system

Abstract

Provide a system. [Solution] an input means for a user to input visual information; a voice input means for a user to input voice data; analysis means for analyzing data input from the input means and the voice input means; generating means for generating an optimal solution based on the analyzed data; a presentation means for presenting the generated solution to a user; a feedback means for feeding back the results of implementing the proposed solution; learning means for learning results received from said feedback means; A system including:

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] In modern society, users are required to quickly and effectively solve the various problems and worries they face in their daily lives. However, currently, when users try to solve problems themselves using visual and auditory information, they often find it difficult to identify the problem and find an appropriate solution. As a result, users end up spending a great deal of effort and time solving the problem. There is an urgent need to solve this problem and provide a more efficient and reliable means of problem-solving. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means: a system including an input means for a user to input visual information, a voice input means for a user to input voice data, an analysis means for analyzing the input data, a generation means for generating an optimal solution based on the analyzed data, a presentation means for presenting the generated solution to the user, a feedback means for feeding back the results of implementing the presented solution, and a learning means for learning the feedback results. This system can quickly and accurately provide solutions to the user's visual and auditory problems, improving problem-solving efficiency.

[0006] "User" refers to the entity that uses the system to seek a solution to a problem.

[0007] "Visual information" refers to image and video data that a user provides to the system through a visual input device such as a camera.

[0008] "Input means" refers to the device or interface that a user uses to input visual information into a system.

[0009] "Voice Data" means voice information provided by a user to a system through a voice input device such as a microphone.

[0010] "Voice input means" means a device or interface used by a user to input voice data into a system.

[0011] "Analysis tools" refers to software and algorithms used to analyze visual and audio data and identify problems.

[0012] "Generator" refers to software or algorithms used to generate optimal solutions based on the analyzed data.

[0013] "Presentation medium" refers to the device or interface used to present the generated solution to the user.

[0014] "Feedback means" refers to a device or interface that provides the results of a solution implemented by a user to the system.

[0015] "Learning tools" refers to software and algorithms that allow the system to continually learn from user feedback and improve the accuracy of future solutions.

[0016] "Image analysis means" refers to software or algorithms that analyze visual information input into the system and recognize specific features or content.

[0017] "Speech recognition means" refers to software or algorithms used to analyze voice data input into the system and convert it into text data.

[0018] A "system" refers to a set of devices and programs that combine the above means to solve the user's problems. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[0041] System Overview

[0042] User Actions

[0043] Users first launch a dedicated application on their smartphone (device), then use the camera to capture visual information (e.g., an image of the problem) and the audio microphone to describe the problem in detail. If necessary, users can also enter additional information in text.

[0044] Device behavior

[0045] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[0046] Server Operation

[0047] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[0048] 1. Analysis of imaging data:

[0049] The server uses image analysis tools (e.g., computer vision algorithms) to analyze the image data and extract features, such as determining whether graffiti in a parking lot is written in white chalk.

[0050] 2. Analysis of audio data:

[0051] The server converts the voice data into text data using a speech recognition method (e.g., a speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[0052] 3. Integration of analysis results:

[0053] The server integrates the results of the analysis of the visual information and the audio data, and generates an optimal solution using a generation means.

[0054] 4. Propose a solution:

[0055] The generated solution is converted into a user-friendly format (e.g., text, audio, image) and sent to the device.

[0056] Feedback and Learning

[0057] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0058] Specific examples

[0059] Visual information input and analysis

[0060] When a user wants to remove graffiti written on the asphalt of a parking lot, they take a picture of the graffiti with their smartphone. A voice prompt then asks, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[0061] The device sends this data to a server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti."

[0062] Solution generation and presentation

[0063] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti," suggesting specific steps such as "pour boiling water on it, scrub with a brush, and finish with detergent."

[0064] The device will provide the user with text and audio instructions.

[0065] Feedback and Learning

[0066] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[0067] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will greatly improve the efficiency and accuracy of problem solving.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). Next, they use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[0071] Step 2:

[0072] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[0073] Step 3:

[0074] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the image is graffiti written in white chalk on asphalt).

[0075] Step 4:

[0076] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[0077] Step 5:

[0078] The server combines the analyzed visual and audio data and inputs the dataset into a generator, which generates an optimal solution (e.g., "How to pour hot water, scrub with a brush, and finish with detergent").

[0079] Step 6:

[0080] The server converts the generated solution into a format that is easy for the user to understand (text, image, audio, etc.), creates a data packet containing the solution, and sends it to the device as an HTTP response.

[0081] Step 7:

[0082] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in a format that is easy to understand (e.g., displaying and playing the solution in text and audio).

[0083] Step 8:

[0084] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[0085] Step 9:

[0086] The server analyzes the received feedback data, adds the analysis results to the training dataset of the generative AI model, and updates the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0087] Example 1

[0088] 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."

[0089] To quickly and effectively solve the various visual and auditory problems users encounter in their daily lives and at work, a system that can integrate and appropriately analyze multiple input data (visual information, audio data, text data) is required. However, current technology lacks the means to integrate and analyze such multiple data and present optimal solutions. As a result, users often spend a great deal of time and effort solving problems.

[0090] 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.

[0091] In this invention, the server includes an analysis means for analyzing visual information using an image analysis means, an analysis means for converting audio data into text data using a voice recognition means, a generation means for generating an optimal solution based on the analyzed visual information and audio data, a presentation means for converting the generated solution into a format that is easy for the user to understand and presenting it, a feedback means for providing feedback on the results of implementing the presented solution, and a learning means for learning from the results received from the feedback means and updating the generative AI model. This enables the analysis of visual and auditory problems and the provision of optimal solutions to be performed quickly and effectively. The user can instantly obtain a solution to the problem, and the system also learns based on the feedback, improving the accuracy of future problem-solving.

[0092] A "user" is an individual or organization that uses the system to input visual information and voice data to solve a problem.

[0093] "Input means" refers to a device or interface that allows a user to input visual information into a system.

[0094] "Audio input means" refers to a microphone or voice recording device that allows a user to input voice data into the system.

[0095] A "terminal" is an electronic device that compiles visual information and audio data entered by a user into a single data set and sends it to a server as an HTTP request.

[0096] A "server" is a computer system that receives data sets sent from terminals and processes analysis, solutions, presentation, and feedback.

[0097] "Image analysis means" refers to computer vision algorithms and software for analyzing visual information and extracting its features.

[0098] "Speech recognition means" refers to software or APIs for converting voice data into text data.

[0099] "Analysis means" is a general term for various tools and techniques for analyzing input visual information and audio data.

[0100] "Generative means" refers to AI models or algorithms that generate optimal solutions based on analyzed data.

[0101] The "presentation means" is a display or audio output device for presenting the generated solution to the user.

[0102] A "feedback means" is an interface that allows a user to report to the system the results of implementing a proposed solution.

[0103] "Learning methods" are algorithms and data processing techniques that update generative AI models based on data obtained from feedback and improve their accuracy.

[0104] A "generative AI model" is an artificial intelligence model that generates optimal solutions to users' concerns and problems.

[0105] A "prompt" is a specific text instruction for inputting instructions into a generative AI model.

[0106] This invention relates to a system in which a user inputs visual information and voice data using a smartphone, and a server analyzes the data to generate and present optimal solutions. This system operates by the user, device, and server each playing a specific role and cooperating with each other.

[0107] System configuration

[0108] User Actions

[0109] The user launches the dedicated application installed on their smartphone, then performs the following operations:

[0110] 1. Visual input: Use your smartphone camera to take a picture of the problem object, for example, graffiti on the asphalt of a parking lot.

[0111] 2. Voice input: Use your smartphone's microphone to verbally describe the problem in detail, for example, "Please tell me how to remove this graffiti."

[0112] 3. Enter text information: If necessary, enter detailed information such as the number of days since the event and the location in text.

[0113] Device behavior

[0114] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[0115] Server Operation

[0116] The server receives the data set sent from the device and performs the following processes:

[0117] 1. Image data analysis: The server uses image analysis tools (e.g., computer vision algorithms) to analyze visual information. Specifically, libraries such as OpenCV can be used. For example, to identify graffiti written in white chalk on the asphalt of a parking lot.

[0118] 2. Analysis of voice data: The server converts the voice data into text data using a voice recognition means (e.g., a voice recognition API). For example, the Google (registered trademark) Speech-to-Text API can be used. The converted text data, along with the text information entered by the user, is analyzed by a natural language processing module (e.g., spaCy) to identify the user's concerns.

[0119] 3. Integrating the analysis results: Integrating the analyzed visual information and audio data, and generating an optimal solution using a generative AI model (e.g., GPT-4 (registered trademark)).

[0120] 4. Presenting the solution: The generated solution is converted into a format that is easy for the user to understand (e.g., text, audio, image) and sent to the device.

[0121] Feedback and Learning

[0122] The user implements the proposed solution and provides feedback on the results to the server via their device. The server then analyzes this feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0123] Specific examples

[0124] Visual information input and analysis

[0125] If a user wants to remove graffiti written on the asphalt of a parking lot, they take a photo of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[0126] Solution generation and presentation

[0127] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti." For example, it might suggest specific steps such as "pour hot water, scrub with a brush, and finish with detergent." The device then presents these steps to the user in text and voice.

[0128] Feedback and Learning

[0129] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[0130] Prompt Sentence Examples

[0131] Below is an example of a prompt sentence to input to the generative AI model.

[0132] "How do I remove graffiti written in white chalk on asphalt?"

[0133] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will significantly improve the efficiency and accuracy of problem solving.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: User enters visual information

[0136] What it does: The user uses their smartphone camera to take an image of the problem they want to solve.

[0137] Input: Visual information (image) of the problem

[0138] Output: Captured image data

[0139] Step 2: User enters voice data

[0140] What it does: The user uses their smartphone's microphone to verbally describe the details of the problem they want to solve.

[0141] Input: User's voice data

[0142] Output: Recorded audio data

[0143] Step 3: User enters text information

[0144] Specific Action: The user enters additional information related to the issue (e.g., number of days since issue occurred or detailed situation) via text into their smartphone, if necessary.

[0145] Input: User's text information

[0146] Output: The input text data

[0147] Step 4: Data integration by terminal

[0148] Specific operation: The device combines visual information, audio data, and text information input by the user into a single data set.

[0149] Input: image data, audio data, text data

[0150] Output: A consolidated dataset

[0151] Step 5: Send data by device

[0152] Specific operation: The terminal sends the integrated data set to the server as an HTTP request.

[0153] Input: Integrated dataset

[0154] Output: HTTP request sent to the server

[0155] Step 6: Image data analysis by the server

[0156] Specific operation: The server extracts image data from the received dataset and extracts features using image analysis means (e.g., OpenCV).

[0157] Input: Image data

[0158] Data processing or calculation: feature extraction by image analysis means

[0159] Output: Image analysis results (e.g., "Graffiti written in white chalk on asphalt")

[0160] Step 7: Server analyzes the audio data

[0161] Specific operation: The server converts the received voice data into text data using a speech recognition tool (e.g., Google Speech-to-Text API), and then uses a natural language processing module (e.g., spaCy) to identify the user's concerns.

[0162] Input: Audio data

[0163] Data processing or computation: Speech-to-text conversion and natural language processing

[0164] Output: Text data of the speech analysis results (e.g., "Please tell me how to erase this graffiti.")

[0165] Step 8: Server integration of analysis results

[0166] Specific operation: The server integrates the image analysis results and audio analysis results and generates the optimal solution using a generative AI model (e.g., GPT-4).

[0167] Input: Image analysis results, audio analysis results

[0168] Data manipulation or computation: Generating solutions using generative AI models

[0169] Output: The generated solution (e.g., "Pour hot water on it, scrub with a brush, and finish with detergent")

[0170] Step 9: Server converts and sends the solution

[0171] Specific operation: The server converts the generated solution into a format that is easy for the user to understand (e.g., text, audio, image) and sends it to the terminal.

[0172] Input: Generated solution

[0173] Data processing or calculation: transformation of the solution

[0174] Output: Solution data to present to the user

[0175] Step 10: Providing a solution via terminal

[0176] Specific operation: The device presents the received solution to the user via text or voice.

[0177] Input: Data for the proposed solution

[0178] Output: Present the solution to the user

[0179] Step 11: User feedback

[0180] Specific operation: After the user implements the solution, the results are fed back through the terminal.

[0181] Input: Execution result feedback (text or audio data)

[0182] Output: Feedback data

[0183] Step 12: Server analyzes feedback and learns

[0184] Specific operation: The server analyzes the feedback data and uses it as training data for the generative AI model.

