconfirms the overall situation. The input is the additional information and the initial data, and the output is the re-analysis results.

[0556] Step 9:

[0557] The server generates hearing items based on the final analysis results. Specifically, it integrates the error message, error log, crash description, etc. provided by the user, and compiles all the information required by the responder into a single list. The input is the reanalysis results, and the output is a list of hearing items.

[0558] Step 10:

[0559] The server provides the final hearing items to the responder, who can then respond quickly and accurately based on the hearing items. The input is a list of hearing items, and the output is information provided to the responder.

[0560] This series of processes enables the system to automatically present missing information in response to user inquiries and efficiently generate final interview items, resulting in a fast and accurate response.

[0561] (Application example 1)

[0562] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0563] In conventional inquiry response systems, if the information sent by the user is insufficient, the responder must request additional information each time, which is inefficient and tends to result in long response times. Furthermore, when supporting security devices, analyzing image data and text data is particularly time-consuming, which also hinders prompt responses. The present invention aims to solve these problems and improve the efficiency of inquiry responses.

[0564] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0565] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating interview items based on the analysis results and the acquired additional information and providing them to a responder, and means installed on a smart device and applied to inquiries regarding security equipment support. This enables efficient processing of inquiries regarding security equipment and fast and accurate support.

[0566] "User" means an individual or organization that uses the system.

[0567] "Image data" is data containing visual information sent by a user.

[0568] "Text data" refers to data containing text information sent by a user.

[0569] The "receiving means" is a device or software that has the function of acquiring data sent from a user.

[0570] The "analyzing means" is a device or software that has the function of analyzing received data and recognizing specific elements or keywords.

[0571] The "specific elements" are important information elements contained in the image data and text data.

[0572] "Missing information" is information that is needed to answer a user's inquiry but that the user has not provided.

[0573] "Additional information" is information that the user is asked to provide to supplement the missing information.

[0574] "Hearing items" are questions and confirmations that are necessary for the responder to answer the user's inquiry.

[0575] A "responder" is a person or system that provides an answer to a user's inquiry.

[0576] The term "system" refers to a collection of hardware and software that constitutes the entire present invention.

[0577] "Analysis results" are information obtained from the analysis of received data.

[0578] A "smart device" is a device with internet connectivity, such as a phone, tablet, or smart glasses.

[0579] "Security equipment" refers to devices such as cameras and sensors that are installed to prevent fraud and accidents.

[0580] "Support" is the activity of providing assistance and solutions to user inquiries and problems.

[0581] The present invention provides a system for efficiently responding to inquiries regarding security device support by utilizing image data and text data sent by users. This system is comprised of three entities: a server, a terminal, and a user.

[0582] User

[0583] A user checks for a problem with a security device (e.g., a home security camera) and prepares data (e.g., screenshots and error messages) to explain the situation. The user enters this data into an inquiry form via a smart device and sends it to the system. For example, the user sends a description of the situation, such as "The camera cannot connect," along with a screenshot of the connection error.

[0584] Terminal

[0585] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user. Smartphones and tablets are used as the hardware for this purpose.

[0586] server

[0587] The server plays a central role in the system by executing the following series of processes: To analyze the received data, the server uses TensorFlow for image recognition and NLTK (Natural Language Toolkit) for text analysis.

[0588] 1. Data Receipt and Analysis

[0589] The server receives the screenshot and text data sent from the device. It then uses a generative AI model to analyze the image data and recognize specific elements on the screen, such as error messages or important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "Connection Error").

[0590] 2. Identifying and providing missing information

[0591] The server identifies any missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log for the connection error," and presents it to the user via the terminal. An example of a generated prompt sentence is as follows:

[0592] Please upload a screenshot of the problem.

[0593] Enter the text of the error message.

[0594] Press "Next" and provide any additional information required.

[0595] 3. Receiving additional information and reanalyzing

[0596] If the user provides additional information (for example, an error log), the terminal sends it again to the server, which receives the additional information and analyzes the entire data again.

[0597] 4. Generating and providing interview items

[0598] The server generates a questionnaire based on the final analysis results, including details of the security camera connection error, error logs, and a description of the connection status. These questionnaires are provided to support personnel to assist in a quick and accurate response.

[0599] In this way, the present invention is a system that can automatically present missing information in response to inquiries about security equipment and efficiently generate final hearing items, thereby speeding up inquiry responses and improving user satisfaction.

[0600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0601] Step 1:

[0602] A user uses a smart device to report a security equipment malfunction. Specifically, the user inputs and sends a screenshot of the security camera's connection error screen and text data such as "Camera cannot connect." The input data is the screenshot image and the error message text.

[0603] Step 2:

[0604] The terminal receives screenshots and text data sent by the user. The input data is the screenshot image and text data provided by the user. After receiving this data, the terminal uploads it to the server via the network. The output data is the data transmitted to the server.

[0605] Step 3:

[0606] The server receives image data and text data sent from the device. The input data is the image data and text data sent from the device. The server uses TensorFlow to analyze the image data and recognize specific elements on the screen (e.g., error messages and UI elements). It also uses NLTK to analyze the text data and extract important keywords and situation descriptions. The output data are the image analysis results and text analysis results.

[0607] Step 4:

[0608] The server identifies missing information based on the analysis results of the image data and text data. The input data are the image analysis results and the text analysis results. Specifically, it recognizes that an error log has not been provided and generates a prompt to obtain additional information, such as "Please provide the error log in the event of a connection error." The output data is the generated prompt.

[0609] Step 5:

[0610] The terminal displays the request from the server to the user. The input data is the prompt received from the server. The terminal displays the prompt to the user, requesting additional information. The output data is the prompt displayed to the user.

[0611] Step 6:

[0612] Based on the request from the server, the user obtains the necessary additional information (for example, an error log), enters it into the terminal again, and transmits it. The input data is the error log obtained by the user.

[0613] Step 7:

[0614] The terminal receives additional information sent by the user and sends it back to the server. The input data is the error log sent by the user. The output data is the data sent to the server.

[0615] Step 8:

[0616] The server receives the data again and performs re-analysis. The input data is the error log provided as additional information. The server analyzes the entire data and generates the final hearing item. The output data is the final hearing item.

[0617] Step 9:

[0618] The server provides the generated hearing items to the responder. The input data is the final hearing items. The server provides this to the support staff to help the responder solve the user's problem quickly and accurately. The output data is the final hearing items shared between the user and the responder.

[0619] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0620] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing the user's emotions. It automatically analyzes image data and text data sent by the user, identifies missing information, presents additional information to the user, and generates final interview items to provide to the responder. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and improves the quality of inquiry responses based on those emotions.

[0621] System configuration and operation

[0622] User

[0623] The user checks the problem with the app and prepares data (for example, screenshots, text data, or audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[0624] Terminal

[0625] The terminal is responsible for receiving data sent by the user and sending it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[0626] server

[0627] The server executes the following series of processes.

[0628] 1. Data Receipt and Analysis

[0629] The server receives screenshots, text data, and audio data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[0630] 2. Use of Emotion Engine

[0631] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0632] 3. Identifying and Presenting Missing Information

[0633] The server identifies missing information based on the image data, text data, and the results of emotion analysis. For example, if an error log is not provided, it determines that it is needed. To obtain the missing information, the server generates a message such as "Please provide the error log from the crash" and displays it to the user via the device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0634] 4. Receiving additional information and reanalyzing

[0635] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and re-analyzes all the data. This re-analysis generates the final hearing item and provides it to the responder.

[0636] 5. Generating and providing interview items

[0637] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and the user's emotional state." These hearing items are provided to support personnel to help them respond quickly and flexibly. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a prompt response is required.

[0638] Specific examples

[0639] For example, when a user inquires about an app crashing, the specific process is as follows:

[0640] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[0641] 2. Terminal: Sends the data to the server.

[0642] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[0643] 4. Terminal: Displays requests from the server to the user.

[0644] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0645] 6. Terminal: Re-send the error log to the server.

[0646] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[0647] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final interview items, thereby improving the efficiency and quality of inquiry responses.In addition, by analyzing user emotions, it is possible to provide more appropriate responses.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] The user checks the application for a problem and prepares a screenshot, text data, and audio data to show the situation. For example, the user takes a screenshot of the moment the application crashes, and creates an explanatory message saying "The application is crashing" and an audio message saying "I'm having trouble using the application."

[0651] Step 2:

[0652] The user inputs the screenshot, text data, and voice data prepared using the terminal into the inquiry form and sends them to the system.

[0653] Step 3:

[0654] The terminal receives the screenshot, text data, and audio data sent by the user.

[0655] Step 4:

[0656] The terminal uploads the received data via the network to send it to the server.

[0657] Step 5:

[0658] The server receives the screenshot, text data, and audio data sent from the terminal.

[0659] Step 6:

[0660] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[0661] Step 7:

[0662] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[0663] Step 8:

[0664] The server analyzes the voice data and uses an emotion engine to recognize the user's emotions, for example, identifying that the user is feeling anxious.

[0665] Step 9:

[0666] The server identifies missing information based on the image data, text data, and sentiment analysis results, for example, if an error log is not provided, and additional information is required.

[0667] Step 10:

[0668] The server generates a message requesting the user for missing information, such as "Please provide the error log of the crash." If the emotion engine detects negative emotions from the user, the message is more polite.

[0669] Step 11:

[0670] The terminal receives the request message from the server and displays it to the user.

[0671] Step 12:

[0672] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[0673] Step 13:

[0674] The terminal receives the additional information sent by the user and retransmits it to the server.

[0675] Step 14:

[0676] The server receives the additional information sent by the terminal and re-analyzes all the data.

[0677] Step 15:

[0678] The server generates the final hearing items based on the reanalysis results, for example, items including "error message, error log, crash description, and user's emotional state."

[0679] Step 16:

[0680] The server prepares to provide the generated final hearing items to the responder, including a notification to prompt a response, especially if the user's sentiment is negative.

[0681] Step 17:

[0682] The responder responds quickly and accurately based on the interview items provided by the server, and communicates appropriately after understanding the user's emotional state.

[0683] Example 2

[0684] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0685] In many modern systems, responding to user inquiries is done manually and is inefficient. Furthermore, responses are often made without considering the user's feelings, making it difficult to provide appropriate support. Furthermore, necessary information is often not provided at the time of inquiry, resulting in multiple exchanges and delays in response.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0687] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for receiving voice data and analyzing it to recognize the user's emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate hearing items while responding appropriately to the user's emotions.

[0688] "User" refers to an individual or corporation that uses the system to make an inquiry.

[0689] "Image data" refers to visual information such as screenshots and photo data sent by users.

[0690] "Text data" refers to sentences and character information entered by the user.

[0691] "Audio Data" refers to audio recordings or speech data that a user transmits to the system.

[0692] "Multimodal generation AI" refers to artificial intelligence that can simultaneously analyze and generate multiple modalities, such as image data and text data.

[0693] "Specific elements" refer to parts or information that play an important role in image data, such as error messages or specific icons.

[0694] An "emotion engine" refers to a software module that analyzes voice and text data to recognize the user's emotions.

[0695] "Analysis" refers to the act of processing data and extracting specific information or features.

[0696] "Hearing items" refer to important information and questions that the support staff should collect from the user.

[0697] "Additional information" refers to any additional data or information that was not included in the initial enquiry but is necessary to provide effective support.

[0698] "Responder" refers to a support staff member or engineer who responds to inquiries from users.

[0699] The present invention provides a system for improving the efficiency of user inquiry responses and providing appropriate support by recognizing the user's emotions. This system receives image data, text data, and voice data sent by the user, analyzes them to identify necessary information, and generates final hearing items to provide to the responder.

[0700] System configuration

[0701] This system mainly consists of users, terminals, and servers. Details of each component are as follows:

[0702] User

[0703] The user checks the problem with the app and prepares data (e.g., screenshots, text data, and audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[0704] Terminal

[0705] The device receives data sent by the user and sends it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user.

[0706] server

[0707] The server uses a multimodal generation AI (e.g., OpenAI's GPT-3 or DALL-E) to perform the following series of processes:

[0708] 1. Data Receipt and Analysis

[0709] The server receives screenshots, text data, and audio data sent from the device, analyzes the image data, recognizes specific elements on the screen (e.g., error messages), and extracts situation descriptions and keywords from the received text data.

[0710] 2. Use of Emotion Engine

[0711] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0712] 3. Identifying and Presenting Missing Information

[0713] The server identifies missing information based on image data, text data, and the results of emotion analysis. For example, if it determines that an error log has not been provided, it generates a request saying, "Please provide the error log from the crash." If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0714] 4. Receiving additional information and reanalyzing

[0715] If the user provides additional information (e.g., an error log), the terminal resends it to the server, which receives the additional information and re-analyzes all data. This re-analysis generates the final hearing item and provides it to the support staff.

[0716] 5. Generating and providing interview items

[0717] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and user's emotional state." These hearing items are provided to support personnel to support a fast and flexible response. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a fast response is required.

[0718] Specific examples

[0719] For example, when a user inquires about an app crashing, the specific process is as follows:

[0720] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[0721] 2. Terminal: Sends the data to the server.

[0722] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[0723] 4. Terminal: Displays requests from the server to the user.

[0724] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0725] 6. Terminal: Re-send the error log to the server.

[0726] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[0727] Through this process, the system automatically presents missing information in response to user inquiries, enabling a prompt and appropriate response.

[0728] An example of a prompt to be input to the generative AI model could be, "Please analyze the screenshot of the crash, the text message 'The app is crashing,' and the audio data 'I'm having trouble using the app,' to identify any additional information that is needed and provide the missing information to the user."

[0729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0730] Step 1:

[0731] The user checks the app for a problem and prepares data to explain the situation. For example, they could prepare a screenshot of the crash, text data such as "The app keeps crashing," and a voice message such as "I'm having trouble using the app." The user then enters this data into the device's inquiry form and submits it.

[0732] Input: Screenshots, text data, audio data

[0733] Output: User input data is sent

[0734] Step 2:

[0735] The device receives screenshots, text data, and audio data sent by the user. The device uploads the received data to the server via the network. It also has the function of displaying requests and notifications from the server to the user.

[0736] Input: Data submitted by the user

[0737] Output: Upload data to server, display notification to user

[0738] Step 3:

[0739] The server receives screenshots, text data, and audio data sent from the device. Using multimodal generative AI, the server analyzes the image data and recognizes specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords.

[0740] Input: Screenshots, text data, audio data

[0741] Output: Specific elements of image data, contextual descriptions and keywords of text data

[0742] Step 4:

[0743] The server analyzes the received text and voice data using an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[0744] Input: Text data, audio data

[0745] Output: Recognition of the user's emotional state

[0746] Step 5:

[0747] The server identifies missing information based on the image data, text data, and the results of emotion analysis. If an error log is not provided, it determines that it is missing information and generates a request saying, "Please provide the error log from the crash." The server then presents this request to the user via their device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[0748] Input: Image data, text data, emotion analysis results

[0749] Output: Missing information request message

[0750] Step 6:

[0751] The user provides additional information (for example, an error log), which the terminal then transmits to the server again. The user obtains the error log, enters it into the terminal, and transmits it.

[0752] Input: User-provided error log

[0753] Output: Send additional information to the server

[0754] Step 7:

[0755] The server receives the additional information and re-analyzes all the data, generating the final hearing items to provide to the support representative, including the error message, error log, crash description, and the user's emotional state.

[0756] Input: Additional information (e.g. error log)

[0757] Output: Generate and deliver the final hearing items

[0758] Through the above processing steps, the system is able to respond quickly and appropriately to inquiries from users.

[0759] (Application example 2)

[0760] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0761] Conventional systems were inefficient in responding to user inquiries, particularly due to a lack of emotion recognition, which prevented them from providing appropriate support. This increased user dissatisfaction and risked a decline in the company's credibility. Furthermore, identifying missing information and requesting additional information was done manually, which took time to respond and made it difficult to provide efficient support. Furthermore, in-factory equipment maintenance requires a fast and appropriate response, but current systems are unable to meet this demand.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0763] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data and voice data sent from the user and analyzing them to extract specific keywords and emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, means for generating an appropriate support message according to the user's emotions based on the analysis results and the acquired additional information, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This enables automatic identification of missing information and flexible response according to the user's emotions.

[0764] A "user" is a person who uses the system to make an inquiry.

[0765] "Image data" is visual information such as screenshots or photographs of devices or systems that users submit.

[0766] "Text data" is information such as textual explanations or comments sent by users.

[0767] "Voice data" refers to voice messages and recordings sent by users.

[0768] A "server" is a central computing device that analyzes and manages data.

[0769] "Analysis" is the process of understanding the transmitted data and extracting specific information or states.

[0770] A "specific element" is a particularly important part or piece of information in image data.

[0771] "Keywords" are important words or phrases within the text data.

[0772] "Emotion" refers to the feelings or state that a user is experiencing, and is extracted from voice data or text data.

[0773] "Additional information" is supplementary data that the server requests the user to provide based on the analysis.

[0774] "Hearing items" are questions or confirmation items that the responder should ultimately ask the user.

[0775] "Responder" refers to the staff or system that responds to inquiries from users.

[0776] "Emotion analysis" is a process of recognizing a user's emotional state from voice data and text data.

[0777] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing emotions. This system is mainly composed of three components: a server, a terminal, and a user. The specific operation of each component and the overall system flow are explained below.

[0778] User

[0779] The user is a worker who uses this system to perform equipment maintenance. When a worker discovers a malfunction in the equipment, they use the smart glasses to capture a picture of the situation and explain the problem in audio. As a specific example of a malfunction, the user sends a voice message explaining the situation, such as "The machine is crashing," along with a screenshot of the crash, to the system via the smart glasses.

[0780] Terminal

[0781] The smart glasses (e.g., Google Glass Enterprise Edition) used as the terminal are responsible for receiving image and audio data sent by the user and transmitting this data to the server. The terminal also has the function of displaying requests and notifications from the server to the user.

[0782] server

[0783] The server performs the following sequence of operations:

[0784] 1. Data Receipt and Analysis

[0785] The server receives image and audio data sent from the device. It uses TensorFlow and OpenCV for image analysis, and IBM Watson Speech to Text for audio analysis. It also uses the Microsoft Azure Emotion API for emotion recognition. These tools are used to extract specific elements in images (e.g., error messages) and specific keywords from audio, as well as the user's emotions.

[0786] 2. Identifying and providing missing information

[0787] The server identifies missing information based on the analysis results. For example, if an error log has not been provided, it determines that it is necessary. In this case, it generates a prompt message such as "Please provide the error log from the crash" and presents it to the user via the device. If emotion recognition reveals that the user is expressing negative emotions such as anxiety or anger, it creates a message requesting a more polite response.

[0788] 3. Receiving additional information and reanalyzing

[0789] If the user provides additional information (e.g., error logs) in response to a request from the system, the terminal again sends the data to the server, which then re-analyzes the additional information and generates the final hearing items based on all the data.

[0790] Examples:

[0791] An example of a specific prompt for a factory worker asking "The machine is crashing" is:

[0792] Image: "Please take a picture of the screen where the machine stops."

[0793] Voice: "Please describe the crash in a voice message."

[0794] The server analyzes this data, and if it determines that there is missing information, it generates a request, for example, "Please provide the error log from the crash," and notifies the user again via the terminal. The user provides the error log and submits it again, and the server reanalyzes it and provides the final hearing items to the responder.

[0795] This makes it possible for the entire system to automatically identify missing information and respond flexibly according to emotions.

[0796] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0797] Step 1:

[0798] The user uses the smart glasses to take a picture of the equipment malfunction and explain the situation by voice. The user's device receives the image and voice data and sends it to the server.

[0799] Input: Image data and audio data of the defect

[0800] Output: Send data to the server

[0801] Step 2:

[0802] The server receives the image data and audio data sent by the user and analyzes them, using TensorFlow and OpenCV for image analysis and IBM Watson Speech to Text for audio analysis to extract specific elements, keywords, and emotions.

[0803] Input: Received data (image data, audio data)

[0804] Output: Analysis results (specific elements in images, keywords and emotions from audio)

[0805] Operation: Received image data is processed using image analysis software to identify error messages and abnormalities. Voice data is converted into text using voice recognition software, and keywords and user sentiment are extracted.

[0806] Step 3:

[0807] The server identifies missing information based on the analysis results. For example, if an error log is missing, it automatically generates a prompt to ask the user for that information. If necessary, it also creates a corresponding message taking into account the results of sentiment analysis.

[0808] Input: Analysis results (specific elements in the image, keywords and emotions from the audio)

[0809] Output: prompt (message requesting additional information), response message according to emotion

[0810] What it does: Checks the analysis results, determines missing information, generates prompts, and adjusts the content based on the results of sentiment analysis.

[0811] Step 4:

[0812] The terminal displays the prompt sent from the server to the user and requests any additional information required from the user. The user follows the instructions and provides additional information, such as an error log.

[0813] Input: Prompt statement (message requesting additional information), response message

[0814] Output: Additional information from the user (such as error logs)

[0815] Behavior: Displays a prompt and corresponding message to the user, prompting them for additional information.

[0816] Step 5:

[0817] The user again enters the requested additional information into the terminal, which then transmits it to the server.

[0818] Input: Additional information (error log, etc.)

[0819] Output: Sending data to the server again

[0820] Operation: The device receives additional information provided by the user and uploads it to the server.

[0821] Step 6:

[0822] The server again analyzes the additional information received and combines all the data to generate a final hearing item, which is then provided to the responder.

[0823] Input: Received data again (additional information)

[0824] Output: Final hearing items

[0825] What it does: Analyzes the additional information and integrates it with existing data to create a comprehensive hearing item that is sent to responders to ensure a rapid response.

[0826] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0827] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0828] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0832] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0833] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0834] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0835] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0836] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0837] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0838] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0839] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0840] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0841] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0842] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0843] System configuration and operation

[0844] User

[0845] The user checks the app for a problem and prepares data (such as screenshots and text) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0846] Terminal

[0847] The terminal is responsible for receiving data sent by the user and sending it to the server. The received screenshots and text data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[0848] server

[0849] The server plays a central role in the system by executing the following series of processes.

[0850] 1. Data Receipt and Analysis

[0851] The server receives screenshots and text data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen, such as error messages and important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (such as "crash").