[0185] Input: Feedback data

[0186] Data processing or computation: analyzing feedback data and updating generative AI models

[0187] Output: An updated generative AI model

[0188] (Application example 1)

[0189] 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."

[0190] On traditional online shopping sites, users often have problems selecting products because they cannot instantly grasp the product's features or because the means to resolve questions about the product's details are not immediately provided. Furthermore, because information from multiple data input methods is not integrated and analyzed, it is difficult to present optimal solutions to the problems users face.

[0191] 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.

[0192] In this invention, the server includes an input means for a user to input visual information, a voice input means for a user to input voice data, an analysis means for analyzing the data input from the input means and the voice input means, a generation means for generating an optimal solution based on the analyzed data, a presentation means for presenting the generated solution to the user, a feedback means for feeding back the results of implementing the presented solution, a learning means for learning the results received from the feedback means, an image analysis means for extracting product features using images, a voice recognition means for converting voice data into text data, a means for analyzing the text data using natural language processing means and understanding the user's question, and a means for presenting the user with a generated solution related to the product using a generative AI model. This makes it possible to quickly and effectively solve problems users have when selecting products.

[0193] A "user" is a person who uses this system to select products or resolve questions.

[0194] A "smartphone" is a portable information terminal that allows a user to input visual and audio data.

[0195] "Visual information" refers to product images and related images that are input by the user using a camera.

[0196] "Voice data" refers to voice information uttered by a user using a microphone, including questions and instructions.

[0197] "Input means" refers to tools or devices that allow a user to input visual information or audio data.

[0198] "Analysis means" refers to algorithms or programs for analyzing and understanding input visual information and audio data.

[0199] "Generation means" refers to the methods and mechanisms for generating optimal solutions based on the analyzed data.

[0200] "Presentation means" refers to a method or device for presenting the generated solution to the user in an easy-to-understand form.

[0201] "Feedback means" refers to the techniques and tools that allow users to return the results of their actions to the system.

[0202] "Learning tools" refers to machine learning models that analyze data from feedback and aim to improve the accuracy of future solutions.

[0203] "Image analysis means" refers to algorithms or software for analyzing visual information and recognizing products and their features.

[0204] "Speech recognition means" refers to techniques and tools for converting voice data into text.

[0205] "Natural language processing means" refers to algorithms and technologies used to analyze text data and understand users' questions and intent.

[0206] A "generative AI model" refers to an artificial intelligence model that generates optimal solutions based on analysis results.

[0207] "Prompt sentence" refers to predefined text that is input into a generative AI model.

[0208] The present invention relates to a system that allows a user to input visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[0209] System Overview

[0210] User Actions

[0211] Users first launch the dedicated application on their smartphone (device), then use the camera to take a picture of the product packaging, and then use the audio microphone to ask questions or provide details. If necessary, they can also enter additional information via text.

[0212] Device behavior

[0213] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[0214] Server Operation

[0215] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[0216] 1. Analysis of imaging data:

[0217] The server analyzes the image data using image analysis tools (e.g., Tensorflow (registered trademark) or OpenCV) to extract product features. For example, it identifies specific features such as "Brand A shampoo."

[0218] 2. Analysis of audio data:

[0219] The server converts the voice data into text using a speech recognition tool (e.g., Google Cloud Speech-to-Text API), then analyzes the converted text using a natural language processing tool (e.g., GPT-4) to understand the user's question.

[0220] 3. Integration of analysis results:

[0221] The server integrates the results of the analysis of visual information and audio data and generates an optimal solution using a generation means (e.g., a generative AI model).

[0222] 4. Propose a solution:

[0223] The generated solution is converted into a user-friendly format (e.g., text, voice) and sent to the device.

[0224] Feedback and Learning

[0225] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0226] Specific examples

[0227] A user wants to know information about "Brand A Shampoo," so they take a picture of the product package with their smartphone. They also ask aloud, "Please tell me the reviews and stock information for this product." An example of a prompt sentence is as follows:

[0228] Example prompt sentence:

[0229] A user uploaded an image of a product package and asked, "Please tell me the reviews and stock information for this product." Image analysis determined that the product was "Brand A Shampoo." Based on this, please generate the best answer for the user.

[0230] The server performs the above process, generates the optimal solution to the user's question, and sends it back to the terminal. The terminal then presents this solution to the user in text and voice. This process allows the user to quickly and accurately obtain product information.

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1:

[0233] The user launches a dedicated application on their smartphone (device), takes a picture of the product packaging with the camera, and then uses the audio microphone to input a question such as, "Please tell me the reviews and stock information for this product." The input data consists of visual information (product image) and audio data (user question).

[0234] Step 2:

[0235] The device acquires visual information (product images) and audio data input by the user, compiles it into a single dataset, and sends it to the server as an HTTP request. The input is a set of product images and audio data, and the output is a dataset in HTTP request format.

[0236] Step 3:

[0237] The server analyzes the dataset received from the device. First, it analyzes the product image using image analysis tools (such as TensorFlow or OpenCV) to extract product features (e.g., "Brand A shampoo"). The input is the product image, and the output is the extracted product features. This step also involves preprocessing the product image (resizing and noise removal).

[0238] Step 4:

[0239] The server converts the voice data into text data using a speech recognition tool (such as the Google Cloud Speech-to-Text API). The input is the voice data, and the output is the text data converted from the voice (e.g., "Please tell me the reviews and stock information for this product."). The converted text data is further analyzed using natural language processing tools to clarify the user's question and intent.

[0240] Step 5:

[0241] The server integrates the results of analysis of visual information (extracted product features) and audio data (text data converted from audio) and generates the optimal solution using a generation method (generative AI model). Specifically, it extracts product-related reviews and inventory information, and generates the information the user is looking for. The input is the integrated analysis results, and the output is the optimal solution (answer in text format).

[0242] Step 6:

[0243] The server converts the generated solution into a user-understandable format (e.g., text or voice) and sends it to the device. The input is the textual solution, and the output is the formatted data for presentation to the user.

[0244] Step 7:

[0245] The device receives the solution sent from the server and presents it to the user. Specifically, it displays the solution as text on the smartphone screen and, in some cases, uses speech synthesis to read it aloud to the user. The input is the formatted solution sent from the server, and the output is the content presented to the user.

[0246] Step 8:

[0247] The user implements the proposed solution and feeds the results back to the server via the terminal. The input is the result of the user's implementation, and the output is the feedback data.

[0248] Step 9:

[0249] The server analyzes the feedback data and uses it as training data for the generative AI model. Here, the formatted data is added to the database to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model.

[0250] 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.

[0251] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, recognizes the user's emotions based on this data, and generates and provides optimal solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. An emotion engine is also integrated to recognize the user's emotions.

[0252] System Overview

[0253] User Actions

[0254] The user first launches a dedicated application using their smartphone (device). Next, they use the camera to capture visual information (e.g., an image of the problem) and use the audio microphone to describe the problem in detail. The user's facial expressions and tone obtained from audio and visual information are also collected to identify the user's emotions. If necessary, additional information can be entered as text.

[0255] Device behavior

[0256] The device compiles the visual, audio, and textual information input by the user into a single dataset, then sends the dataset to the server, which is also responsible for presenting the server's solutions and the user's emotion recognition results.

[0257] Server Operation

[0258] The server receives the data set sent from the terminal and processes it as follows.

[0259] 1. Analysis of imaging data:

[0260] The server uses an image analysis module (e.g., computer vision algorithms) to analyze the image data and extract its features, for example, to determine whether graffiti in a parking lot is written in white chalk.

[0261] 2. Analysis of audio data:

[0262] The server converts the voice data into text data using a speech recognition module (e.g., speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[0263] 3. Emotion Recognition:

[0264] The server uses an emotion engine to identify the user's emotions from the audio data and visual information, for example, determining whether the user is anxious or calm from the tone of their voice and facial expressions.

[0265] 4. Integrating the analysis results and generating solutions:

[0266] The server combines the analyzed visual information, audio data, and emotion recognition results to generate an optimal solution. The generated solution is adjusted according to the user's emotions. For example, if the user is impatient, a simpler and faster solution will be presented.

[0267] 5. Propose a solution:

[0268] The generated solution is converted into a user-friendly format (text, audio, image) and sent to the device.

[0269] Feedback and Learning

[0270] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes this feedback data and uses it as training data for the generative AI model and emotion engine. This will improve the accuracy of solutions to similar problems and emotion recognition in the future.

[0271] Specific examples

[0272] Input and analysis of visual information and emotion recognition

[0273] If a user wants to remove graffiti from the asphalt of a parking lot, they can take a picture of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." Furthermore, if the user is anxious, the system will recognize their emotion from their facial expression and tone of voice.

[0274] The device sends this data to the server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti." The emotion engine then recognizes that the user is anxious.

[0275] Solution generation and presentation

[0276] Based on the integrated analysis and emotion recognition results, the server uses a generative AI model to generate solutions, such as suggesting specific steps to quickly remove graffiti: pour boiling water over it, scrub with a brush, and finish with detergent.

[0277] The device will explain these steps to the user in text and audio, and will simplify the steps to accommodate the user's impatience.

[0278] Feedback and Learning

[0279] After implementing the solution, the user provides feedback on the results to the server via their device (e.g., "The graffiti has completely disappeared"). The server receives this feedback and updates the generative AI model and emotion engine to improve the accuracy of problem-solving in future.

[0280] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems they encounter in their daily lives, incorporating emotion recognition, which will significantly improve the efficiency and accuracy of problem-solving.

[0281] The processing flow will be explained below.

[0282] Step 1:

[0283] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). They also use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[0284] Step 2:

[0285] The device compiles the visual, audio, and text information input by the user into a single dataset. It then uses an emotion engine to recognize the user's emotions from the audio and visual information. The dataset, which also includes the emotion recognition results, is then sent to the server.

[0286] Step 3:

[0287] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the data is graffiti written in white chalk on asphalt).

[0288] Step 4:

[0289] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[0290] Step 5:

[0291] The server analyzes the results of the emotion engine to identify the user's emotional state (e.g., anxious, calm). The server then combines the analyzed visual information, audio data, and emotion recognition results and inputs the resulting dataset into the generator.

[0292] Step 6:

[0293] The generator generates an optimal solution based on the integrated data (e.g., "Pour hot water, scrub with a brush, and finish with detergent"), which is customized according to the user's emotional state (e.g., if the user is impatient, simplify the steps).

[0294] Step 7:

[0295] The server converts the generated solution into a user-friendly format (text, image, audio), creates a data packet containing the converted solution, and sends it to the device as an HTTP response.

[0296] Step 8:

[0297] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in an easy-to-understand format (e.g., displaying and playing the solution in text and audio). At this time, it also displays the emotion recognition results so that the user can understand their own emotional state.

[0298] Step 9:

[0299] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[0300] Step 10:

[0301] The server analyzes the received feedback data and adds the analysis results to the training datasets of the generative AI model and emotion engine, updating them to improve the accuracy of solutions to similar problems in the future and the accuracy of emotion recognition.

[0302] Example 2

[0303] 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."

[0304] In modern life, it is important to provide quick and effective solutions to the various problems users face. However, with conventional methods, it has been difficult to provide solutions that take into account the user's emotional state. For example, it is difficult to present different solutions depending on whether the user is anxious or calm. In addition, there are limited means to continuously train the system through feedback and improve its accuracy. To solve these challenges, a system that recognizes the user's emotions and provides optimal solutions based on those emotions is needed.

[0305] 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.

[0306] In this invention, the server includes an analysis means, an emotion recognition means, and a generation means. This makes it possible to analyze the visual information and voice data input by the user, recognize the user's emotions, and generate and present optimal solutions according to that state. Furthermore, feedback from users can be collected and analyzed by a learning means, and the accuracy of the system can be continuously improved. In this way, a system is realized that can provide solutions optimized for individual situations for the various problems faced by users.

[0307] "Image input means" refers to a function that allows the user to input visual information.

[0308] "Voice input means" refers to a function that allows a user to input voice data.

[0309] The "data set generating means" refers to a function that combines data input from the image input means and the voice input means into one data set.

[0310] "Data transmission means" refers to a function for transmitting the data set to the server.

[0311] "Analysis means" refers to a function in the server that analyzes the dataset.

[0312] The "emotion recognition means" refers to a function that recognizes the user's emotions based on the data analyzed by the analysis means.