[0852] 2. Identifying and providing missing information

[0853] The server identifies missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and presents it to the user via the terminal.

[0854] 3. Receiving additional information and reanalyzing

[0855] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing item and provides it to the responder.

[0856] 4. Generating and providing interview items

[0857] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0858] Specific examples

[0859] For example, when a user inquires about an app crashing, the specific process is as follows:

[0860] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0861] 2. Terminal: Sends the data to the server.

[0862] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0863] 4. Terminal: Displays requests from the server to the user.

[0864] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0865] 6. Terminal: Re-send the error log to the server.

[0866] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0867] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0868] The processing flow will be explained below.

[0869] Step 1:

[0870] The user checks the application for a problem and prepares screenshots and text data to show the situation. Specifically, the user takes a screenshot of the moment the application crashes and writes a description that reads, "The application crashes."

[0871] Step 2:

[0872] The user inputs the screenshot and text data prepared using the terminal into the inquiry form and sends it to the system.

[0873] Step 3:

[0874] The terminal receives the screenshot and text data sent by the user.

[0875] Step 4:

[0876] The terminal uploads the received data via the network to send it to the server.

[0877] Step 5:

[0878] The server receives the screenshot and text data sent from the terminal.

[0879] Step 6:

[0880] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[0881] Step 7:

[0882] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[0883] Step 8:

[0884] The server identifies missing information based on the analysis of the image data and text data, for example, if an error log is not provided.

[0885] Step 9:

[0886] The server generates a message to ask the user for missing information, for example, making a specific request such as "Please provide the error log from the crash."

[0887] Step 10:

[0888] The terminal receives the request message from the server and displays it to the user.

[0889] Step 11:

[0890] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[0891] Step 12:

[0892] The terminal receives additional information from the user and retransmits it to the server.

[0893] Step 13:

[0894] The server receives the additional information sent by the terminal and analyzes all the data again.

[0895] Step 14:

[0896] The server generates the final hearing items based on the reanalysis results, such as "the error code and detailed description of the situation that is likely to have caused the crash."

[0897] Step 15:

[0898] The server prepares the generated final hearing items to be provided to the responder.

[0899] Step 16:

[0900] The responder responds quickly and accurately based on the hearing items provided by the server.

[0901] Example 1

[0902] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0903] In conventional inquiry response systems, the information about the problem reported by the user is often insufficient, which forces the responder to request additional information each time, resulting in delayed responses. Furthermore, when the problem is complex, simple text data alone does not provide sufficient information, making it difficult for the responder to grasp the details. This increases the amount of back-and-forth communication between the user and the responder, resulting in reduced response efficiency.

[0904] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0905] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder, means for receiving and reanalyzing the additional information from the user, and means for generating final hearing items and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate final hearing items.

[0906] "Image data" refers to data containing visual information such as screenshots that are sent by a user when reporting a problem with an application.

[0907] "Text data" is data containing character information that is sent when a user writes an explanation or detailed information about a problem in an application.

[0908] A "specific element" is an important part contained in image data, such as an error message or an important user interface element.

[0909] "Keywords" are important words or phrases that a user writes in text data, such as "crash" or "error message."

[0910] A "multimodal generative AI model" is an artificial intelligence model for analyzing both image data and text data, and has the ability to extract and analyze information from these data.

[0911] "Insufficient information" refers to information that is not sufficient for the person in charge to understand the details of the problem from the data initially provided by the user, and that must be provided additionally.

[0912] "Additional information" refers to detailed information, such as an error log or further explanation, that the server provides in response to a user's request for missing information.

[0913] "Hearing items" refers to a series of questions and confirmations that are generated by the server based on analysis data and that are required by the responder to respond to the problem.

[0914] The term "responder" refers to an agent or system administrator who responds to inquiries from users and provides support to resolve problems.

[0915] "Re-analysis" refers to the process in which the server re-analyzes the additional information provided by the user, thereby reconfirming the overall situation and generating the final hearing items.

[0916] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[0917] System configuration and operation

[0918] User

[0919] The user prepares image data (e.g., screenshots) and text data (e.g., detailed description of the problem) to report an app malfunction. The user enters this data into an inquiry form via their device and sends it to the system. As a specific example of the malfunction, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[0920] Terminal

[0921] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the Internet. The device also has the function of displaying requests and notifications from the server to the user.

[0922] server

[0923] The server plays a central role in the system and performs the following series of processes.

[0924] 1. Data Receipt and Analysis

[0925] The server receives the screenshot and text data sent from the device. It then uses a multimodal generative AI model to analyze the image data and recognize specific elements on the screen (e.g., error messages or important UI elements). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[0926] 2. Identifying and providing missing information

[0927] The server identifies missing information based on the received and analyzed information. For example, if an error log is not provided, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and displays it to the user via the terminal.

[0928] 3. Receiving additional information and reanalyzing

[0929] If the user provides additional information (e.g., error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing items and provides them to the responder.

[0930] 4. Generating and providing interview items

[0931] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[0932] Specific examples

[0933] As a concrete example, the flow when a user makes an inquiry about "my app crashes" is shown below.

[0934] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[0935] 2. Terminal: Sends the data to the server.

[0936] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[0937] 4. Terminal: Displays requests from the server to the user.

[0938] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[0939] 6. Terminal: Re-send the error log to the server.

[0940] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[0941] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[0942] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0943] Step 1:

[0944] To report an app malfunction, a user prepares a screenshot and text data describing the situation. Specifically, the user captures a screenshot of the moment the app crashes and writes an explanation such as "The app crashes" in the input form. After entering the necessary information in this form, the user presses the send button to send the data to the device.

[0945] Step 2:

[0946] The device receives the screenshot and text data sent by the user. This received data is uploaded to a server via the Internet. Specifically, an HTTP request is generated, the user's sent data is attached to it, and it is sent to the server. The input is the user's screenshot and text data, and the output is an HTTP request to the server.

[0947] Step 3:

[0948] The server receives data sent from the device. It classifies the received data and uses a multimodal generative AI model to analyze image data. The AI ​​model identifies error messages and important UI elements from screenshots. It also analyzes text data using natural language processing techniques to extract situation descriptions and keywords. The input is image data and text data from the device, and the output is error messages and keywords as the analysis results.

[0949] Step 4:

[0950] The server identifies missing information based on the analysis results. For example, if the analysis does not provide an error log, it determines that it is necessary. The server generates a request message saying, "Please provide the error log at the time of the crash," and sends it to the terminal. The input is the analysis result, and the output is a request message requesting additional information.

[0951] Step 5:

[0952] The terminal receives the request from the server and displays the contents to the user. Specifically, it presents the user with a pop-up notification or a prompt message on the screen saying "Please provide the error log in the event of a crash." The input is the request statement from the server, and the output is the notification to the user.

[0953] Step 6:

[0954] The user obtains the error log according to the instructions and sends it again via the terminal. The user selects the error log file and uploads it to the inquiry form as additional information. The user presses the send button again to send the data to the terminal. The input is the error log file, and the output is the data sent to the terminal.

[0955] Step 7:

[0956] The terminal receives additional information (error log) sent by the user again and uploads it to the server again. The input is the error log from the user, and the output is an HTTP request to the server.

[0957] Step 8:

[0958] The server receives the additional information and re-analyzes the data, including the results of the previous analysis. Using a multimodal generative AI model, it re-analyzes all data, including the added error log, and reconfirms the overall situation. The input is the additional information and the initial data, and the output is the re-analysis results.

[0959] Step 9:

[0960] The server generates hearing items based on the final analysis results. Specifically, it integrates the error message, error log, crash description, etc. provided by the user, and compiles all the information required by the responder into a single list. The input is the reanalysis results, and the output is a list of hearing items.

[0961] Step 10:

[0962] The server provides the final hearing items to the responder, who can then respond quickly and accurately based on the hearing items. The input is a list of hearing items, and the output is information provided to the responder.

[0963] This series of processes enables the system to automatically present missing information in response to user inquiries and efficiently generate final interview items, resulting in a fast and accurate response.

[0964] (Application example 1)

[0965] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0966] In conventional inquiry response systems, if the information sent by the user is insufficient, the responder must request additional information each time, which is inefficient and tends to result in long response times. Furthermore, when supporting security devices, analyzing image data and text data is particularly time-consuming, which also hinders prompt responses. The present invention aims to solve these problems and improve the efficiency of inquiry responses.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0968] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating interview items based on the analysis results and the acquired additional information and providing them to a responder, and means installed on a smart device and applied to inquiries regarding security equipment support. This enables efficient processing of inquiries regarding security equipment and fast and accurate support.

[0969] "User" means an individual or organization that uses the system.

[0970] "Image data" is data containing visual information sent by a user.

[0971] "Text data" refers to data containing text information sent by a user.

[0972] The "receiving means" is a device or software that has the function of acquiring data sent from a user.

[0973] The "analyzing means" is a device or software that has the function of analyzing received data and recognizing specific elements or keywords.

[0974] The "specific elements" are important information elements contained in the image data and text data.

[0975] "Missing information" is information that is needed to answer a user's inquiry but that the user has not provided.

[0976] "Additional information" is information that the user is asked to provide to supplement the missing information.

[0977] "Hearing items" are questions and confirmations that are necessary for the responder to answer the user's inquiry.

[0978] A "responder" is a person or system that provides an answer to a user's inquiry.

[0979] The term "system" refers to a collection of hardware and software that constitutes the entire present invention.

[0980] "Analysis results" are information obtained from the analysis of received data.

[0981] A "smart device" is a device with internet connectivity, such as a phone, tablet, or smart glasses.

[0982] "Security equipment" refers to devices such as cameras and sensors that are installed to prevent fraud and accidents.

[0983] "Support" is the activity of providing assistance and solutions to user inquiries and problems.

[0984] The present invention provides a system for efficiently responding to inquiries regarding security device support by utilizing image data and text data sent by users. This system is comprised of three entities: a server, a terminal, and a user.

[0985] User

[0986] A user checks for a problem with a security device (e.g., a home security camera) and prepares data (e.g., screenshots and error messages) to explain the situation. The user enters this data into an inquiry form via a smart device and sends it to the system. For example, the user sends a description of the situation, such as "The camera cannot connect," along with a screenshot of the connection error.

[0987] Terminal

[0988] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user. Smartphones and tablets are used as the hardware for this purpose.

[0989] server

[0990] The server plays a central role in the system by executing the following series of processes: To analyze the received data, the server uses TensorFlow for image recognition and NLTK (Natural Language Toolkit) for text analysis.

[0991] 1. Data Receipt and Analysis

[0992] The server receives the screenshot and text data sent from the device. It then uses a generative AI model to analyze the image data and recognize specific elements on the screen, such as error messages or important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "Connection Error").

[0993] 2. Identifying and providing missing information

[0994] The server identifies any missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log for the connection error," and presents it to the user via the terminal. An example of a generated prompt sentence is as follows:

[0995] Please upload a screenshot of the problem.

[0996] Enter the text of the error message.

[0997] Press "Next" and provide any additional information required.

[0998] 3. Receiving additional information and reanalyzing

[0999] If the user provides additional information (for example, an error log), the terminal sends it again to the server, which receives the additional information and analyzes the entire data again.