[0313] The "generation means" refers to a function that generates an optimal solution by taking into account the results of the emotion recognition means.

[0314] The "presentation means" refers to a function that presents the generated solution to the user.

[0315] The "feedback means" refers to a function for reflecting the results of implementing the proposed solution.

[0316] The "learning means" refers to a function that learns the system based on the results received from the feedback means and improves accuracy.

[0317] "Image analysis means" refers to a function for analyzing visual information.

[0318] "Speech recognition means" refers to a function that converts voice data into text data.

[0319] The present invention relates to a system that allows a user to input visual information and voice data using a smart device, recognizes the user's emotions based on this data, and generates and provides appropriate solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. Specific embodiments are described in detail below.

[0320] User Actions

[0321] 1. Launch the dedicated app

[0322] The user launches a dedicated app on a smart device (e.g., a smartphone). The app's generic name is "Problem Solving Assistant."

[0323] 2. Visual information input

[0324] Users use their smart device's camera to take an image of the problem, for example, graffiti in a parking lot.

[0325] 3. Inputting voice data

[0326] Users can use the microphone to verbally describe the problem in detail, such as "How do I remove this graffiti?", and optionally enter additional information in text.

[0327] 4. Collecting emotional information

[0328] The user's facial expressions and tone of voice are also collected through the smart device.

[0329] Device behavior

[0330] 1. Generating the dataset

[0331] The terminal (smart device) combines the collected visual information, audio data, and text information into a single data set.

[0332] 2. Submitting the dataset

[0333] The device sends the generated data set to a server over the internet, where it is encrypted.

[0334] 3. Receiving and Displaying the Solution

[0335] The device receives solutions and emotion recognition results sent from the server, and the received information is presented to the user via text message or voice.

[0336] Server Operation

[0337] 1. Receiving Data

[0338] The server receives the data set sent from the device, stores it in a database, and begins analysis.

[0339] 2. Analysis of image data

[0340] The server uses computer vision algorithms (e.g., OpenCV) to analyze the image data, for example, to detect graffiti written in white chalk on the asphalt of a parking lot.

[0341] 3. Analysis of audio data

[0342] The server converts the voice data into text using a speech recognition API (e.g., a cloud-based speech recognition service), and then uses a natural language processing module (e.g., an open-source NLP library) to identify the user's concerns.

[0343] 4. Emotion recognition

[0344] The server uses an emotion recognition engine (e.g., a tone analyzer) to recognize the user's emotions from voice data and visual information. It determines whether the user is anxious or calm from their voice tone and facial expression.

[0345] 5. Solution Generation

[0346] The server integrates the analyzed visual information, audio data, and emotion recognition results and uses a generative AI model (e.g., an advanced language generation model) to generate an optimal solution. For example, it might suggest a quick method for removing graffiti: pour hot water over it, scrub with a brush, and finish with detergent.

[0347] 6. Submit your solution

[0348] The server sends the generated solution in a user-friendly format to the device, where the solution is presented in text and audio format.

[0349] Feedback and Learning

[0350] 1. Implementing the solution

[0351] The user follows the suggested solutions to solve the problem.

[0352] 2. Submitting Feedback

[0353] The user sends the results of the solution to the server via their device, providing feedback such as whether the graffiti has been completely removed.

[0354] 3. Processing Feedback

[0355] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine, thereby improving the system's problem-solving accuracy and emotion recognition accuracy.

[0356] Specific examples

[0357] If a user wants to remove graffiti written on the asphalt of a parking lot, they first take a picture of the graffiti with their smart device and then provide a voice instruction saying, "Please tell me how to remove this graffiti." The device then sends this visual and voice information to the server. The server analyzes this data, uses image analysis means to determine that it is "graffiti made with white chalk," and uses voice recognition means to convert the user's request into text. The server then uses an emotion recognition engine to recognize that the user is impatient and generates a solution appropriate to that situation. For example, it provides specific instructions such as, "To quickly remove graffiti, use hot water and a brush."

[0358] As such, the present invention is a system that quickly provides solutions optimized for individual situations to various problems faced by users, thereby improving user satisfaction and problem-solving efficiency.

[0359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0360] Processing step flow

[0361] Step 1:

[0362] Launching the dedicated app

[0363] The user launches a dedicated app on their smart device. The input is the operation to launch the app, and the output is the display of the app's home screen. The app launches when the user taps the app's icon.

[0364] Step 2:

[0365] Visual information input

[0366] The user activates the camera on their smart device and takes a picture of the target object. The input is the image data captured by the camera, and the output is saved as an image file on the device. The user opens the camera app and taps the shutter button to capture the image.

[0367] Step 3:

[0368] Inputting audio data

[0369] The user uses the microphone on their smart device to describe the details of the problem. The input is audio data collected by the microphone, and the output is saved as an audio file on the device. The user presses the microphone button in the app and speaks, "Please tell me how to erase this graffiti."

[0370] Step 4:

[0371] Collecting emotional information

[0372] The user's facial expressions and voice tone are collected by the device's camera and microphone. The input is facial expression data and voice tone data captured by the camera, and the output is the data necessary for analysis to identify emotions. Emotional information such as the user's impatience or calmness is collected.

[0373] Step 5:

[0374] Generating the dataset

[0375] The device combines visual information, audio data, and text information into a single dataset. The input is captured images, recorded audio, and collected emotion data, and the output is a unified dataset. The device combines these different data formats into a single file.

[0376] Step 6:

[0377] Submitting a Dataset

[0378] The terminal sends the generated dataset to the server. The input is the dataset, and the output is the transmission result to the server (such as a transmission completion message). The dataset is encrypted and sent to the server over the network.

[0379] Step 7:

[0380] Receiving data

[0381] The server receives the dataset sent from the device. The input is the received dataset, and the output is the data stored in the server's database. The server stores the received data in the database in preparation for analysis.

[0382] Step 8:

[0383] Image data analysis

[0384] The server analyzes the image data using a computer vision algorithm (e.g., OpenCV) and extracts features. The input is the image data, and the output is the analyzed feature information. For example, it can detect graffiti written in chalk and identify its location and color.

[0385] Step 9:

[0386] Analysis of audio data

[0387] The server converts the voice data into text data using a voice recognition API (e.g., a cloud-based voice recognition service). The input is voice data, and the output is text data. The user's speech, "Please tell me how to erase this graffiti," is converted into text.

[0388] Step 10:

[0389] emotion recognition

[0390] The server uses an emotion engine (e.g., tone analyzer) to recognize the user's emotion from voice tone and visual information. The input is voice data and facial expression data, and the output is the user's emotional state. It identifies whether the user is anxious or calm.

[0391] Step 11:

[0392] Integrating analysis results and generating solutions

[0393] The server integrates the analyzed visual information, audio data, and emotion recognition results, and generates an appropriate solution using a generative AI model (e.g., an advanced language generation model). The input is the integrated data, and the output is the generated solution. For example, a specific procedure such as "pour boiling water over the area, scrub with a brush, and finish with detergent" may be suggested.

[0394] Step 12:

[0395] Submit a solution

[0396] The server sends the generated solution to the terminal. The input is the solution data, and the output is a transmission completion message. The solution data is converted into a format that is easy for the user to understand before being sent.

[0397] Step 13:

[0398] Providing a solution

[0399] The terminal presents the received solutions to the user. The input is the solution data received from the server, and the output is the solution information displayed to the user. The terminal presents the proposed solutions to the user in text or voice.

[0400] Step 14:

[0401] Implementing the solution

[0402] The user executes the proposed solution. The input is the proposed solution, and the output is the execution result. The user follows specific steps to solve the problem.

[0403] Step 15:

[0404] Send Feedback

[0405] After implementing the solution, the user feeds the results back to the server via their device. The input is the implementation result, and the output is the feedback data. For example, the user may report that the graffiti has completely disappeared.

[0406] Step 16:

[0407] Processing Feedback

[0408] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine. The input is the feedback data, and the output is an updated training model. This continuously improves the accuracy and effectiveness of the system.

[0409] The above is the processing flow and specific operation of the program of this system.

[0410] (Application example 2)

[0411] 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."

[0412] Currently, many security systems face challenges in providing appropriate information and responding quickly when users feel anxious. Specifically, they are unable to fully alleviate users' anxiety because they mechanically present solutions without considering the user's emotions. Furthermore, while users who feel anxious or nervous need a quick and effective solution, current systems do not adequately support this.

[0413] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to input visual information, voice input means for the user to input voice data, analysis means for analyzing the data input from the input means and the voice input means, generation means for generating an optimal solution based on the analyzed data, presentation means for presenting the generated solution to the user, feedback means for feeding back the results of implementing the presented solution, learning means for learning the results received from the feedback means, emotion recognition means for recognizing the user's emotion, and adjustment means for adjusting the solution based on the output of the emotion recognition means. This makes it possible to provide quick and accurate security measures according to the user's emotional state.

[0414] "Visual information" refers to images and videos that users input through devices such as cameras.

[0415] "Voice data" refers to voice information input by a user using a microphone.

[0416] "Input means" refers to devices and functions for acquiring visual information and audio data.

[0417] "Analysis means" refers to a function that processes input visual information and audio data and analyzes the content thereof.

[0418] "Generation means" refers to a function that generates an optimal solution based on the data processed by the analysis means.

[0419] "Presentation means" refers to a function for displaying the generated solution to the user.

[0420] "Feedback means" refers to the function of collecting the results of users implementing the proposed solutions.

[0421] "Learning means" refers to a function that performs learning to improve the accuracy of the system based on the results received from the feedback means.

[0422] "Emotion recognition means" refers to the function of recognizing emotions from the user's tone of voice, facial expressions, etc.

[0423] The "adjustment means" refers to a function that adjusts the generated solution according to the user's emotional state based on the output of the emotion recognition means.

[0424] To implement this invention, it is necessary to build a system that allows a user to input visual information and voice data using a smartphone, recognize emotions based on that data, and generate and present optimal solutions. To realize this system, the following hardware and software are used in combination.

[0425] Hardware

[0426] Smartphone: A device equipped with a camera and microphone that allows the user to input visual and audio data.

[0427] Server: The computational resources for analyzing data and generating and coordinating solutions.

[0428] software

[0429] Smartphone application (iOS / ANDROID (registered trademark)): Has the function of collecting visual information and audio data and sending it to a server.

[0430] Image analysis modules (e.g., OpenCV, TensorFlow): Analyze visual information and identify security vulnerabilities.

[0431] Speech recognition APIs (e.g., Google Speech-to-Text, Amazon Transcribe): Converts voice data into text data.

[0432] Emotion recognition engine (e.g., Microsoft® Azure® Emotion API, Amazon Rekognition): Recognizes emotions from the user's tone of voice, facial expressions, etc.

[0433] Generative AI model: Generates optimal solutions based on analyzed data.

[0434] Feedback collection module: Collects the results of user actions and uses them as learning data for the system.

[0435] System Operation Overview

[0436] 1. Input method: The user takes visual information (e.g., images of the area around their home) using the smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using the microphone.

[0437] 2. Data transmission: The smartphone application transmits these data to the server as a dataset.

[0438] 3. Data analysis: The server analyzes visual information using an image analysis module, converts voice data into text using a voice recognition API, and analyzes the user's emotions using an emotion recognition engine.

[0439] 4. Solution generation and adjustment: The generative AI model generates optimal solutions based on the analysis data and adjusts the solutions based on emotion recognition results. For example, if the user is in a hurry, it will provide a quick and easy solution.

[0440] 5. Presenting a solution: The generated solution is sent to the user's smartphone and presented to them via text or voice.

[0441] 6. Feedback collection and learning: The user implements the proposed solution and provides feedback on the results to the server via their smartphone. The server uses this feedback to update the learning data and improve the accuracy of the system.

[0442] Specific examples

[0443] When a user feels unsure about the security situation at home at night, they can take a video of their garden with their smartphone camera and ask, "Where are you worried about tonight?" The smartphone application sends this data to a server, and the generative AI model uses the analysis and emotion recognition results to quickly and accurately generate solutions. For example, it provides specific instructions to the user via text and voice, such as, "Adding lighting to the north side of the garden and adjusting the position of the security camera would be effective."

[0444] Prompt Sentence Examples

[0445] text

[0446] Please check the security situation in the area and let us know what measures are in place to prevent crime. Users are very anxious.

[0447] Such a system will enable users to quickly resolve security concerns, and will hopefully continue to improve its accuracy and effectiveness through feedback gathering and learning.