[1000] 4. Generating and providing interview items

[1001] The server generates a questionnaire based on the final analysis results, including details of the security camera connection error, error logs, and a description of the connection status. These questionnaires are provided to support personnel to assist in a quick and accurate response.

[1002] In this way, the present invention is a system that can automatically present missing information in response to inquiries about security equipment and efficiently generate final hearing items, thereby speeding up inquiry responses and improving user satisfaction.

[1003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1004] Step 1:

[1005] A user uses a smart device to report a security equipment malfunction. Specifically, the user inputs and sends a screenshot of the security camera's connection error screen and text data such as "Camera cannot connect." The input data is the screenshot image and the error message text.

[1006] Step 2:

[1007] The terminal receives screenshots and text data sent by the user. The input data is the screenshot image and text data provided by the user. After receiving this data, the terminal uploads it to the server via the network. The output data is the data transmitted to the server.

[1008] Step 3:

[1009] The server receives image data and text data sent from the device. The input data is the image data and text data sent from the device. The server uses TensorFlow to analyze the image data and recognize specific elements on the screen (e.g., error messages and UI elements). It also uses NLTK to analyze the text data and extract important keywords and situation descriptions. The output data are the image analysis results and text analysis results.

[1010] Step 4:

[1011] The server identifies missing information based on the analysis results of the image data and text data. The input data are the image analysis results and the text analysis results. Specifically, it recognizes that an error log has not been provided and generates a prompt to obtain additional information, such as "Please provide the error log in the event of a connection error." The output data is the generated prompt.

[1012] Step 5:

[1013] The terminal displays the request from the server to the user. The input data is the prompt received from the server. The terminal displays the prompt to the user, requesting additional information. The output data is the prompt displayed to the user.

[1014] Step 6:

[1015] Based on the request from the server, the user obtains the necessary additional information (for example, an error log), enters it into the terminal again, and transmits it. The input data is the error log obtained by the user.

[1016] Step 7:

[1017] The terminal receives additional information sent by the user and sends it back to the server. The input data is the error log sent by the user. The output data is the data sent to the server.

[1018] Step 8:

[1019] The server receives the data again and performs re-analysis. The input data is the error log provided as additional information. The server analyzes the entire data and generates the final hearing item. The output data is the final hearing item.

[1020] Step 9:

[1021] The server provides the generated hearing items to the responder. The input data is the final hearing items. The server provides this to the support staff to help the responder solve the user's problem quickly and accurately. The output data is the final hearing items shared between the user and the responder.

[1022] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1023] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing the user's emotions. It automatically analyzes image data and text data sent by the user, identifies missing information, presents additional information to the user, and generates final interview items to provide to the responder. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and improves the quality of inquiry responses based on those emotions.

[1024] System configuration and operation

[1025] User

[1026] The user checks the problem with the app and prepares data (for example, screenshots, text data, or audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[1027] Terminal

[1028] The terminal is responsible for receiving data sent by the user and sending it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[1029] server

[1030] The server executes the following series of processes.

[1031] 1. Data Receipt and Analysis

[1032] The server receives screenshots, text data, and audio data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[1033] 2. Use of Emotion Engine

[1034] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1035] 3. Identifying and Presenting Missing Information

[1036] The server identifies missing information based on the image data, text data, and the results of emotion analysis. For example, if an error log is not provided, it determines that it is needed. To obtain the missing information, the server generates a message such as "Please provide the error log from the crash" and displays it to the user via the device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1037] 4. Receiving additional information and reanalyzing

[1038] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and re-analyzes all the data. This re-analysis generates the final hearing item and provides it to the responder.

[1039] 5. Generating and providing interview items

[1040] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and the user's emotional state." These hearing items are provided to support personnel to help them respond quickly and flexibly. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a prompt response is required.

[1041] Specific examples

[1042] For example, when a user inquires about an app crashing, the specific process is as follows:

[1043] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[1044] 2. Terminal: Sends the data to the server.

[1045] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[1046] 4. Terminal: Displays requests from the server to the user.

[1047] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1048] 6. Terminal: Re-send the error log to the server.

[1049] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[1050] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final interview items, thereby improving the efficiency and quality of inquiry responses.In addition, by analyzing user emotions, it is possible to provide more appropriate responses.

[1051] The processing flow will be explained below.

[1052] Step 1:

[1053] The user checks the application for a problem and prepares a screenshot, text data, and audio data to show the situation. For example, the user takes a screenshot of the moment the application crashes, and creates an explanatory message saying "The application is crashing" and an audio message saying "I'm having trouble using the application."

[1054] Step 2:

[1055] The user inputs the screenshot, text data, and voice data prepared using the terminal into the inquiry form and sends them to the system.

[1056] Step 3:

[1057] The terminal receives the screenshot, text data, and audio data sent by the user.

[1058] Step 4:

[1059] The terminal uploads the received data via the network to send it to the server.

[1060] Step 5:

[1061] The server receives the screenshot, text data, and audio data sent from the terminal.

[1062] Step 6:

[1063] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[1064] Step 7:

[1065] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[1066] Step 8:

[1067] The server analyzes the voice data and uses an emotion engine to recognize the user's emotions, for example, identifying that the user is feeling anxious.

[1068] Step 9:

[1069] The server identifies missing information based on the image data, text data, and sentiment analysis results, for example, if an error log is not provided, and additional information is required.

[1070] Step 10:

[1071] The server generates a message requesting the user for missing information, such as "Please provide the error log of the crash." If the emotion engine detects negative emotions from the user, the message is more polite.

[1072] Step 11:

[1073] The terminal receives the request message from the server and displays it to the user.

[1074] Step 12:

[1075] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[1076] Step 13:

[1077] The terminal receives the additional information sent by the user and retransmits it to the server.

[1078] Step 14:

[1079] The server receives the additional information sent by the terminal and re-analyzes all the data.

[1080] Step 15:

[1081] The server generates the final hearing items based on the reanalysis results, for example, items including "error message, error log, crash description, and user's emotional state."

[1082] Step 16:

[1083] The server prepares to provide the generated final hearing items to the responder, including a notification to prompt a response, especially if the user's sentiment is negative.

[1084] Step 17:

[1085] The responder responds quickly and accurately based on the interview items provided by the server, and communicates appropriately after understanding the user's emotional state.

[1086] Example 2

[1087] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1088] In many modern systems, responding to user inquiries is done manually and is inefficient. Furthermore, responses are often made without considering the user's feelings, making it difficult to provide appropriate support. Furthermore, necessary information is often not provided at the time of inquiry, resulting in multiple exchanges and delays in response.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1090] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for receiving voice data and analyzing it to recognize the user's emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate hearing items while responding appropriately to the user's emotions.

[1091] "User" refers to an individual or corporation that uses the system to make an inquiry.

[1092] "Image data" refers to visual information such as screenshots and photo data sent by users.

[1093] "Text data" refers to sentences and character information entered by the user.

[1094] "Audio Data" refers to audio recordings or speech data that a user transmits to the system.

[1095] "Multimodal generation AI" refers to artificial intelligence that can simultaneously analyze and generate multiple modalities, such as image data and text data.

[1096] "Specific elements" refer to parts or information that play an important role in image data, such as error messages or specific icons.

[1097] An "emotion engine" refers to a software module that analyzes voice and text data to recognize the user's emotions.

[1098] "Analysis" refers to the act of processing data and extracting specific information or features.

[1099] "Hearing items" refer to important information and questions that the support staff should collect from the user.

[1100] "Additional information" refers to any additional data or information that was not included in the initial enquiry but is necessary to provide effective support.

[1101] "Responder" refers to a support staff member or engineer who responds to inquiries from users.

[1102] The present invention provides a system for improving the efficiency of user inquiry responses and providing appropriate support by recognizing the user's emotions. This system receives image data, text data, and voice data sent by the user, analyzes them to identify necessary information, and generates final hearing items to provide to the responder.

[1103] System configuration

[1104] This system mainly consists of users, terminals, and servers. Details of each component are as follows:

[1105] User

[1106] The user checks the problem with the app and prepares data (e.g., screenshots, text data, and audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[1107] Terminal

[1108] The device receives data sent by the user and sends it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user.

[1109] server

[1110] The server uses a multimodal generation AI (e.g., OpenAI's GPT-3 or DALL-E) to perform the following series of processes:

[1111] 1. Data Receipt and Analysis

[1112] The server receives screenshots, text data, and audio data sent from the device, analyzes the image data, recognizes specific elements on the screen (e.g., error messages), and extracts situation descriptions and keywords from the received text data.

[1113] 2. Use of Emotion Engine

[1114] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1115] 3. Identifying and Presenting Missing Information

[1116] The server identifies missing information based on image data, text data, and the results of emotion analysis. For example, if it determines that an error log has not been provided, it generates a request saying, "Please provide the error log from the crash." If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1117] 4. Receiving additional information and reanalyzing

[1118] If the user provides additional information (e.g., an error log), the terminal resends it to the server, which receives the additional information and re-analyzes all data. This re-analysis generates the final hearing item and provides it to the support staff.

[1119] 5. Generating and providing interview items

[1120] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and user's emotional state." These hearing items are provided to support personnel to support a fast and flexible response. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a fast response is required.

[1121] Specific examples

[1122] For example, when a user inquires about an app crashing, the specific process is as follows:

[1123] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[1124] 2. Terminal: Sends the data to the server.

[1125] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[1126] 4. Terminal: Displays requests from the server to the user.

[1127] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1128] 6. Terminal: Re-send the error log to the server.

[1129] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[1130] Through this process, the system automatically presents missing information in response to user inquiries, enabling a prompt and appropriate response.

[1131] An example of a prompt to be input to the generative AI model could be, "Please analyze the screenshot of the crash, the text message 'The app is crashing,' and the audio data 'I'm having trouble using the app,' to identify any additional information that is needed and provide the missing information to the user."

[1132] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1133] Step 1:

[1134] The user checks the app for a problem and prepares data to explain the situation. For example, they could prepare a screenshot of the crash, text data such as "The app keeps crashing," and a voice message such as "I'm having trouble using the app." The user then enters this data into the device's inquiry form and submits it.

[1135] Input: Screenshots, text data, audio data

[1136] Output: User input data is sent

[1137] Step 2:

[1138] The device receives screenshots, text data, and audio data sent by the user. The device uploads the received data to the server via the network. It also has the function of displaying requests and notifications from the server to the user.

[1139] Input: Data submitted by the user

[1140] Output: Upload data to server, display notification to user

[1141] Step 3:

[1142] The server receives screenshots, text data, and audio data sent from the device. Using multimodal generative AI, the server analyzes the image data and recognizes specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords.

[1143] Input: Screenshots, text data, audio data

[1144] Output: Specific elements of image data, contextual descriptions and keywords of text data

[1145] Step 4:

[1146] The server analyzes the received text and voice data using an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1147] Input: Text data, audio data

[1148] Output: Recognition of the user's emotional state

[1149] Step 5:

[1150] The server identifies missing information based on the image data, text data, and the results of emotion analysis. If an error log is not provided, it determines that it is missing information and generates a request saying, "Please provide the error log from the crash." The server then presents this request to the user via their device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1151] Input: Image data, text data, emotion analysis results

[1152] Output: Missing information request message

[1153] Step 6:

[1154] The user provides additional information (for example, an error log), which the terminal then transmits to the server again. The user obtains the error log, enters it into the terminal, and transmits it.