[0448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0449] Step 1:

[0450] A user takes visual information (e.g., images of the area around their home) using a smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using a microphone. At this time, the user also includes facial expressions and tone of voice that express their emotional state.

[0451] Step 2:

[0452] The device collects the captured image data and recorded audio data and compiles them into a single dataset, which contains both visual information and audio data.

[0453] Step 3:

[0454] The device sends the dataset to the server, which stores the received dataset for analysis.

[0455] Step 4:

[0456] The server analyzes visual information using image analysis modules (e.g., OpenCV, TensorFlow), for example, to identify security vulnerabilities in image data around the home. The results of this analysis are generated as output.

[0457] Step 5:

[0458] The server converts the voice data into text data using a speech recognition API (e.g., Google Speech-to-Text, Amazon Transcribe). For example, the voice saying "Where are you worried about tonight?" is output as text data.

[0459] Step 6:

[0460] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition) to recognize the user's emotions. It identifies whether the user is anxious or calm from their tone of voice and facial expressions. The recognition results are generated as output.

[0461] Step 7:

[0462] The server uses a generative AI model to generate optimal solutions based on the analytical data and emotion recognition results, such as "Adding lighting to the north side of the garden and adjusting the position of security cameras would be effective."

[0463] Step 8:

[0464] The server sends the generated solution in text or audio format to the device, which then presents the solution to the user. Specifically, the solution is displayed as text on the smartphone screen or notified to the user by audio.

[0465] Step 9:

[0466] The user implements the proposed solution and sends the results back to the server via their smartphone, for example, "Adding lighting to the north side of the garden has improved crime prevention."

[0467] Step 10:

[0468] The server collects feedback data and stores it as training data, which updates the generative AI model and emotion recognition engine, improving the accuracy of the system.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] [Second embodiment]

[0473] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0474] 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.

[0475] 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).

[0476] 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.

[0477] 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.

[0478] 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).

[0479] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0480] 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.

[0481] 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.

[0482] 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.

[0483] 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.

[0484] 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."

[0485] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[0486] System Overview

[0487] User Actions

[0488] Users first launch a dedicated application on their smartphone (device), then use the camera to capture visual information (e.g., an image of the problem) and the audio microphone to describe the problem in detail. If necessary, users can also enter additional information in text.

[0489] Device behavior

[0490] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[0491] Server Operation

[0492] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[0493] 1. Analysis of imaging data:

[0494] The server uses image analysis tools (e.g., computer vision algorithms) to analyze the image data and extract features, such as determining whether graffiti in a parking lot is written in white chalk.

[0495] 2. Analysis of audio data:

[0496] The server converts the voice data into text data using a speech recognition method (e.g., a speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[0497] 3. Integration of analysis results:

[0498] The server integrates the results of the analysis of the visual information and the audio data, and generates an optimal solution using a generation means.

[0499] 4. Propose a solution:

[0500] The generated solution is converted into a user-friendly format (e.g., text, audio, image) and sent to the device.

[0501] Feedback and Learning

[0502] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0503] Specific examples

[0504] Visual information input and analysis

[0505] When a user wants to remove graffiti written on the asphalt of a parking lot, they take a picture of the graffiti with their smartphone. A voice prompt then asks, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[0506] The device sends this data to a server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti."

[0507] Solution generation and presentation

[0508] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti," suggesting specific steps such as "pour boiling water on it, scrub with a brush, and finish with detergent."

[0509] The device will provide the user with text and audio instructions.

[0510] Feedback and Learning

[0511] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[0512] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will greatly improve the efficiency and accuracy of problem solving.

[0513] The processing flow will be explained below.

[0514] Step 1:

[0515] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). Next, they use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[0516] Step 2:

[0517] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[0518] Step 3:

[0519] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the image is graffiti written in white chalk on asphalt).

[0520] Step 4:

[0521] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[0522] Step 5:

[0523] The server combines the analyzed visual and audio data and inputs the dataset into a generator, which generates an optimal solution (e.g., "How to pour hot water, scrub with a brush, and finish with detergent").

[0524] Step 6:

[0525] The server converts the generated solution into a format that is easy for the user to understand (text, image, audio, etc.), creates a data packet containing the solution, and sends it to the device as an HTTP response.

[0526] Step 7:

[0527] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in a format that is easy to understand (e.g., displaying and playing the solution in text and audio).

[0528] Step 8:

[0529] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[0530] Step 9:

[0531] The server analyzes the received feedback data, adds the analysis results to the training dataset of the generative AI model, and updates the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0532] Example 1

[0533] 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."

[0534] To quickly and effectively solve the various visual and auditory problems users encounter in their daily lives and at work, a system that can integrate and appropriately analyze multiple input data (visual information, audio data, text data) is required. However, current technology lacks the means to integrate and analyze such multiple data and present optimal solutions. As a result, users often spend a great deal of time and effort solving problems.

[0535] 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.

[0536] In this invention, the server includes an analysis means for analyzing visual information using an image analysis means, an analysis means for converting audio data into text data using a voice recognition means, a generation means for generating an optimal solution based on the analyzed visual information and audio data, a presentation means for converting the generated solution into a format that is easy for the user to understand and presenting it, a feedback means for providing feedback on the results of implementing the presented solution, and a learning means for learning from the results received from the feedback means and updating the generative AI model. This enables the analysis of visual and auditory problems and the provision of optimal solutions to be performed quickly and effectively. The user can instantly obtain a solution to the problem, and the system also learns based on the feedback, improving the accuracy of future problem-solving.

[0537] A "user" is an individual or organization that uses the system to input visual information and voice data to solve a problem.

[0538] "Input means" refers to a device or interface that allows a user to input visual information into a system.

[0539] "Audio input means" refers to a microphone or voice recording device that allows a user to input voice data into the system.

[0540] A "terminal" is an electronic device that compiles visual information and audio data entered by a user into a single data set and sends it to a server as an HTTP request.

[0541] A "server" is a computer system that receives data sets sent from terminals and processes analysis, solutions, presentation, and feedback.

[0542] "Image analysis means" refers to computer vision algorithms and software for analyzing visual information and extracting its features.

[0543] "Speech recognition means" refers to software or APIs for converting voice data into text data.

[0544] "Analysis means" is a general term for various tools and techniques for analyzing input visual information and audio data.

[0545] "Generative means" refers to AI models or algorithms that generate optimal solutions based on analyzed data.

[0546] The "presentation means" is a display or audio output device for presenting the generated solution to the user.

[0547] A "feedback means" is an interface that allows a user to report to the system the results of implementing a proposed solution.

[0548] "Learning methods" are algorithms and data processing techniques that update generative AI models based on data obtained from feedback and improve their accuracy.

[0549] A "generative AI model" is an artificial intelligence model that generates optimal solutions to users' concerns and problems.

[0550] A "prompt" is a specific text instruction for inputting instructions into a generative AI model.

[0551] This invention relates to a system in which a user inputs visual information and voice data using a smartphone, and a server analyzes the data to generate and present optimal solutions. This system operates by the user, device, and server each playing a specific role and cooperating with each other.

[0552] System configuration

[0553] User Actions

[0554] The user launches the dedicated application installed on their smartphone, then performs the following operations:

[0555] 1. Visual input: Use your smartphone camera to take a picture of the problem object, for example, graffiti on the asphalt of a parking lot.

[0556] 2. Voice input: Use your smartphone's microphone to verbally describe the problem in detail, for example, "Please tell me how to remove this graffiti."

[0557] 3. Enter text information: If necessary, enter detailed information such as the number of days since the event and the location in text.

[0558] Device behavior

[0559] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[0560] Server Operation

[0561] The server receives the data set sent from the device and performs the following processes:

[0562] 1. Image data analysis: The server uses image analysis tools (e.g., computer vision algorithms) to analyze visual information. Specifically, libraries such as OpenCV can be used. For example, to identify graffiti written in white chalk on the asphalt of a parking lot.

[0563] 2. Analysis of voice data: The server converts the voice data into text data using a voice recognition method (e.g., a voice recognition API). For example, the Google Speech-to-Text API can be used. The converted text data, along with the text information entered by the user, is analyzed by a natural language processing module (e.g., spaCy) to identify the user's concerns.

[0564] 3. Integrating the analysis results: Integrating the analyzed visual information and audio data and generating an optimal solution using a generative AI model (e.g., GPT-4).

[0565] 4. Presenting the solution: The generated solution is converted into a format that is easy for the user to understand (e.g., text, audio, image) and sent to the device.

[0566] Feedback and Learning

[0567] The user implements the proposed solution and provides feedback on the results to the server via their device. The server then analyzes this feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0568] Specific examples

[0569] Visual information input and analysis

[0570] If a user wants to remove graffiti written on the asphalt of a parking lot, they take a photo of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[0571] Solution generation and presentation

[0572] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti." For example, it might suggest specific steps such as "pour hot water, scrub with a brush, and finish with detergent." The device then presents these steps to the user in text and voice.

[0573] Feedback and Learning

[0574] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[0575] Prompt Sentence Examples

[0576] Below is an example of a prompt sentence to input to the generative AI model.

[0577] "How do I remove graffiti written in white chalk on asphalt?"

[0578] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will significantly improve the efficiency and accuracy of problem solving.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1: User enters visual information

[0581] What it does: The user uses their smartphone camera to take an image of the problem they want to solve.

[0582] Input: Visual information (image) of the problem

[0583] Output: Captured image data

[0584] Step 2: User enters voice data

[0585] What it does: The user uses their smartphone's microphone to verbally describe the details of the problem they want to solve.

[0586] Input: User's voice data

[0587] Output: Recorded audio data

[0588] Step 3: User enters text information

[0589] Specific Action: The user enters additional information related to the issue (e.g., number of days since issue occurred or detailed situation) via text into their smartphone, if necessary.

[0590] Input: User's text information

[0591] Output: The input text data

[0592] Step 4: Data integration by terminal

[0593] Specific operation: The device combines visual information, audio data, and text information input by the user into a single data set.

[0594] Input: image data, audio data, text data

[0595] Output: A consolidated dataset

[0596] Step 5: Send data by device

[0597] Specific operation: The terminal sends the integrated data set to the server as an HTTP request.

[0598] Input: Integrated dataset

[0599] Output: HTTP request sent to the server

[0600] Step 6: Image data analysis by the server

[0601] Specific operation: The server extracts image data from the received dataset and extracts features using image analysis means (e.g., OpenCV).

[0602] Input: Image data

[0603] Data processing or calculation: feature extraction by image analysis means

[0604] Output: Image analysis results (e.g., "Graffiti written in white chalk on asphalt")

[0605] Step 7: Server analyzes the audio data

[0606] Specific operation: The server converts the received voice data into text data using a speech recognition tool (e.g., Google Speech-to-Text API), and then uses a natural language processing module (e.g., spaCy) to identify the user's concerns.

[0607] Input: Audio data

[0608] Data processing or computation: Speech-to-text conversion and natural language processing

[0609] Output: Text data of the speech analysis results (e.g., "Please tell me how to erase this graffiti.")

[0610] Step 8: Server integration of analysis results

[0611] Specific operation: The server integrates the image analysis results and audio analysis results and generates the optimal solution using a generative AI model (e.g., GPT-4).

[0612] Input: Image analysis results, audio analysis results

[0613] Data manipulation or computation: Generating solutions using generative AI models

[0614] Output: The generated solution (e.g., "Pour hot water on it, scrub with a brush, and finish with detergent")

[0615] Step 9: Server converts and sends the solution

[0616] Specific operation: The server converts the generated solution into a format that is easy for the user to understand (e.g., text, audio, image) and sends it to the terminal.

[0617] Input: Generated solution

[0618] Data processing or calculation: transformation of the solution

[0619] Output: Solution data to present to the user

[0620] Step 10: Providing a solution via terminal

[0621] Specific operation: The device presents the received solution to the user via text or voice.

[0622] Input: Data for the proposed solution

[0623] Output: Present the solution to the user

[0624] Step 11: User feedback

[0625] Specific operation: After the user implements the solution, the results are fed back through the terminal.

[0626] Input: Execution result feedback (text or audio data)

[0627] Output: Feedback data

[0628] Step 12: Server analyzes feedback and learns

[0629] Specific operation: The server analyzes the feedback data and uses it as training data for the generative AI model.

[0630] Input: Feedback data

[0631] Data processing or computation: analyzing feedback data and updating generative AI models

[0632] Output: An updated generative AI model

[0633] (Application example 1)

[0634] 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."

[0635] On traditional online shopping sites, users often have problems selecting products because they cannot instantly grasp the product's features or because the means to resolve questions about the product's details are not immediately provided. Furthermore, because information from multiple data input methods is not integrated and analyzed, it is difficult to present optimal solutions to the problems users face.

[0636] 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.

[0637] In this invention, the server includes an input means for a user to input visual information, a voice input means for a user to input voice data, an analysis means for analyzing the data input from the input means and the voice input means, a generation means for generating an optimal solution based on the analyzed data, a presentation means for presenting the generated solution to the user, a feedback means for feeding back the results of implementing the presented solution, a learning means for learning the results received from the feedback means, an image analysis means for extracting product features using images, a voice recognition means for converting voice data into text data, a means for analyzing the text data using natural language processing means and understanding the user's question, and a means for presenting the user with a generated solution related to the product using a generative AI model. This makes it possible to quickly and effectively solve problems users have when selecting products.

[0638] A "user" is a person who uses this system to select products or resolve questions.

[0639] A "smartphone" is a portable information terminal that allows a user to input visual and audio data.

[0640] "Visual information" refers to product images and related images that are input by the user using a camera.

[0641] "Voice data" refers to voice information uttered by a user using a microphone, including questions and instructions.

[0642] "Input means" refers to tools or devices that allow a user to input visual information or audio data.

[0643] "Analysis means" refers to algorithms or programs for analyzing and understanding input visual information and audio data.

[0644] "Generation means" refers to the methods and mechanisms for generating optimal solutions based on the analyzed data.

[0645] "Presentation means" refers to a method or device for presenting the generated solution to the user in an easy-to-understand form.

[0646] "Feedback means" refers to the techniques and tools that allow users to return the results of their actions to the system.

[0647] "Learning tools" refers to machine learning models that analyze data from feedback and aim to improve the accuracy of future solutions.

[0648] "Image analysis means" refers to algorithms or software for analyzing visual information and recognizing products and their features.

[0649] "Speech recognition means" refers to techniques and tools for converting voice data into text.

[0650] "Natural language processing means" refers to algorithms and technologies used to analyze text data and understand users' questions and intent.

[0651] A "generative AI model" refers to an artificial intelligence model that generates optimal solutions based on analysis results.

[0652] "Prompt sentence" refers to predefined text that is input into a generative AI model.

[0653] The present invention relates to a system that allows a user to input visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[0654] System Overview

[0655] User Actions

[0656] Users first launch the dedicated application on their smartphone (device), then use the camera to take a picture of the product packaging, and then use the audio microphone to ask questions or provide details. If necessary, they can also enter additional information via text.

[0657] Device behavior

[0658] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[0659] Server Operation

[0660] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[0661] 1. Analysis of imaging data:

[0662] The server analyzes the image data using image analysis tools (e.g., TensorFlow or OpenCV) to extract product features. For example, it identifies specific features such as "Brand A shampoo."

[0663] 2. Analysis of audio data:

[0664] The server converts the voice data into text using a speech recognition tool (e.g., Google Cloud Speech-to-Text API), then analyzes the converted text using a natural language processing tool (e.g., GPT-4) to understand the user's question.

[0665] 3. Integration of analysis results:

[0666] The server integrates the results of the analysis of visual information and audio data and generates an optimal solution using a generation means (e.g., a generative AI model).

[0667] 4. Propose a solution:

[0668] The generated solution is converted into a user-friendly format (e.g., text, voice) and sent to the device.

[0669] Feedback and Learning

[0670] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0671] Specific examples

[0672] A user wants to know information about "Brand A Shampoo," so they take a picture of the product package with their smartphone. They also ask aloud, "Please tell me the reviews and stock information for this product." An example of a prompt sentence is as follows:

[0673] Example prompt sentence:

[0674] A user uploaded an image of a product package and asked, "Please tell me the reviews and stock information for this product." Image analysis determined that the product was "Brand A Shampoo." Based on this, please generate the best answer for the user.

[0675] The server performs the above process, generates the optimal solution to the user's question, and sends it back to the terminal. The terminal then presents this solution to the user in text and voice. This process allows the user to quickly and accurately obtain product information.

[0676] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0677] Step 1:

[0678] The user launches a dedicated application on their smartphone (device), takes a picture of the product packaging with the camera, and then uses the audio microphone to input a question such as, "Please tell me the reviews and stock information for this product." The input data consists of visual information (product image) and audio data (user question).

[0679] Step 2:

[0680] The device acquires visual information (product images) and audio data input by the user, compiles it into a single dataset, and sends it to the server as an HTTP request. The input is a set of product images and audio data, and the output is a dataset in HTTP request format.

[0681] Step 3:

[0682] The server analyzes the dataset received from the device. First, it analyzes the product image using image analysis tools (such as TensorFlow or OpenCV) to extract product features (e.g., "Brand A shampoo"). The input is the product image, and the output is the extracted product features. This step also involves preprocessing the product image (resizing and noise removal).

[0683] Step 4:

[0684] The server converts the voice data into text data using a speech recognition tool (such as the Google Cloud Speech-to-Text API). The input is the voice data, and the output is the text data converted from the voice (e.g., "Please tell me the reviews and stock information for this product."). The converted text data is further analyzed using natural language processing tools to clarify the user's question and intent.

[0685] Step 5:

[0686] The server integrates the results of analysis of visual information (extracted product features) and audio data (text data converted from audio) and generates the optimal solution using a generation method (generative AI model). Specifically, it extracts product-related reviews and inventory information, and generates the information the user is looking for. The input is the integrated analysis results, and the output is the optimal solution (answer in text format).

[0687] Step 6:

[0688] The server converts the generated solution into a user-understandable format (e.g., text or voice) and sends it to the device. The input is the textual solution, and the output is the formatted data for presentation to the user.

[0689] Step 7:

[0690] The device receives the solution sent from the server and presents it to the user. Specifically, it displays the solution as text on the smartphone screen and, in some cases, uses speech synthesis to read it aloud to the user. The input is the formatted solution sent from the server, and the output is the content presented to the user.

[0691] Step 8:

[0692] The user implements the proposed solution and feeds the results back to the server via the terminal. The input is the result of the user's implementation, and the output is the feedback data.

[0693] Step 9:

[0694] The server analyzes the feedback data and uses it as training data for the generative AI model. Here, the formatted data is added to the database to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model.

[0695] 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.

[0696] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, recognizes the user's emotions based on this data, and generates and provides optimal solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. An emotion engine is also integrated to recognize the user's emotions.

[0697] System Overview

[0698] User Actions

[0699] The user first launches a dedicated application using their smartphone (device). Next, they use the camera to capture visual information (e.g., an image of the problem) and use the audio microphone to describe the problem in detail. The user's facial expressions and tone obtained from audio and visual information are also collected to identify the user's emotions. If necessary, additional information can be entered as text.

[0700] Device behavior

[0701] The device compiles the visual, audio, and textual information input by the user into a single dataset, then sends the dataset to the server, which is also responsible for presenting the server's solutions and the user's emotion recognition results.

[0702] Server Operation

[0703] The server receives the data set sent from the terminal and processes it as follows.

[0704] 1. Analysis of imaging data:

[0705] The server uses an image analysis module (e.g., computer vision algorithms) to analyze the image data and extract its features, for example, to determine whether graffiti in a parking lot is written in white chalk.

[0706] 2. Analysis of audio data:

[0707] The server converts the voice data into text data using a speech recognition module (e.g., speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[0708] 3. Emotion Recognition:

[0709] The server uses an emotion engine to identify the user's emotions from the audio data and visual information, for example, determining whether the user is anxious or calm from the tone of their voice and facial expressions.

[0710] 4. Integrating the analysis results and generating solutions:

[0711] The server combines the analyzed visual information, audio data, and emotion recognition results to generate an optimal solution. The generated solution is adjusted according to the user's emotions. For example, if the user is impatient, a simpler and faster solution will be presented.

[0712] 5. Propose a solution:

[0713] The generated solution is converted into a user-friendly format (text, audio, image) and sent to the device.

[0714] Feedback and Learning

[0715] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes this feedback data and uses it as training data for the generative AI model and emotion engine. This will improve the accuracy of solutions to similar problems and emotion recognition in the future.

[0716] Specific examples

[0717] Input and analysis of visual information and emotion recognition

[0718] If a user wants to remove graffiti from the asphalt of a parking lot, they can take a picture of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." Furthermore, if the user is anxious, the system will recognize their emotion from their facial expression and tone of voice.

[0719] The device sends this data to the server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti." The emotion engine then recognizes that the user is anxious.

[0720] Solution generation and presentation

[0721] Based on the integrated analysis and emotion recognition results, the server uses a generative AI model to generate solutions, such as suggesting specific steps to quickly remove graffiti: pour boiling water over it, scrub with a brush, and finish with detergent.

[0722] The device will explain these steps to the user in text and audio, and will simplify the steps to accommodate the user's impatience.

[0723] Feedback and Learning

[0724] After implementing the solution, the user provides feedback on the results to the server via their device (e.g., "The graffiti has completely disappeared"). The server receives this feedback and updates the generative AI model and emotion engine to improve the accuracy of problem-solving in future.

[0725] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems they encounter in their daily lives, incorporating emotion recognition, which will significantly improve the efficiency and accuracy of problem-solving.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). They also use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[0729] Step 2:

[0730] The device compiles the visual, audio, and text information input by the user into a single dataset. It then uses an emotion engine to recognize the user's emotions from the audio and visual information. The dataset, which also includes the emotion recognition results, is then sent to the server.

[0731] Step 3:

[0732] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the data is graffiti written in white chalk on asphalt).

[0733] Step 4:

[0734] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[0735] Step 5:

[0736] The server analyzes the results of the emotion engine to identify the user's emotional state (e.g., anxious, calm). The server then combines the analyzed visual information, audio data, and emotion recognition results and inputs the resulting dataset into the generator.

[0737] Step 6:

[0738] The generator generates an optimal solution based on the integrated data (e.g., "Pour hot water, scrub with a brush, and finish with detergent"), which is customized according to the user's emotional state (e.g., if the user is impatient, simplify the steps).

[0739] Step 7:

[0740] The server converts the generated solution into a user-friendly format (text, image, audio), creates a data packet containing the converted solution, and sends it to the device as an HTTP response.

[0741] Step 8:

[0742] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in an easy-to-understand format (e.g., displaying and playing the solution in text and audio). At this time, it also displays the emotion recognition results so that the user can understand their own emotional state.

[0743] Step 9:

[0744] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[0745] Step 10:

[0746] The server analyzes the received feedback data and adds the analysis results to the training datasets of the generative AI model and emotion engine, updating them to improve the accuracy of solutions to similar problems in the future and the accuracy of emotion recognition.

[0747] Example 2

[0748] 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."

[0749] In modern life, it is important to provide quick and effective solutions to the various problems users face. However, with conventional methods, it has been difficult to provide solutions that take into account the user's emotional state. For example, it is difficult to present different solutions depending on whether the user is anxious or calm. In addition, there are limited means to continuously train the system through feedback and improve its accuracy. To solve these challenges, a system that recognizes the user's emotions and provides optimal solutions based on those emotions is needed.

[0750] 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.

[0751] In this invention, the server includes an analysis means, an emotion recognition means, and a generation means. This makes it possible to analyze the visual information and voice data input by the user, recognize the user's emotions, and generate and present optimal solutions according to that state. Furthermore, feedback from users can be collected and analyzed by a learning means, and the accuracy of the system can be continuously improved. In this way, a system is realized that can provide solutions optimized for individual situations for the various problems faced by users.

[0752] "Image input means" refers to a function that allows the user to input visual information.

[0753] "Voice input means" refers to a function that allows a user to input voice data.

[0754] The "data set generating means" refers to a function that combines data input from the image input means and the voice input means into one data set.

[0755] "Data transmission means" refers to a function for transmitting the data set to the server.

[0756] "Analysis means" refers to a function in the server that analyzes the dataset.

[0757] The "emotion recognition means" refers to a function that recognizes the user's emotions based on the data analyzed by the analysis means.

[0758] The "generation means" refers to a function that generates an optimal solution by taking into account the results of the emotion recognition means.

[0759] The "presentation means" refers to a function that presents the generated solution to the user.

[0760] The "feedback means" refers to a function for reflecting the results of implementing the proposed solution.

[0761] The "learning means" refers to a function that learns the system based on the results received from the feedback means and improves accuracy.

[0762] "Image analysis means" refers to a function for analyzing visual information.

[0763] "Speech recognition means" refers to a function that converts voice data into text data.