[1155] Input: User-provided error log

[1156] Output: Send additional information to the server

[1157] Step 7:

[1158] The server receives the additional information and re-analyzes all the data, generating the final hearing items to provide to the support representative, including the error message, error log, crash description, and the user's emotional state.

[1159] Input: Additional information (e.g. error log)

[1160] Output: Generate and deliver the final hearing items

[1161] Through the above processing steps, the system is able to respond quickly and appropriately to inquiries from users.

[1162] (Application example 2)

[1163] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1164] Conventional systems were inefficient in responding to user inquiries, particularly due to a lack of emotion recognition, which prevented them from providing appropriate support. This increased user dissatisfaction and risked a decline in the company's credibility. Furthermore, identifying missing information and requesting additional information was done manually, which took time to respond and made it difficult to provide efficient support. Furthermore, in-factory equipment maintenance requires a fast and appropriate response, but current systems are unable to meet this demand.

[1165] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1166] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data and voice data sent from the user and analyzing them to extract specific keywords and emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, means for generating an appropriate support message according to the user's emotions based on the analysis results and the acquired additional information, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This enables automatic identification of missing information and flexible response according to the user's emotions.

[1167] A "user" is a person who uses the system to make an inquiry.

[1168] "Image data" is visual information such as screenshots or photographs of devices or systems that users submit.

[1169] "Text data" is information such as textual explanations or comments sent by users.

[1170] "Voice data" refers to voice messages and recordings sent by users.

[1171] A "server" is a central computing device that analyzes and manages data.

[1172] "Analysis" is the process of understanding the transmitted data and extracting specific information or states.

[1173] A "specific element" is a particularly important part or piece of information in image data.

[1174] "Keywords" are important words or phrases within the text data.

[1175] "Emotion" refers to the feelings or state that a user is experiencing, and is extracted from voice data or text data.

[1176] "Additional information" is supplementary data that the server requests the user to provide based on the analysis.

[1177] "Hearing items" are questions or confirmation items that the responder should ultimately ask the user.

[1178] "Responder" refers to the staff or system that responds to inquiries from users.

[1179] "Emotion analysis" is a process of recognizing a user's emotional state from voice data and text data.

[1180] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing emotions. This system is mainly composed of three components: a server, a terminal, and a user. The specific operation of each component and the overall system flow are explained below.

[1181] User

[1182] The user is a worker who uses this system to perform equipment maintenance. When a worker discovers a malfunction in the equipment, they use the smart glasses to capture a picture of the situation and explain the problem in audio. As a specific example of a malfunction, the user sends a voice message explaining the situation, such as "The machine is crashing," along with a screenshot of the crash, to the system via the smart glasses.

[1183] Terminal

[1184] The smart glasses (e.g., Google Glass Enterprise Edition) used as the terminal are responsible for receiving image and audio data sent by the user and transmitting this data to the server. The terminal also has the function of displaying requests and notifications from the server to the user.

[1185] server

[1186] The server performs the following sequence of operations:

[1187] 1. Data Receipt and Analysis

[1188] The server receives image and audio data sent from the device. It uses TensorFlow and OpenCV for image analysis, and IBM Watson Speech to Text for audio analysis. It also uses the Microsoft Azure Emotion API for emotion recognition. These tools are used to extract specific elements in images (e.g., error messages) and specific keywords from audio, as well as the user's emotions.

[1189] 2. Identifying and providing missing information

[1190] The server identifies missing information based on the analysis results. For example, if an error log has not been provided, it determines that it is necessary. In this case, it generates a prompt message such as "Please provide the error log from the crash" and presents it to the user via the device. If emotion recognition reveals that the user is expressing negative emotions such as anxiety or anger, it creates a message requesting a more polite response.

[1191] 3. Receiving additional information and reanalyzing

[1192] If the user provides additional information (e.g., error logs) in response to a request from the system, the terminal again sends the data to the server, which then re-analyzes the additional information and generates the final hearing items based on all the data.

[1193] Examples:

[1194] An example of a specific prompt for a factory worker asking "The machine is crashing" is:

[1195] Image: "Please take a picture of the screen where the machine stops."

[1196] Voice: "Please describe the crash in a voice message."

[1197] The server analyzes this data, and if it determines that there is missing information, it generates a request, for example, "Please provide the error log from the crash," and notifies the user again via the terminal. The user provides the error log and submits it again, and the server reanalyzes it and provides the final hearing items to the responder.

[1198] This makes it possible for the entire system to automatically identify missing information and respond flexibly according to emotions.

[1199] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1200] Step 1:

[1201] The user uses the smart glasses to take a picture of the equipment malfunction and explain the situation by voice. The user's device receives the image and voice data and sends it to the server.

[1202] Input: Image data and audio data of the defect

[1203] Output: Send data to the server

[1204] Step 2:

[1205] The server receives the image data and audio data sent by the user and analyzes them, using TensorFlow and OpenCV for image analysis and IBM Watson Speech to Text for audio analysis to extract specific elements, keywords, and emotions.

[1206] Input: Received data (image data, audio data)

[1207] Output: Analysis results (specific elements in images, keywords and emotions from audio)

[1208] Operation: Received image data is processed using image analysis software to identify error messages and abnormalities. Voice data is converted into text using voice recognition software, and keywords and user sentiment are extracted.

[1209] Step 3:

[1210] The server identifies missing information based on the analysis results. For example, if an error log is missing, it automatically generates a prompt to ask the user for that information. If necessary, it also creates a corresponding message taking into account the results of sentiment analysis.

[1211] Input: Analysis results (specific elements in the image, keywords and emotions from the audio)

[1212] Output: prompt (message requesting additional information), response message according to emotion

[1213] What it does: Checks the analysis results, determines missing information, generates prompts, and adjusts the content based on the results of sentiment analysis.

[1214] Step 4:

[1215] The terminal displays the prompt sent from the server to the user and requests any additional information required from the user. The user follows the instructions and provides additional information, such as an error log.

[1216] Input: Prompt statement (message requesting additional information), response message

[1217] Output: Additional information from the user (such as error logs)

[1218] Behavior: Displays a prompt and corresponding message to the user, prompting them for additional information.

[1219] Step 5:

[1220] The user again enters the requested additional information into the terminal, which then transmits it to the server.

[1221] Input: Additional information (error log, etc.)

[1222] Output: Sending data to the server again

[1223] Operation: The device receives additional information provided by the user and uploads it to the server.

[1224] Step 6:

[1225] The server again analyzes the additional information received and combines all the data to generate a final hearing item, which is then provided to the responder.

[1226] Input: Received data again (additional information)

[1227] Output: Final hearing items

[1228] What it does: Analyzes the additional information and integrates it with existing data to create a comprehensive hearing item that is sent to responders to ensure a rapid response.

[1229] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1230] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1231] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1232] [Fourth embodiment]

[1233] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1234] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1235] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1236] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1237] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1239] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1240] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1241] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1242] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1243] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1244] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1245] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1246] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[1247] System configuration and operation

[1248] User

[1249] The user checks the app for a problem and prepares data (such as screenshots and text) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[1250] Terminal

[1251] The terminal is responsible for receiving data sent by the user and sending it to the server. The received screenshots and text data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[1252] server

[1253] The server plays a central role in the system by executing the following series of processes.

[1254] 1. Data Receipt and Analysis

[1255] The server receives screenshots and text data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen, such as error messages and important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (such as "crash").

[1256] 2. Identifying and providing missing information

[1257] The server identifies missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and presents it to the user via the terminal.

[1258] 3. Receiving additional information and reanalyzing

[1259] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing item and provides it to the responder.

[1260] 4. Generating and providing interview items

[1261] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[1262] Specific examples

[1263] For example, when a user inquires about an app crashing, the specific process is as follows:

[1264] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[1265] 2. Terminal: Sends the data to the server.

[1266] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[1267] 4. Terminal: Displays requests from the server to the user.

[1268] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1269] 6. Terminal: Re-send the error log to the server.

[1270] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[1271] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[1272] The processing flow will be explained below.

[1273] Step 1:

[1274] The user checks the application for a problem and prepares screenshots and text data to show the situation. Specifically, the user takes a screenshot of the moment the application crashes and writes a description that reads, "The application crashes."

[1275] Step 2:

[1276] The user inputs the screenshot and text data prepared using the terminal into the inquiry form and sends it to the system.

[1277] Step 3:

[1278] The terminal receives the screenshot and text data sent by the user.

[1279] Step 4:

[1280] The terminal uploads the received data via the network to send it to the server.

[1281] Step 5:

[1282] The server receives the screenshot and text data sent from the terminal.

[1283] Step 6:

[1284] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[1285] Step 7:

[1286] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[1287] Step 8:

[1288] The server identifies missing information based on the analysis of the image data and text data, for example, if an error log is not provided.

[1289] Step 9:

[1290] The server generates a message to ask the user for missing information, for example, making a specific request such as "Please provide the error log from the crash."

[1291] Step 10:

[1292] The terminal receives the request message from the server and displays it to the user.

[1293] Step 11:

[1294] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[1295] Step 12:

[1296] The terminal receives additional information from the user and retransmits it to the server.

[1297] Step 13:

[1298] The server receives the additional information sent by the terminal and analyzes all the data again.

[1299] Step 14:

[1300] The server generates the final hearing items based on the reanalysis results, such as "the error code and detailed description of the situation that is likely to have caused the crash."

[1301] Step 15:

[1302] The server prepares the generated final hearing items to be provided to the responder.

[1303] Step 16:

[1304] The responder responds quickly and accurately based on the hearing items provided by the server.

[1305] Example 1

[1306] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1307] In conventional inquiry response systems, the information about the problem reported by the user is often insufficient, which forces the responder to request additional information each time, resulting in delayed responses. Furthermore, when the problem is complex, simple text data alone does not provide sufficient information, making it difficult for the responder to grasp the details. This increases the amount of back-and-forth communication between the user and the responder, resulting in reduced response efficiency.

[1308] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1309] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder, means for receiving and reanalyzing the additional information from the user, and means for generating final hearing items and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate final hearing items.

[1310] "Image data" refers to data containing visual information such as screenshots that are sent by a user when reporting a problem with an application.

[1311] "Text data" is data containing character information that is sent when a user writes an explanation or detailed information about a problem in an application.

[1312] A "specific element" is an important part contained in image data, such as an error message or an important user interface element.

[1313] "Keywords" are important words or phrases that a user writes in text data, such as "crash" or "error message."

[1314] A "multimodal generative AI model" is an artificial intelligence model for analyzing both image data and text data, and has the ability to extract and analyze information from these data.

[1315] "Insufficient information" refers to information that is not sufficient for the person in charge to understand the details of the problem from the data initially provided by the user, and that must be provided additionally.

[1316] "Additional information" refers to detailed information, such as an error log or further explanation, that the server provides in response to a user's request for missing information.

[1317] "Hearing items" refers to a series of questions and confirmations that are generated by the server based on analysis data and that are required by the responder to respond to the problem.

[1318] The term "responder" refers to an agent or system administrator who responds to inquiries from users and provides support to resolve problems.

[1319] "Re-analysis" refers to the process in which the server re-analyzes the additional information provided by the user, thereby reconfirming the overall situation and generating the final hearing items.

[1320] This invention is a system that aims to improve the efficiency of inquiry responses by automatically analyzing image data and text data sent by users, identifying missing information, presenting additional information to the user, and generating final interview items to provide to the responder. This system is composed of three entities: a server, a terminal, and a user.

[1321] System configuration and operation

[1322] User

[1323] The user prepares image data (e.g., screenshots) and text data (e.g., detailed description of the problem) to report an app malfunction. The user enters this data into an inquiry form via their device and sends it to the system. As a specific example of the malfunction, the user sends a description of the situation, such as "the app crashes," along with a screenshot showing the error message that occurred when the crash occurred.

[1324] Terminal

[1325] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the Internet. The device also has the function of displaying requests and notifications from the server to the user.

[1326] server

[1327] The server plays a central role in the system and performs the following series of processes.

[1328] 1. Data Receipt and Analysis

[1329] The server receives the screenshot and text data sent from the device. It then uses a multimodal generative AI model to analyze the image data and recognize specific elements on the screen (e.g., error messages or important UI elements). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[1330] 2. Identifying and providing missing information

[1331] The server identifies missing information based on the received and analyzed information. For example, if an error log is not provided, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log at the time of the crash" and displays it to the user via the terminal.

[1332] 3. Receiving additional information and reanalyzing

[1333] If the user provides additional information (e.g., error log), the terminal sends it again to the server. The server receives the additional information and analyzes the entire data again. This reanalysis generates the final hearing items and provides them to the responder.

[1334] 4. Generating and providing interview items

[1335] The server generates a report based on the final analysis, including error messages, error logs, and crash description. This report is provided to support personnel to assist in a quick and accurate response.

[1336] Specific examples

[1337] As a concrete example, the flow when a user makes an inquiry about "my app crashes" is shown below.

[1338] 1. User: Send a screenshot of the crash and the text "The app is crashing" to your device.

[1339] 2. Terminal: Sends the data to the server.

[1340] 3. Server: Analyzes the received data and identifies the error message and crash situation. If it determines that an error log is required as missing information, it generates a request to "Please provide the error log at the time of the crash."

[1341] 4. Terminal: Displays requests from the server to the user.

[1342] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1343] 6. Terminal: Re-send the error log to the server.

[1344] 7. Server: Analyzes all data again, generates final hearing items and provides them to the support staff.

[1345] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final hearing items, thereby improving the efficiency of inquiry responses.

[1346] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1347] Step 1:

[1348] To report an app malfunction, a user prepares a screenshot and text data describing the situation. Specifically, the user captures a screenshot of the moment the app crashes and writes an explanation such as "The app crashes" in the input form. After entering the necessary information in this form, the user presses the send button to send the data to the device.

[1349] Step 2:

[1350] The device receives the screenshot and text data sent by the user. This received data is uploaded to a server via the Internet. Specifically, an HTTP request is generated, the user's sent data is attached to it, and it is sent to the server. The input is the user's screenshot and text data, and the output is an HTTP request to the server.

[1351] Step 3:

[1352] The server receives data sent from the device. It classifies the received data and uses a multimodal generative AI model to analyze image data. The AI ​​model identifies error messages and important UI elements from screenshots. It also analyzes text data using natural language processing techniques to extract situation descriptions and keywords. The input is image data and text data from the device, and the output is error messages and keywords as the analysis results.

[1353] Step 4:

[1354] The server identifies missing information based on the analysis results. For example, if the analysis does not provide an error log, it determines that it is necessary. The server generates a request message saying, "Please provide the error log at the time of the crash," and sends it to the terminal. The input is the analysis result, and the output is a request message requesting additional information.

[1355] Step 5:

[1356] The terminal receives the request from the server and displays the contents to the user. Specifically, it presents the user with a pop-up notification or a prompt message on the screen saying "Please provide the error log in the event of a crash." The input is the request statement from the server, and the output is the notification to the user.

[1357] Step 6:

[1358] The user obtains the error log according to the instructions and sends it again via the terminal. The user selects the error log file and uploads it to the inquiry form as additional information. The user presses the send button again to send the data to the terminal. The input is the error log file, and the output is the data sent to the terminal.

[1359] Step 7:

[1360] The terminal receives additional information (error log) sent by the user again and uploads it to the server again. The input is the error log from the user, and the output is an HTTP request to the server.

[1361] Step 8:

[1362] The server receives the additional information and re-analyzes the data, including the results of the previous analysis. Using a multimodal generative AI model, it re-analyzes all data, including the added error log, and reconfirms the overall situation. The input is the additional information and the initial data, and the output is the re-analysis results.

[1363] Step 9:

[1364] The server generates hearing items based on the final analysis results. Specifically, it integrates the error message, error log, crash description, etc. provided by the user, and compiles all the information required by the responder into a single list. The input is the reanalysis results, and the output is a list of hearing items.

[1365] Step 10:

[1366] The server provides the final hearing items to the responder, who can then respond quickly and accurately based on the hearing items. The input is a list of hearing items, and the output is information provided to the responder.

[1367] This series of processes enables the system to automatically present missing information in response to user inquiries and efficiently generate final interview items, resulting in a fast and accurate response.

[1368] (Application example 1)

[1369] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1370] In conventional inquiry response systems, if the information sent by the user is insufficient, the responder must request additional information each time, which is inefficient and tends to result in long response times. Furthermore, when supporting security devices, analyzing image data and text data is particularly time-consuming, which also hinders prompt responses. The present invention aims to solve these problems and improve the efficiency of inquiry responses.

[1371] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1372] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user, means for generating interview items based on the analysis results and the acquired additional information and providing them to a responder, and means installed on a smart device and applied to inquiries regarding security equipment support. This enables efficient processing of inquiries regarding security equipment and fast and accurate support.

[1373] "User" means an individual or organization that uses the system.

[1374] "Image data" is data containing visual information sent by a user.

[1375] "Text data" refers to data containing text information sent by a user.

[1376] The "receiving means" is a device or software that has the function of acquiring data sent from a user.

[1377] The "analyzing means" is a device or software that has the function of analyzing received data and recognizing specific elements or keywords.

[1378] The "specific elements" are important information elements contained in the image data and text data.

[1379] "Missing information" is information that is needed to answer a user's inquiry but that the user has not provided.

[1380] "Additional information" is information that the user is asked to provide to supplement the missing information.

[1381] "Hearing items" are questions and confirmations that are necessary for the responder to answer the user's inquiry.

[1382] A "responder" is a person or system that provides an answer to a user's inquiry.

[1383] The term "system" refers to a collection of hardware and software that constitutes the entire present invention.

[1384] "Analysis results" are information obtained from the analysis of received data.

[1385] A "smart device" is a device with internet connectivity, such as a phone, tablet, or smart glasses.

[1386] "Security equipment" refers to devices such as cameras and sensors that are installed to prevent fraud and accidents.

[1387] "Support" is the activity of providing assistance and solutions to user inquiries and problems.

[1388] The present invention provides a system for efficiently responding to inquiries regarding security device support by utilizing image data and text data sent by users. This system is comprised of three entities: a server, a terminal, and a user.

[1389] User

[1390] A user checks for a problem with a security device (e.g., a home security camera) and prepares data (e.g., screenshots and error messages) to explain the situation. The user enters this data into an inquiry form via a smart device and sends it to the system. For example, the user sends a description of the situation, such as "The camera cannot connect," along with a screenshot of the connection error.

[1391] Terminal

[1392] The device receives data sent by the user and sends it to the server. The received screenshots and text data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user. Smartphones and tablets are used as the hardware for this purpose.

[1393] server

[1394] The server plays a central role in the system by executing the following series of processes: To analyze the received data, the server uses TensorFlow for image recognition and NLTK (Natural Language Toolkit) for text analysis.

[1395] 1. Data Receipt and Analysis

[1396] The server receives the screenshot and text data sent from the device. It then uses a generative AI model to analyze the image data and recognize specific elements on the screen, such as error messages or important UI elements. At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "Connection Error").

[1397] 2. Identifying and providing missing information

[1398] The server identifies any missing information based on the received and analyzed results. For example, if the user has not provided an error log, it determines that it is necessary. To obtain the missing information, the server generates a message such as "Please provide the error log of the connection error," and presents it to the user via the terminal. An example of a prompt sentence generated here is as follows:

[1399] Please upload a screenshot of the problem.

[1400] Enter the text of the error message.

[1401] Press "Next" and provide any additional information required.

[1402] 3. Receiving additional information and reanalyzing

[1403] If the user provides additional information (for example, an error log), the terminal sends it again to the server, which receives the additional information and analyzes the entire data again.

[1404] 4. Generating and providing interview items

[1405] The server generates a questionnaire based on the final analysis results, including details of the security camera connection error, error logs, and a description of the connection status. These questionnaires are provided to support personnel to assist in a quick and accurate response.

[1406] In this way, the present invention is a system that can automatically present missing information in response to inquiries about security equipment and efficiently generate final hearing items, thereby speeding up inquiry responses and improving user satisfaction.

[1407] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1408] Step 1:

[1409] A user uses a smart device to report a security equipment malfunction. Specifically, the user inputs and sends a screenshot of the security camera's connection error screen and text data such as "Camera cannot connect." The input data is the screenshot image and the error message text.

[1410] Step 2:

[1411] The terminal receives screenshots and text data sent by the user. The input data is the screenshot image and text data provided by the user. After receiving this data, the terminal uploads it to the server via the network. The output data is the data transmitted to the server.

[1412] Step 3:

[1413] The server receives image data and text data sent from the device. The input data is the image data and text data sent from the device. The server uses TensorFlow to analyze the image data and recognize specific elements on the screen (e.g., error messages and UI elements). It also uses NLTK to analyze the text data and extract important keywords and situation descriptions. The output data are the image analysis results and text analysis results.

[1414] Step 4:

[1415] The server identifies missing information based on the analysis results of the image data and text data. The input data are the image analysis results and the text analysis results. Specifically, it recognizes that an error log has not been provided and generates a prompt to obtain additional information, such as "Please provide the error log in the event of a connection error." The output data is the generated prompt.

[1416] Step 5:

[1417] The terminal displays the request from the server to the user. The input data is the prompt received from the server. The terminal displays the prompt to the user, requesting additional information. The output data is the prompt displayed to the user.

[1418] Step 6:

[1419] Based on the request from the server, the user obtains the necessary additional information (for example, an error log), enters it into the terminal again, and transmits it. The input data is the error log obtained by the user.

[1420] Step 7:

[1421] The terminal receives additional information sent by the user and sends it back to the server. The input data is the error log sent by the user. The output data is the data sent to the server.

[1422] Step 8:

[1423] The server receives the data again and performs re-analysis. The input data is the error log provided as additional information. The server analyzes the entire data and generates the final hearing item. The output data is the final hearing item.

[1424] Step 9:

[1425] The server provides the generated hearing items to the responder. The input data is the final hearing items. The server provides this to the support staff to help the responder solve the user's problem quickly and accurately. The output data is the final hearing items shared between the user and the responder.