[0764] The present invention relates to a system that allows a user to input visual information and voice data using a smart device, recognizes the user's emotions based on this data, and generates and provides appropriate solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. Specific embodiments are described in detail below.

[0765] User Actions

[0766] 1. Launch the dedicated app

[0767] The user launches a dedicated app on a smart device (e.g., a smartphone). The app's generic name is "Problem Solving Assistant."

[0768] 2. Visual information input

[0769] Users use their smart device's camera to take an image of the problem, for example, graffiti in a parking lot.

[0770] 3. Inputting voice data

[0771] Users can use the microphone to verbally describe the problem in detail, such as "How do I remove this graffiti?", and optionally enter additional information in text.

[0772] 4. Collecting emotional information

[0773] The user's facial expressions and tone of voice are also collected through the smart device.

[0774] Device behavior

[0775] 1. Generating the dataset

[0776] The terminal (smart device) combines the collected visual information, audio data, and text information into a single data set.

[0777] 2. Submitting the dataset

[0778] The device sends the generated data set to a server over the internet, where it is encrypted.

[0779] 3. Receiving and Displaying the Solution

[0780] The device receives solutions and emotion recognition results sent from the server, and the received information is presented to the user via text message or voice.

[0781] Server Operation

[0782] 1. Receiving Data

[0783] The server receives the data set sent from the device, stores it in a database, and begins analysis.

[0784] 2. Analysis of image data

[0785] The server uses computer vision algorithms (e.g., OpenCV) to analyze the image data, for example, to detect graffiti written in white chalk on the asphalt of a parking lot.

[0786] 3. Analysis of audio data

[0787] The server converts the voice data into text using a speech recognition API (e.g., a cloud-based speech recognition service), and then uses a natural language processing module (e.g., an open-source NLP library) to identify the user's concerns.

[0788] 4. Emotion recognition

[0789] The server uses an emotion recognition engine (e.g., a tone analyzer) to recognize the user's emotions from voice data and visual information. It determines whether the user is anxious or calm from their voice tone and facial expression.

[0790] 5. Solution Generation

[0791] The server integrates the analyzed visual information, audio data, and emotion recognition results and uses a generative AI model (e.g., an advanced language generation model) to generate an optimal solution. For example, it might suggest a quick method for removing graffiti: pour hot water over it, scrub with a brush, and finish with detergent.

[0792] 6. Submit your solution

[0793] The server sends the generated solution in a user-friendly format to the device, where the solution is presented in text and audio format.

[0794] Feedback and Learning

[0795] 1. Implementing the solution

[0796] The user follows the suggested solutions to solve the problem.

[0797] 2. Submitting Feedback

[0798] The user sends the results of the solution to the server via their device, providing feedback such as whether the graffiti has been completely removed.

[0799] 3. Processing Feedback

[0800] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine, thereby improving the system's problem-solving accuracy and emotion recognition accuracy.

[0801] Specific examples

[0802] If a user wants to remove graffiti written on the asphalt of a parking lot, they first take a picture of the graffiti with their smart device and then provide a voice instruction saying, "Please tell me how to remove this graffiti." The device then sends this visual and voice information to the server. The server analyzes this data, uses image analysis means to determine that it is "graffiti made with white chalk," and uses voice recognition means to convert the user's request into text. The server then uses an emotion recognition engine to recognize that the user is impatient and generates a solution appropriate to that situation. For example, it provides specific instructions such as, "To quickly remove graffiti, use hot water and a brush."

[0803] As such, the present invention is a system that quickly provides solutions optimized for individual situations to various problems faced by users, thereby improving user satisfaction and problem-solving efficiency.

[0804] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0805] Processing step flow

[0806] Step 1:

[0807] Launching the dedicated app

[0808] The user launches a dedicated app on their smart device. The input is the operation to launch the app, and the output is the display of the app's home screen. The app launches when the user taps the app's icon.

[0809] Step 2:

[0810] Visual information input

[0811] The user activates the camera on their smart device and takes a picture of the target object. The input is the image data captured by the camera, and the output is saved as an image file on the device. The user opens the camera app and taps the shutter button to capture the image.

[0812] Step 3:

[0813] Inputting audio data

[0814] The user uses the microphone on their smart device to describe the details of the problem. The input is audio data collected by the microphone, and the output is saved as an audio file on the device. The user presses the microphone button in the app and speaks, "Please tell me how to erase this graffiti."

[0815] Step 4:

[0816] Collecting emotional information

[0817] The user's facial expressions and voice tone are collected by the device's camera and microphone. The input is facial expression data and voice tone data captured by the camera, and the output is the data necessary for analysis to identify emotions. Emotional information such as the user's impatience or calmness is collected.

[0818] Step 5:

[0819] Generating the dataset

[0820] The device combines visual information, audio data, and text information into a single dataset. The input is captured images, recorded audio, and collected emotion data, and the output is a unified dataset. The device combines these different data formats into a single file.

[0821] Step 6:

[0822] Submitting a Dataset

[0823] The terminal sends the generated dataset to the server. The input is the dataset, and the output is the transmission result to the server (such as a transmission completion message). The dataset is encrypted and sent to the server over the network.

[0824] Step 7:

[0825] Receiving data

[0826] The server receives the dataset sent from the device. The input is the received dataset, and the output is the data stored in the server's database. The server stores the received data in the database in preparation for analysis.

[0827] Step 8:

[0828] Image data analysis

[0829] The server analyzes the image data using a computer vision algorithm (e.g., OpenCV) and extracts features. The input is the image data, and the output is the analyzed feature information. For example, it can detect graffiti written in chalk and identify its location and color.

[0830] Step 9:

[0831] Analysis of audio data

[0832] The server converts the voice data into text data using a voice recognition API (e.g., a cloud-based voice recognition service). The input is voice data, and the output is text data. The user's speech, "Please tell me how to erase this graffiti," is converted into text.

[0833] Step 10:

[0834] emotion recognition

[0835] The server uses an emotion engine (e.g., tone analyzer) to recognize the user's emotion from voice tone and visual information. The input is voice data and facial expression data, and the output is the user's emotional state. It identifies whether the user is anxious or calm.

[0836] Step 11:

[0837] Integrating analysis results and generating solutions

[0838] The server integrates the analyzed visual information, audio data, and emotion recognition results, and generates an appropriate solution using a generative AI model (e.g., an advanced language generation model). The input is the integrated data, and the output is the generated solution. For example, a specific procedure such as "pour boiling water over the area, scrub with a brush, and finish with detergent" may be suggested.

[0839] Step 12:

[0840] Submit a solution

[0841] The server sends the generated solution to the terminal. The input is the solution data, and the output is a transmission completion message. The solution data is converted into a format that is easy for the user to understand before being sent.

[0842] Step 13:

[0843] Providing a solution

[0844] The terminal presents the received solutions to the user. The input is the solution data received from the server, and the output is the solution information displayed to the user. The terminal presents the proposed solutions to the user in text or voice.

[0845] Step 14:

[0846] Implementing the solution

[0847] The user executes the proposed solution. The input is the proposed solution, and the output is the execution result. The user follows specific steps to solve the problem.

[0848] Step 15:

[0849] Send Feedback

[0850] After implementing the solution, the user feeds the results back to the server via their device. The input is the implementation result, and the output is the feedback data. For example, the user may report that the graffiti has completely disappeared.

[0851] Step 16:

[0852] Processing Feedback

[0853] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine. The input is the feedback data, and the output is an updated training model. This continuously improves the accuracy and effectiveness of the system.

[0854] The above is the processing flow and specific operation of the program of this system.

[0855] (Application example 2)

[0856] 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."

[0857] Currently, many security systems face challenges in providing appropriate information and responding quickly when users feel anxious. Specifically, they are unable to fully alleviate users' anxiety because they mechanically present solutions without considering the user's emotions. Furthermore, while users who feel anxious or nervous need a quick and effective solution, current systems do not adequately support this.

[0858] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to input visual information, voice input means for the user to input voice data, analysis means for analyzing the data input from the input means and the voice input means, generation means for generating an optimal solution based on the analyzed data, presentation means for presenting the generated solution to the user, feedback means for feeding back the results of implementing the presented solution, learning means for learning the results received from the feedback means, emotion recognition means for recognizing the user's emotion, and adjustment means for adjusting the solution based on the output of the emotion recognition means. This makes it possible to provide quick and accurate security measures according to the user's emotional state.

[0859] "Visual information" refers to images and videos that users input through devices such as cameras.

[0860] "Voice data" refers to voice information input by a user using a microphone.

[0861] "Input means" refers to devices and functions for acquiring visual information and audio data.

[0862] "Analysis means" refers to a function that processes input visual information and audio data and analyzes the content thereof.

[0863] "Generation means" refers to a function that generates an optimal solution based on the data processed by the analysis means.

[0864] "Presentation means" refers to a function for displaying the generated solution to the user.

[0865] "Feedback means" refers to the function of collecting the results of users implementing the proposed solutions.

[0866] "Learning means" refers to a function that performs learning to improve the accuracy of the system based on the results received from the feedback means.

[0867] "Emotion recognition means" refers to the function of recognizing emotions from the user's tone of voice, facial expressions, etc.

[0868] The "adjustment means" refers to a function that adjusts the generated solution according to the user's emotional state based on the output of the emotion recognition means.

[0869] To implement this invention, it is necessary to build a system that allows a user to input visual information and voice data using a smartphone, recognize emotions based on that data, and generate and present optimal solutions. To realize this system, the following hardware and software are used in combination.

[0870] Hardware

[0871] Smartphone: A device equipped with a camera and microphone that allows the user to input visual and audio data.

[0872] Server: The computational resources for analyzing data and generating and coordinating solutions.

[0873] software

[0874] Smartphone application (iOS / Android): Has the function of collecting visual information and audio data and sending it to a server.

[0875] Image analysis modules (e.g., OpenCV, TensorFlow): Analyze visual information and identify security vulnerabilities.

[0876] Speech recognition APIs (e.g., Google Speech-to-Text, Amazon Transcribe): Converts voice data into text data.

[0877] Emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition): Recognizes emotions from the user's tone of voice, facial expressions, etc.

[0878] Generative AI model: Generates optimal solutions based on analyzed data.

[0879] Feedback collection module: Collects the results of user actions and uses them as learning data for the system.

[0880] System Operation Overview

[0881] 1. Input method: The user takes visual information (e.g., images of the area around their home) using the smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using the microphone.

[0882] 2. Data transmission: The smartphone application transmits these data to the server as a dataset.

[0883] 3. Data analysis: The server analyzes visual information using an image analysis module, converts voice data into text using a voice recognition API, and analyzes the user's emotions using an emotion recognition engine.

[0884] 4. Solution generation and adjustment: The generative AI model generates optimal solutions based on the analysis data and adjusts the solutions based on emotion recognition results. For example, if the user is in a hurry, it will provide a quick and easy solution.

[0885] 5. Presenting a solution: The generated solution is sent to the user's smartphone and presented to them via text or voice.

[0886] 6. Feedback collection and learning: The user implements the proposed solution and provides feedback on the results to the server via their smartphone. The server uses this feedback to update the learning data and improve the accuracy of the system.

[0887] Specific examples

[0888] When a user feels unsure about the security situation at home at night, they can take a video of their garden with their smartphone camera and ask, "Where are you worried about tonight?" The smartphone application sends this data to a server, and the generative AI model uses the analysis and emotion recognition results to quickly and accurately generate solutions. For example, it provides specific instructions to the user via text and voice, such as, "Adding lighting to the north side of the garden and adjusting the position of the security camera would be effective."

[0889] Prompt Sentence Examples

[0890] text

[0891] Please check the security situation in the area and let us know what measures are in place to prevent crime. Users are very anxious.

[0892] Such a system will enable users to quickly resolve security concerns, and will hopefully continue to improve its accuracy and effectiveness through feedback gathering and learning.

[0893] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0894] Step 1:

[0895] A user takes visual information (e.g., images of the area around their home) using a smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using a microphone. At this time, the user also includes facial expressions and tone of voice that express their emotional state.

[0896] Step 2:

[0897] The device collects the captured image data and recorded audio data and compiles them into a single dataset, which contains both visual information and audio data.

[0898] Step 3:

[0899] The device sends the dataset to the server, which stores the received dataset for analysis.

[0900] Step 4:

[0901] The server analyzes visual information using image analysis modules (e.g., OpenCV, TensorFlow), for example, to identify security vulnerabilities in image data around the home. The results of this analysis are generated as output.

[0902] Step 5:

[0903] The server converts the voice data into text data using a speech recognition API (e.g., Google Speech-to-Text, Amazon Transcribe). For example, the voice saying "Where are you worried about tonight?" is output as text data.

[0904] Step 6:

[0905] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition) to recognize the user's emotions. It identifies whether the user is anxious or calm from their tone of voice and facial expressions. The recognition results are generated as output.

[0906] Step 7:

[0907] The server uses a generative AI model to generate optimal solutions based on the analytical data and emotion recognition results, such as "Adding lighting to the north side of the garden and adjusting the position of security cameras would be effective."

[0908] Step 8:

[0909] The server sends the generated solution in text or audio format to the device, which then presents the solution to the user. Specifically, the solution is displayed as text on the smartphone screen or notified to the user by audio.

[0910] Step 9:

[0911] The user implements the proposed solution and sends the results back to the server via their smartphone, for example, "Adding lighting to the north side of the garden has improved crime prevention."

[0912] Step 10:

[0913] The server collects feedback data and stores it as training data, which updates the generative AI model and emotion recognition engine, improving the accuracy of the system.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] [Third embodiment]

[0918] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0919] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0920] 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).

[0921] 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.

[0922] 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.

[0923] 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).

[0924] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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."

[0930] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[0931] System Overview

[0932] User Actions

[0933] Users first launch a dedicated application on their smartphone (device), then use the camera to capture visual information (e.g., an image of the problem) and the audio microphone to describe the problem in detail. If necessary, users can also enter additional information in text.

[0934] Device behavior

[0935] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[0936] Server Operation

[0937] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[0938] 1. Analysis of imaging data:

[0939] The server uses image analysis tools (e.g., computer vision algorithms) to analyze the image data and extract features, such as determining whether graffiti in a parking lot is written in white chalk.

[0940] 2. Analysis of audio data:

[0941] The server converts the voice data into text data using a speech recognition method (e.g., a speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[0942] 3. Integration of analysis results:

[0943] The server integrates the results of the analysis of the visual information and the audio data, and generates an optimal solution using a generation means.

[0944] 4. Propose a solution:

[0945] The generated solution is converted into a user-friendly format (e.g., text, audio, image) and sent to the device.

[0946] Feedback and Learning

[0947] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0948] Specific examples

[0949] Visual information input and analysis

[0950] When a user wants to remove graffiti written on the asphalt of a parking lot, they take a picture of the graffiti with their smartphone. A voice prompt then asks, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[0951] The device sends this data to a server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti."

[0952] Solution generation and presentation

[0953] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti," suggesting specific steps such as "pour boiling water on it, scrub with a brush, and finish with detergent."

[0954] The device will provide the user with text and audio instructions.

[0955] Feedback and Learning

[0956] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[0957] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will greatly improve the efficiency and accuracy of problem solving.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). Next, they use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[0961] Step 2:

[0962] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[0963] Step 3:

[0964] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the image is graffiti written in white chalk on asphalt).

[0965] Step 4:

[0966] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[0967] Step 5:

[0968] The server combines the analyzed visual and audio data and inputs the dataset into a generator, which generates an optimal solution (e.g., "How to pour hot water, scrub with a brush, and finish with detergent").

[0969] Step 6:

[0970] The server converts the generated solution into a format that is easy for the user to understand (text, image, audio, etc.), creates a data packet containing the solution, and sends it to the device as an HTTP response.

[0971] Step 7:

[0972] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in a format that is easy to understand (e.g., displaying and playing the solution in text and audio).

[0973] Step 8:

[0974] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[0975] Step 9:

[0976] The server analyzes the received feedback data, adds the analysis results to the training dataset of the generative AI model, and updates the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[0977] Example 1

[0978] 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."

[0979] To quickly and effectively solve the various visual and auditory problems users encounter in their daily lives and at work, a system that can integrate and appropriately analyze multiple input data (visual information, audio data, text data) is required. However, current technology lacks the means to integrate and analyze such multiple data and present optimal solutions. As a result, users often spend a great deal of time and effort solving problems.

[0980] 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.

[0981] In this invention, the server includes an analysis means for analyzing visual information using an image analysis means, an analysis means for converting audio data into text data using a voice recognition means, a generation means for generating an optimal solution based on the analyzed visual information and audio data, a presentation means for converting the generated solution into a format that is easy for the user to understand and presenting it, a feedback means for providing feedback on the results of implementing the presented solution, and a learning means for learning from the results received from the feedback means and updating the generative AI model. This enables the analysis of visual and auditory problems and the provision of optimal solutions to be performed quickly and effectively. The user can instantly obtain a solution to the problem, and the system also learns based on the feedback, improving the accuracy of future problem-solving.

[0982] A "user" is an individual or organization that uses the system to input visual information and voice data to solve a problem.

[0983] "Input means" refers to a device or interface that allows a user to input visual information into a system.

[0984] "Audio input means" refers to a microphone or voice recording device that allows a user to input voice data into the system.

[0985] A "terminal" is an electronic device that compiles visual information and audio data entered by a user into a single data set and sends it to a server as an HTTP request.

[0986] A "server" is a computer system that receives data sets sent from terminals and processes analysis, solutions, presentation, and feedback.

[0987] "Image analysis means" refers to computer vision algorithms and software for analyzing visual information and extracting its features.

[0988] "Speech recognition means" refers to software or APIs for converting voice data into text data.

[0989] "Analysis means" is a general term for various tools and techniques for analyzing input visual information and audio data.

[0990] "Generative means" refers to AI models or algorithms that generate optimal solutions based on analyzed data.

[0991] The "presentation means" is a display or audio output device for presenting the generated solution to the user.

[0992] A "feedback means" is an interface that allows a user to report to the system the results of implementing a proposed solution.

[0993] "Learning methods" are algorithms and data processing techniques that update generative AI models based on data obtained from feedback and improve their accuracy.

[0994] A "generative AI model" is an artificial intelligence model that generates optimal solutions to users' concerns and problems.

[0995] A "prompt" is a specific text instruction for inputting instructions into a generative AI model.

[0996] This invention relates to a system in which a user inputs visual information and voice data using a smartphone, and a server analyzes the data to generate and present optimal solutions. This system operates by the user, device, and server each playing a specific role and cooperating with each other.

[0997] System configuration

[0998] User Actions

[0999] The user launches the dedicated application installed on their smartphone, then performs the following operations:

[1000] 1. Visual input: Use your smartphone camera to take a picture of the problem object, for example, graffiti on the asphalt of a parking lot.

[1001] 2. Voice input: Use your smartphone's microphone to verbally describe the problem in detail, for example, "Please tell me how to remove this graffiti."

[1002] 3. Enter text information: If necessary, enter detailed information such as the number of days since the event and the location in text.

[1003] Device behavior

[1004] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[1005] Server Operation

[1006] The server receives the data set sent from the device and performs the following processes:

[1007] 1. Image data analysis: The server uses image analysis tools (e.g., computer vision algorithms) to analyze visual information. Specifically, libraries such as OpenCV can be used. For example, to identify graffiti written in white chalk on the asphalt of a parking lot.

[1008] 2. Analysis of voice data: The server converts the voice data into text data using a voice recognition method (e.g., a voice recognition API). For example, the Google Speech-to-Text API can be used. The converted text data, along with the text information entered by the user, is analyzed by a natural language processing module (e.g., spaCy) to identify the user's concerns.

[1009] 3. Integrating the analysis results: Integrating the analyzed visual information and audio data and generating an optimal solution using a generative AI model (e.g., GPT-4).

[1010] 4. Presenting the solution: The generated solution is converted into a format that is easy for the user to understand (e.g., text, audio, image) and sent to the device.

[1011] Feedback and Learning

[1012] The user implements the proposed solution and provides feedback on the results to the server via their device. The server then analyzes this feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1013] Specific examples

[1014] Visual information input and analysis

[1015] If a user wants to remove graffiti written on the asphalt of a parking lot, they take a photo of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[1016] Solution generation and presentation

[1017] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti." For example, it might suggest specific steps such as "pour hot water, scrub with a brush, and finish with detergent." The device then presents these steps to the user in text and voice.

[1018] Feedback and Learning

[1019] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[1020] Prompt Sentence Examples

[1021] Below is an example of a prompt sentence to input to the generative AI model.

[1022] "How do I remove graffiti written in white chalk on asphalt?"

[1023] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will significantly improve the efficiency and accuracy of problem solving.

[1024] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1025] Step 1: User enters visual information

[1026] What it does: The user uses their smartphone camera to take an image of the problem they want to solve.

[1027] Input: Visual information (image) of the problem

[1028] Output: Captured image data

[1029] Step 2: User enters voice data

[1030] What it does: The user uses their smartphone's microphone to verbally describe the details of the problem they want to solve.

[1031] Input: User's voice data

[1032] Output: Recorded audio data

[1033] Step 3: User enters text information

[1034] Specific Action: The user enters additional information related to the issue (e.g., number of days since issue occurred or detailed situation) via text into their smartphone, if necessary.

[1035] Input: User's text information

[1036] Output: The input text data

[1037] Step 4: Data integration by terminal

[1038] Specific operation: The device combines visual information, audio data, and text information input by the user into a single data set.

[1039] Input: image data, audio data, text data

[1040] Output: A consolidated dataset

[1041] Step 5: Send data by device

[1042] Specific operation: The terminal sends the integrated data set to the server as an HTTP request.

[1043] Input: Integrated dataset

[1044] Output: HTTP request sent to the server

[1045] Step 6: Image data analysis by the server

[1046] Specific operation: The server extracts image data from the received dataset and extracts features using image analysis means (e.g., OpenCV).

[1047] Input: Image data

[1048] Data processing or calculation: feature extraction by image analysis means

[1049] Output: Image analysis results (e.g., "Graffiti written in white chalk on asphalt")

[1050] Step 7: Server analyzes the audio data

[1051] Specific operation: The server converts the received voice data into text data using a speech recognition tool (e.g., Google Speech-to-Text API), and then uses a natural language processing module (e.g., spaCy) to identify the user's concerns.

[1052] Input: Audio data

[1053] Data processing or computation: Speech-to-text conversion and natural language processing

[1054] Output: Text data of the speech analysis results (e.g., "Please tell me how to erase this graffiti.")

[1055] Step 8: Server integration of analysis results

[1056] Specific operation: The server integrates the image analysis results and audio analysis results and generates the optimal solution using a generative AI model (e.g., GPT-4).

[1057] Input: Image analysis results, audio analysis results

[1058] Data manipulation or computation: Generating solutions using generative AI models

[1059] Output: The generated solution (e.g., "Pour hot water on it, scrub with a brush, and finish with detergent")

[1060] Step 9: Server converts and sends the solution

[1061] Specific operation: The server converts the generated solution into a format that is easy for the user to understand (e.g., text, audio, image) and sends it to the terminal.

[1062] Input: Generated solution

[1063] Data processing or calculation: transformation of the solution

[1064] Output: Solution data to present to the user

[1065] Step 10: Providing a solution via terminal

[1066] Specific operation: The device presents the received solution to the user via text or voice.

[1067] Input: Data for the proposed solution

[1068] Output: Present the solution to the user

[1069] Step 11: User feedback

[1070] Specific operation: After the user implements the solution, the results are fed back through the terminal.

[1071] Input: Execution result feedback (text or audio data)

[1072] Output: Feedback data

[1073] Step 12: Server analyzes feedback and learns

[1074] Specific operation: The server analyzes the feedback data and uses it as training data for the generative AI model.

[1075] Input: Feedback data

[1076] Data processing or computation: analyzing feedback data and updating generative AI models

[1077] Output: An updated generative AI model

[1078] (Application example 1)

[1079] 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."

[1080] On traditional online shopping sites, users often have problems selecting products because they cannot instantly grasp the product's features or because the means to resolve questions about the product's details are not immediately provided. Furthermore, because information from multiple data input methods is not integrated and analyzed, it is difficult to present optimal solutions to the problems users face.

[1081] 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.

[1082] In this invention, the server includes an input means for a user to input visual information, a voice input means for a user to input voice data, an analysis means for analyzing the data input from the input means and the voice input means, a generation means for generating an optimal solution based on the analyzed data, a presentation means for presenting the generated solution to the user, a feedback means for feeding back the results of implementing the presented solution, a learning means for learning the results received from the feedback means, an image analysis means for extracting product features using images, a voice recognition means for converting voice data into text data, a means for analyzing the text data using natural language processing means and understanding the user's question, and a means for presenting the user with a generated solution related to the product using a generative AI model. This makes it possible to quickly and effectively solve problems users have when selecting products.