[1426] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1427] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing the user's emotions. It automatically analyzes image data and text data sent by the user, identifies missing information, presents additional information to the user, and generates final interview items to provide to the responder. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and improves the quality of inquiry responses based on those emotions.

[1428] System configuration and operation

[1429] User

[1430] The user checks the problem with the app and prepares data (for example, screenshots, text data, or audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[1431] Terminal

[1432] The terminal is responsible for receiving data sent by the user and sending it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The terminal also has the function of displaying requests and notifications from the server to the user.

[1433] server

[1434] The server executes the following series of processes.

[1435] 1. Data Receipt and Analysis

[1436] The server receives screenshots, text data, and audio data sent from the device. It then uses multimodal generative AI to analyze the image data and recognize specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords (e.g., "crash").

[1437] 2. Use of Emotion Engine

[1438] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1439] 3. Identifying and Presenting Missing Information

[1440] The server identifies missing information based on the image data, text data, and the results of emotion analysis. For example, if an error log is not provided, it determines that it is needed. To obtain the missing information, the server generates a message such as "Please provide the error log from the crash" and displays it to the user via the device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1441] 4. Receiving additional information and reanalyzing

[1442] If the user provides additional information (e.g., an error log), the terminal sends it again to the server. The server receives the additional information and re-analyzes all the data. This re-analysis generates the final hearing item and provides it to the responder.

[1443] 5. Generating and providing interview items

[1444] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and the user's emotional state." These hearing items are provided to support personnel to help them respond quickly and flexibly. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a prompt response is required.

[1445] Specific examples

[1446] For example, when a user inquires about an app crashing, the specific process is as follows:

[1447] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[1448] 2. Terminal: Sends the data to the server.

[1449] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[1450] 4. Terminal: Displays requests from the server to the user.

[1451] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1452] 6. Terminal: Re-send the error log to the server.

[1453] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[1454] In this way, this system automatically presents missing information in response to user inquiries and efficiently generates final interview items, thereby improving the efficiency and quality of inquiry responses.In addition, by analyzing user emotions, it is possible to provide more appropriate responses.

[1455] The processing flow will be explained below.

[1456] Step 1:

[1457] The user checks the application for a problem and prepares a screenshot, text data, and audio data to show the situation. For example, the user takes a screenshot of the moment the application crashes, and creates an explanatory message saying "The application is crashing" and an audio message saying "I'm having trouble using the application."

[1458] Step 2:

[1459] The user inputs the screenshot, text data, and voice data prepared using the terminal into the inquiry form and sends them to the system.

[1460] Step 3:

[1461] The terminal receives the screenshot, text data, and audio data sent by the user.

[1462] Step 4:

[1463] The terminal uploads the received data via the network to send it to the server.

[1464] Step 5:

[1465] The server receives the screenshot, text data, and audio data sent from the terminal.

[1466] Step 6:

[1467] The server analyzes the screenshots using multimodal generative AI to identify error messages and important UI elements from the images.

[1468] Step 7:

[1469] The server analyzes the received text data and extracts specific keywords and descriptions of the situation, for example, the keyword "crash."

[1470] Step 8:

[1471] The server analyzes the voice data and uses an emotion engine to recognize the user's emotions, for example, identifying that the user is feeling anxious.

[1472] Step 9:

[1473] The server identifies missing information based on the image data, text data, and sentiment analysis results, for example, if an error log is not provided, and additional information is required.

[1474] Step 10:

[1475] The server generates a message requesting the user for missing information, such as "Please provide the error log of the crash." If the emotion engine detects negative emotions from the user, the message is more polite.

[1476] Step 11:

[1477] The terminal receives the request message from the server and displays it to the user.

[1478] Step 12:

[1479] The user obtains additional information (for example, an error log) in response to a request from the server, enters it into the terminal, and retransmits it.

[1480] Step 13:

[1481] The terminal receives the additional information sent by the user and retransmits it to the server.

[1482] Step 14:

[1483] The server receives the additional information sent by the terminal and re-analyzes all the data.

[1484] Step 15:

[1485] The server generates the final hearing items based on the reanalysis results, for example, items including "error message, error log, crash description, and user's emotional state."

[1486] Step 16:

[1487] The server prepares to provide the generated final hearing items to the responder, including a notification to prompt a response, especially if the user's sentiment is negative.

[1488] Step 17:

[1489] The responder responds quickly and accurately based on the interview items provided by the server, and communicates appropriately after understanding the user's emotional state.

[1490] Example 2

[1491] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1492] In many modern systems, responding to user inquiries is done manually and is inefficient. Furthermore, responses are often made without considering the user's feelings, making it difficult to provide appropriate support. Furthermore, necessary information is often not provided at the time of inquiry, resulting in multiple exchanges and delays in response.

[1493] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1494] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data sent from the user and analyzing it to extract specific keywords and situation descriptions, means for receiving voice data and analyzing it to recognize the user's emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This makes it possible to automatically present missing information in response to a user inquiry and efficiently generate hearing items while responding appropriately to the user's emotions.

[1495] "User" refers to an individual or corporation that uses the system to make an inquiry.

[1496] "Image data" refers to visual information such as screenshots and photo data sent by users.

[1497] "Text data" refers to sentences and character information entered by the user.

[1498] "Audio Data" refers to audio recordings or speech data that a user transmits to the system.

[1499] "Multimodal generation AI" refers to artificial intelligence that can simultaneously analyze and generate multiple modalities, such as image data and text data.

[1500] "Specific elements" refer to parts or information that play an important role in image data, such as error messages or specific icons.

[1501] An "emotion engine" refers to a software module that analyzes voice and text data to recognize the user's emotions.

[1502] "Analysis" refers to the act of processing data and extracting specific information or features.

[1503] "Hearing items" refer to important information and questions that the support staff should collect from the user.

[1504] "Additional information" refers to any additional data or information that was not included in the initial enquiry but is necessary to provide effective support.

[1505] "Responder" refers to a support staff member or engineer who responds to inquiries from users.

[1506] The present invention provides a system for improving the efficiency of user inquiry responses and providing appropriate support by recognizing the user's emotions. This system receives image data, text data, and voice data sent by the user, analyzes them to identify necessary information, and generates final hearing items to provide to the responder.

[1507] System configuration

[1508] This system mainly consists of users, terminals, and servers. Details of each component are as follows:

[1509] User

[1510] The user checks the problem with the app and prepares data (e.g., screenshots, text data, and audio data) to explain the situation. The user enters this data into an inquiry form on their device and sends it to the system. As a specific example of the problem, the user sends a description of the situation, such as "the app crashes," a screenshot showing the error message at the time of the crash, and an audio message.

[1511] Terminal

[1512] The device receives data sent by the user and sends it to the server. Received screenshots, text data, and audio data are uploaded to the server via the network. The device also has the function of displaying requests and notifications from the server to the user.

[1513] server

[1514] The server uses a multimodal generation AI (e.g., OpenAI's GPT-3 or DALL-E) to perform the following series of processes:

[1515] 1. Data Receipt and Analysis

[1516] The server receives screenshots, text data, and audio data sent from the device, analyzes the image data, recognizes specific elements on the screen (e.g., error messages), and extracts situation descriptions and keywords from the received text data.

[1517] 2. Use of Emotion Engine

[1518] The server analyzes the received text and voice data and uses an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1519] 3. Identifying and Presenting Missing Information

[1520] The server identifies missing information based on image data, text data, and the results of emotion analysis. For example, if it determines that an error log has not been provided, it generates a request saying, "Please provide the error log from the crash." If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1521] 4. Receiving additional information and reanalyzing

[1522] If the user provides additional information (e.g., an error log), the terminal resends it to the server, which receives the additional information and re-analyzes all data. This re-analysis generates the final hearing item and provides it to the support staff.

[1523] 5. Generating and providing interview items

[1524] The server generates the final hearing items based on the reanalysis results. For example, they may include "error message, error log, crash description, and user's emotional state." These hearing items are provided to support personnel to support a fast and flexible response. In particular, if the user's emotional state is negative, the support personnel should be notified immediately and a fast response is required.

[1525] Specific examples

[1526] For example, when a user inquires about an app crashing, the specific process is as follows:

[1527] 1. User: Send a screenshot of the crash, a text message saying "The app is crashing," and a voice message saying "I'm having trouble using the app."

[1528] 2. Terminal: Sends the data to the server.

[1529] 3. Server: Analyzes the received data and identifies the error message and crash details. It determines that an error log is required as missing information, and generates a request saying, "Please provide the error log from the time of the crash." At the same time, it recognizes from the voice data that the user is feeling anxious, and creates a message encouraging a polite response.

[1530] 4. Terminal: Displays requests from the server to the user.

[1531] 5. User: Obtain the error log, enter it again into the terminal, and send it.

[1532] 6. Terminal: Re-send the error log to the server.

[1533] 7. Server: Analyze all data again, generate the final questionnaire, and provide it to the support staff. Since the user is worried, add instructions to respond quickly.

[1534] Through this process, the system automatically presents missing information in response to user inquiries, enabling a prompt and appropriate response.

[1535] An example of a prompt to be input to the generative AI model could be, "Please analyze the screenshot of the crash, the text message 'The app is crashing,' and the audio data 'I'm having trouble using the app,' to identify any additional information that is needed and provide the missing information to the user."

[1536] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1537] Step 1:

[1538] The user checks the app for a problem and prepares data to explain the situation. For example, they could prepare a screenshot of the crash, text data such as "The app keeps crashing," and a voice message such as "I'm having trouble using the app." The user then enters this data into the device's inquiry form and submits it.

[1539] Input: Screenshots, text data, audio data

[1540] Output: User input data is sent

[1541] Step 2:

[1542] The device receives screenshots, text data, and audio data sent by the user. The device uploads the received data to the server via the network. It also has the function of displaying requests and notifications from the server to the user.

[1543] Input: Data submitted by the user

[1544] Output: Upload data to server, display notification to user

[1545] Step 3:

[1546] The server receives screenshots, text data, and audio data sent from the device. Using multimodal generative AI, the server analyzes the image data and recognizes specific elements on the screen (e.g., error messages). At the same time, it analyzes the text data to extract situation descriptions and keywords.

[1547] Input: Screenshots, text data, audio data

[1548] Output: Specific elements of image data, contextual descriptions and keywords of text data

[1549] Step 4:

[1550] The server analyzes the received text and voice data using an emotion engine to recognize the user's emotions. For example, it identifies negative emotions such as anger or anxiety from the voice data.

[1551] Input: Text data, audio data

[1552] Output: Recognition of the user's emotional state

[1553] Step 5:

[1554] The server identifies missing information based on the image data, text data, and the results of emotion analysis. If an error log is not provided, it determines that it is missing information and generates a request saying, "Please provide the error log from the crash." The server then presents this request to the user via their device. If the emotion engine detects negative emotions, it adjusts the content of the message to respond more flexibly to the user.

[1555] Input: Image data, text data, emotion analysis results

[1556] Output: Missing information request message

[1557] Step 6:

[1558] The user provides additional information (for example, an error log), which the terminal then transmits to the server again. The user obtains the error log, enters it into the terminal, and transmits it.

[1559] Input: User-provided error log

[1560] Output: Send additional information to the server

[1561] Step 7:

[1562] The server receives the additional information and re-analyzes all the data, generating the final hearing items to provide to the support representative, including the error message, error log, crash description, and the user's emotional state.

[1563] Input: Additional information (e.g. error log)

[1564] Output: Generate and deliver the final hearing items

[1565] Through the above processing steps, the system is able to respond quickly and appropriately to inquiries from users.

[1566] (Application example 2)

[1567] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1568] Conventional systems were inefficient in responding to user inquiries, particularly due to a lack of emotion recognition, which prevented them from providing appropriate support. This increased user dissatisfaction and risked a decline in the company's credibility. Furthermore, identifying missing information and requesting additional information was done manually, which took time to respond and made it difficult to provide efficient support. Furthermore, in-factory equipment maintenance requires a fast and appropriate response, but current systems are unable to meet this demand.

[1569] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1570] In this invention, the server includes means for receiving image data sent from a user, means for analyzing the received image data and recognizing specific elements on the screen, means for receiving text data and voice data sent from the user and analyzing them to extract specific keywords and emotions, means for identifying missing information based on the analysis results of the image data, text data, and voice data and presenting additional information to the user, means for generating an appropriate support message according to the user's emotions based on the analysis results and the acquired additional information, and means for generating hearing items based on the analysis results and the acquired additional information and providing them to a responder. This enables automatic identification of missing information and flexible response according to the user's emotions.

[1571] A "user" is a person who uses the system to make an inquiry.

[1572] "Image data" is visual information such as screenshots or photographs of devices or systems that users submit.

[1573] "Text data" is information such as textual explanations or comments sent by users.

[1574] "Voice data" refers to voice messages and recordings sent by users.

[1575] A "server" is a central computing device that analyzes and manages data.

[1576] "Analysis" is the process of understanding the transmitted data and extracting specific information or states.

[1577] A "specific element" is a particularly important part or piece of information in image data.

[1578] "Keywords" are important words or phrases within the text data.

[1579] "Emotion" refers to the feelings or state that a user is experiencing, and is extracted from voice data or text data.

[1580] "Additional information" is supplementary data that the server requests the user to provide based on the analysis.

[1581] "Hearing items" are questions or confirmation items that the responder should ultimately ask the user.

[1582] "Responder" refers to the staff or system that responds to inquiries from users.

[1583] "Emotion analysis" is a process of recognizing a user's emotional state from voice data and text data.

[1584] This invention is a system that improves the efficiency of user inquiry responses and provides appropriate support by recognizing emotions. This system is mainly composed of three components: a server, a terminal, and a user. The specific operation of each component and the overall system flow are explained below.

[1585] User

[1586] The user is a worker who uses this system to perform equipment maintenance. When a worker discovers a malfunction in the equipment, they use the smart glasses to capture a picture of the situation and explain the problem in audio. As a specific example of a malfunction, the user sends a voice message explaining the situation, such as "The machine is crashing," along with a screenshot of the crash, to the system via the smart glasses.

[1587] Terminal

[1588] The smart glasses (e.g., Google Glass Enterprise Edition) used as the terminal are responsible for receiving image and audio data sent by the user and transmitting this data to the server. The terminal also has the function of displaying requests and notifications from the server to the user.

[1589] server

[1590] The server performs the following sequence of operations:

[1591] 1. Data Receipt and Analysis

[1592] The server receives image and audio data sent from the device. It uses TensorFlow and OpenCV for image analysis, and IBM Watson Speech to Text for audio analysis. It also uses the Microsoft Azure Emotion API for emotion recognition. These tools are used to extract specific elements in images (e.g., error messages) and specific keywords from audio, as well as the user's emotions.

[1593] 2. Identifying and providing missing information

[1594] The server identifies missing information based on the analysis results. For example, if an error log has not been provided, it determines that it is necessary. In this case, it generates a prompt message such as "Please provide the error log from the crash" and presents it to the user via the device. If emotion recognition reveals that the user is expressing negative emotions such as anxiety or anger, it creates a message requesting a more polite response.

[1595] 3. Receiving additional information and reanalyzing

[1596] If the user provides additional information (e.g., error logs) in response to a request from the system, the terminal again sends the data to the server, which then re-analyzes the additional information and generates the final hearing items based on all the data.

[1597] Examples:

[1598] An example of a specific prompt for a factory worker asking "The machine is crashing" is:

[1599] Image: "Please take a picture of the screen where the machine stops."

[1600] Voice: "Please describe the crash in a voice message."

[1601] The server analyzes this data, and if it determines that there is missing information, it generates a request, for example, "Please provide the error log from the crash," and notifies the user again via the terminal. The user provides the error log and submits it again, and the server reanalyzes it and provides the final hearing items to the responder.

[1602] This makes it possible for the entire system to automatically identify missing information and respond flexibly according to emotions.

[1603] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1604] Step 1:

[1605] The user uses the smart glasses to take a picture of the equipment malfunction and explain the situation by voice. The user's device receives the image and voice data and sends it to the server.

[1606] Input: Image data and audio data of the defect

[1607] Output: Send data to the server

[1608] Step 2:

[1609] The server receives the image data and audio data sent by the user and analyzes them, using TensorFlow and OpenCV for image analysis and IBM Watson Speech to Text for audio analysis to extract specific elements, keywords, and emotions.

[1610] Input: Received data (image data, audio data)

[1611] Output: Analysis results (specific elements in images, keywords and emotions from audio)

[1612] Operation: Received image data is processed using image analysis software to identify error messages and abnormalities. Voice data is converted into text using voice recognition software, and keywords and user sentiment are extracted.

[1613] Step 3:

[1614] The server identifies missing information based on the analysis results. For example, if an error log is missing, it automatically generates a prompt to ask the user for that information. If necessary, it also creates a corresponding message taking into account the results of sentiment analysis.

[1615] Input: Analysis results (specific elements in the image, keywords and emotions from the audio)

[1616] Output: prompt (message requesting additional information), response message according to emotion

[1617] What it does: Checks the analysis results, determines missing information, generates prompts, and adjusts the content based on the results of sentiment analysis.

[1618] Step 4:

[1619] The terminal displays the prompt sent from the server to the user and requests any additional information required from the user. The user follows the instructions and provides additional information, such as an error log.

[1620] Input: Prompt statement (message requesting additional information), response message

[1621] Output: Additional information from the user (such as error logs)

[1622] Behavior: Displays a prompt and corresponding message to the user, prompting them for additional information.

[1623] Step 5:

[1624] The user again enters the requested additional information into the terminal, which then transmits it to the server.

[1625] Input: Additional information (error log, etc.)

[1626] Output: Sending data to the server again

[1627] Operation: The device receives additional information provided by the user and uploads it to the server.

[1628] Step 6:

[1629] The server again analyzes the additional information received and combines all the data to generate a final hearing item, which is then provided to the responder.

[1630] Input: Received data again (additional information)

[1631] Output: Final hearing items

[1632] What it does: Analyzes the additional information and integrates it with existing data to create a comprehensive hearing item that is sent to responders to ensure a rapid response.

[1633] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1634] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1635] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1636] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1637] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1638] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1639] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1640] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1641] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1642] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1643] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1644] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1645] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1646] 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.

[1647] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1648] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1649] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1650] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1651] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1652] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1653] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1654] The following is further disclosed regarding the above embodiment.

[1655] (Claim 1)

[1656] means for receiving image data sent from a user;

[1657] means for analyzing the received image data and recognizing specific elements within the screen;

[1658] A means for receiving and analyzing text data sent from a user to extract specific keywords and situation descriptions;

[1659] means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user;

[1660] A means for generating interview items based on the analysis results and additional information obtained and providing them to responders;

[1661] A system including:

[1662] (Claim 2)

[1663] The system of claim 1, which utilizes multimodal generative AI to analyze image data and text data.

[1664] (Claim 3)

[1665] 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item.

[1666] "Example 1"

[1667] (Claim 1)

[1668] means for receiving image data sent from a user;

[1669] means for analyzing the received image data and recognizing specific elements within the screen;

[1670] A means for receiving and analyzing text data sent from a user to extract specific keywords and situation descriptions;

[1671] means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user;

[1672] A means for generating interview items based on the analysis results and additional information obtained and providing them to responders;

[1673] means for receiving and re-analyzing additional information from the user;

[1674] A means for generating and providing final hearing items to the responder;

[1675] A system including:

[1676] (Claim 2)

[1677] 10. The system of claim 1, utilizing a generative AI model for analyzing image data and text data.

[1678] (Claim 3)

[1679] 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item.

[1680] "Application Example 1"

[1681] (Claim 1)

[1682] means for receiving image data sent from a user;

[1683] means for analyzing the received image data and recognizing specific elements within the screen;

[1684] A means for receiving and analyzing text data sent from a user to extract specific keywords and situation descriptions;

[1685] means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user;

[1686] A means for generating interview items based on the analysis results and additional information obtained and providing them to responders;

[1687] A means installed on a smart device and applied to inquiries regarding support for security devices;

[1688] A system including:

[1689] (Claim 2)

[1690] The system of claim 1, which utilizes multimodal generative AI to analyze image data and text data.

[1691] (Claim 3)

[1692] 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item.

[1693] "Example 2: Combining Emotion Engines"

[1694] (Claim 1)

[1695] means for receiving image data sent from a user;

[1696] means for analyzing the received image data and recognizing specific elements within the screen;

[1697] A means for receiving and analyzing text data sent from a user to extract specific keywords and situation descriptions;

[1698] means for receiving and analyzing voice data to recognize a user's emotion;

[1699] means for identifying missing information based on the analysis results of the image data, text data, and voice data, and presenting additional information to the user;

[1700] A means for generating interview items based on the analysis results and additional information obtained and providing them to responders;

[1701] A system including:

[1702] (Claim 2)

[1703] The system of claim 1, which utilizes multimodal generative AI to analyze image data and text data.

[1704] (Claim 3)

[1705] 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item.

[1706] "Application example 2 when combining emotion engines"

[1707] (Claim 1)

[1708] means for receiving image data sent from a user;

[1709] means for analyzing the received image data and recognizing specific elements within the screen;

[1710] A means for receiving and analyzing text data and voice data sent from a user to extract specific keywords and emotions;

[1711] means for identifying missing information based on the analysis results of the image data, text data, and voice data, and presenting additional information to the user;

[1712] means for generating an appropriate support message according to the user's emotions based on the result of the emotion analysis;

[1713] A means for generating interview items based on the analysis results and additional information obtained and providing them to responders;

[1714] A system including:

[1715] (Claim 2)

[1716] The system of claim 1 utilizes multimodal generative AI to analyze image data, text data, and audio data.

[1717] (Claim 3)

[1718] 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item. [Explanation of symbols]

[1719] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving image data sent from a user; means for analyzing the received image data and recognizing specific elements within the screen; A means for receiving and analyzing text data sent from a user to extract specific keywords and situation descriptions; means for identifying missing information based on the analysis results of the image data and text data and presenting additional information to the user; A means for generating interview items based on the analysis results and additional information obtained and providing them to responders; A system including:

2. The system of claim 1, which utilizes multimodal generative AI to analyze image data and text data.

3. 2. The system according to claim 1, further comprising means for receiving additional information sent by the user and reanalyzing the information as a final hearing item.

Images