[1083] A "user" is a person who uses this system to select products or resolve questions.

[1084] A "smartphone" is a portable information terminal that allows a user to input visual and audio data.

[1085] "Visual information" refers to product images and related images that are input by the user using a camera.

[1086] "Voice data" refers to voice information uttered by a user using a microphone, including questions and instructions.

[1087] "Input means" refers to tools or devices that allow a user to input visual information or audio data.

[1088] "Analysis means" refers to algorithms or programs for analyzing and understanding input visual information and audio data.

[1089] "Generation means" refers to the methods and mechanisms for generating optimal solutions based on the analyzed data.

[1090] "Presentation means" refers to a method or device for presenting the generated solution to the user in an easy-to-understand form.

[1091] "Feedback means" refers to the techniques and tools that allow users to return the results of their actions to the system.

[1092] "Learning tools" refers to machine learning models that analyze data from feedback and aim to improve the accuracy of future solutions.

[1093] "Image analysis means" refers to algorithms or software for analyzing visual information and recognizing products and their features.

[1094] "Speech recognition means" refers to techniques and tools for converting voice data into text.

[1095] "Natural language processing means" refers to algorithms and technologies used to analyze text data and understand users' questions and intent.

[1096] A "generative AI model" refers to an artificial intelligence model that generates optimal solutions based on analysis results.

[1097] "Prompt sentence" refers to predefined text that is input into a generative AI model.

[1098] The present invention relates to a system that allows a user to input visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[1099] System Overview

[1100] User Actions

[1101] Users first launch the dedicated application on their smartphone (device), then use the camera to take a picture of the product packaging, and then use the audio microphone to ask questions or provide details. If necessary, they can also enter additional information via text.

[1102] Device behavior

[1103] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[1104] Server Operation

[1105] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[1106] 1. Analysis of imaging data:

[1107] The server analyzes the image data using image analysis tools (e.g., TensorFlow or OpenCV) to extract product features. For example, it identifies specific features such as "Brand A shampoo."

[1108] 2. Analysis of audio data:

[1109] The server converts the voice data into text using a speech recognition tool (e.g., Google Cloud Speech-to-Text API), then analyzes the converted text using a natural language processing tool (e.g., GPT-4) to understand the user's question.

[1110] 3. Integration of analysis results:

[1111] The server integrates the results of the analysis of visual information and audio data and generates an optimal solution using a generation means (e.g., a generative AI model).

[1112] 4. Propose a solution:

[1113] The generated solution is converted into a user-friendly format (e.g., text, voice) and sent to the device.

[1114] Feedback and Learning

[1115] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1116] Specific examples

[1117] A user wants to know information about "Brand A Shampoo," so they take a picture of the product package with their smartphone. They also ask aloud, "Please tell me the reviews and stock information for this product." An example of a prompt sentence is as follows:

[1118] Example prompt sentence:

[1119] A user uploaded an image of a product package and asked, "Please tell me the reviews and stock information for this product." Image analysis determined that the product was "Brand A Shampoo." Based on this, please generate the best answer for the user.

[1120] The server performs the above process, generates the optimal solution to the user's question, and sends it back to the terminal. The terminal then presents this solution to the user in text and voice. This process allows the user to quickly and accurately obtain product information.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] The user launches a dedicated application on their smartphone (device), takes a picture of the product packaging with the camera, and then uses the audio microphone to input a question such as, "Please tell me the reviews and stock information for this product." The input data consists of visual information (product image) and audio data (user question).

[1124] Step 2:

[1125] The device acquires visual information (product images) and audio data input by the user, compiles it into a single dataset, and sends it to the server as an HTTP request. The input is a set of product images and audio data, and the output is a dataset in HTTP request format.

[1126] Step 3:

[1127] The server analyzes the dataset received from the device. First, it analyzes the product image using image analysis tools (such as TensorFlow or OpenCV) to extract product features (e.g., "Brand A shampoo"). The input is the product image, and the output is the extracted product features. This step also involves preprocessing the product image (resizing and noise removal).

[1128] Step 4:

[1129] The server converts the voice data into text data using a speech recognition tool (such as the Google Cloud Speech-to-Text API). The input is the voice data, and the output is the text data converted from the voice (e.g., "Please tell me the reviews and stock information for this product."). The converted text data is further analyzed using natural language processing tools to clarify the user's question and intent.

[1130] Step 5:

[1131] The server integrates the results of analysis of visual information (extracted product features) and audio data (text data converted from audio) and generates the optimal solution using a generation method (generative AI model). Specifically, it extracts product-related reviews and inventory information, and generates the information the user is looking for. The input is the integrated analysis results, and the output is the optimal solution (answer in text format).

[1132] Step 6:

[1133] The server converts the generated solution into a user-understandable format (e.g., text or voice) and sends it to the device. The input is the textual solution, and the output is the formatted data for presentation to the user.

[1134] Step 7:

[1135] The device receives the solution sent from the server and presents it to the user. Specifically, it displays the solution as text on the smartphone screen and, in some cases, uses speech synthesis to read it aloud to the user. The input is the formatted solution sent from the server, and the output is the content presented to the user.

[1136] Step 8:

[1137] The user implements the proposed solution and feeds the results back to the server via the terminal. The input is the result of the user's implementation, and the output is the feedback data.

[1138] Step 9:

[1139] The server analyzes the feedback data and uses it as training data for the generative AI model. Here, the formatted data is added to the database to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model.

[1140] 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.

[1141] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, recognizes the user's emotions based on this data, and generates and provides optimal solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. An emotion engine is also integrated to recognize the user's emotions.

[1142] System Overview

[1143] User Actions

[1144] The user first launches a dedicated application using their smartphone (device). Next, they use the camera to capture visual information (e.g., an image of the problem) and use the audio microphone to describe the problem in detail. The user's facial expressions and tone obtained from audio and visual information are also collected to identify the user's emotions. If necessary, additional information can be entered as text.

[1145] Device behavior

[1146] The device compiles the visual, audio, and textual information input by the user into a single dataset, then sends the dataset to the server, which is also responsible for presenting the server's solutions and the user's emotion recognition results.

[1147] Server Operation

[1148] The server receives the data set sent from the terminal and processes it as follows.

[1149] 1. Analysis of imaging data:

[1150] The server uses an image analysis module (e.g., computer vision algorithms) to analyze the image data and extract its features, for example, to determine whether graffiti in a parking lot is written in white chalk.

[1151] 2. Analysis of audio data:

[1152] The server converts the voice data into text data using a speech recognition module (e.g., speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[1153] 3. Emotion Recognition:

[1154] The server uses an emotion engine to identify the user's emotions from the audio data and visual information, for example, determining whether the user is anxious or calm from the tone of their voice and facial expressions.

[1155] 4. Integrating the analysis results and generating solutions:

[1156] The server combines the analyzed visual information, audio data, and emotion recognition results to generate an optimal solution. The generated solution is adjusted according to the user's emotions. For example, if the user is impatient, a simpler and faster solution will be presented.

[1157] 5. Propose a solution:

[1158] The generated solution is converted into a user-friendly format (text, audio, image) and sent to the device.

[1159] Feedback and Learning

[1160] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes this feedback data and uses it as training data for the generative AI model and emotion engine. This will improve the accuracy of solutions to similar problems and emotion recognition in the future.

[1161] Specific examples

[1162] Input and analysis of visual information and emotion recognition

[1163] If a user wants to remove graffiti from the asphalt of a parking lot, they can take a picture of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." Furthermore, if the user is anxious, the system will recognize their emotion from their facial expression and tone of voice.

[1164] The device sends this data to the server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti." The emotion engine then recognizes that the user is anxious.

[1165] Solution generation and presentation

[1166] Based on the integrated analysis and emotion recognition results, the server uses a generative AI model to generate solutions, such as suggesting specific steps to quickly remove graffiti: pour boiling water over it, scrub with a brush, and finish with detergent.

[1167] The device will explain these steps to the user in text and audio, and will simplify the steps to accommodate the user's impatience.

[1168] Feedback and Learning

[1169] After implementing the solution, the user provides feedback on the results to the server via their device (e.g., "The graffiti has completely disappeared"). The server receives this feedback and updates the generative AI model and emotion engine to improve the accuracy of problem-solving in future.

[1170] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems they encounter in their daily lives, incorporating emotion recognition, which will significantly improve the efficiency and accuracy of problem-solving.

[1171] The processing flow will be explained below.

[1172] Step 1:

[1173] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). They also use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[1174] Step 2:

[1175] The device compiles the visual, audio, and text information input by the user into a single dataset. It then uses an emotion engine to recognize the user's emotions from the audio and visual information. The dataset, which also includes the emotion recognition results, is then sent to the server.

[1176] Step 3:

[1177] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the data is graffiti written in white chalk on asphalt).

[1178] Step 4:

[1179] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[1180] Step 5:

[1181] The server analyzes the results of the emotion engine to identify the user's emotional state (e.g., anxious, calm). The server then combines the analyzed visual information, audio data, and emotion recognition results and inputs the resulting dataset into the generator.

[1182] Step 6:

[1183] The generator generates an optimal solution based on the integrated data (e.g., "Pour hot water, scrub with a brush, and finish with detergent"), which is customized according to the user's emotional state (e.g., if the user is impatient, simplify the steps).

[1184] Step 7:

[1185] The server converts the generated solution into a user-friendly format (text, image, audio), creates a data packet containing the converted solution, and sends it to the device as an HTTP response.

[1186] Step 8:

[1187] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in an easy-to-understand format (e.g., displaying and playing the solution in text and audio). At this time, it also displays the emotion recognition results so that the user can understand their own emotional state.

[1188] Step 9:

[1189] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[1190] Step 10:

[1191] The server analyzes the received feedback data and adds the analysis results to the training datasets of the generative AI model and emotion engine, updating them to improve the accuracy of solutions to similar problems in the future and the accuracy of emotion recognition.

[1192] Example 2

[1193] 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."

[1194] In modern life, it is important to provide quick and effective solutions to the various problems users face. However, with conventional methods, it has been difficult to provide solutions that take into account the user's emotional state. For example, it is difficult to present different solutions depending on whether the user is anxious or calm. In addition, there are limited means to continuously train the system through feedback and improve its accuracy. To solve these challenges, a system that recognizes the user's emotions and provides optimal solutions based on those emotions is needed.

[1195] 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.

[1196] In this invention, the server includes an analysis means, an emotion recognition means, and a generation means. This makes it possible to analyze the visual information and voice data input by the user, recognize the user's emotions, and generate and present optimal solutions according to that state. Furthermore, feedback from users can be collected and analyzed by a learning means, and the accuracy of the system can be continuously improved. In this way, a system is realized that can provide solutions optimized for individual situations for the various problems faced by users.

[1197] "Image input means" refers to a function that allows the user to input visual information.

[1198] "Voice input means" refers to a function that allows a user to input voice data.

[1199] The "data set generating means" refers to a function that combines data input from the image input means and the voice input means into one data set.

[1200] "Data transmission means" refers to a function for transmitting the data set to the server.

[1201] "Analysis means" refers to a function in the server that analyzes the dataset.

[1202] The "emotion recognition means" refers to a function that recognizes the user's emotions based on the data analyzed by the analysis means.

[1203] The "generation means" refers to a function that generates an optimal solution by taking into account the results of the emotion recognition means.

[1204] The "presentation means" refers to a function that presents the generated solution to the user.

[1205] The "feedback means" refers to a function for reflecting the results of implementing the proposed solution.

[1206] The "learning means" refers to a function that learns the system based on the results received from the feedback means and improves accuracy.

[1207] "Image analysis means" refers to a function for analyzing visual information.

[1208] "Speech recognition means" refers to a function that converts voice data into text data.

[1209] The present invention relates to a system that allows a user to input visual information and voice data using a smart device, recognizes the user's emotions based on this data, and generates and provides appropriate solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. Specific embodiments are described in detail below.

[1210] User Actions

[1211] 1. Launch the dedicated app

[1212] The user launches a dedicated app on a smart device (e.g., a smartphone). The app's generic name is "Problem Solving Assistant."

[1213] 2. Visual information input

[1214] Users use their smart device's camera to take an image of the problem, for example, graffiti in a parking lot.

[1215] 3. Inputting voice data

[1216] Users can use the microphone to verbally describe the problem in detail, such as "How do I remove this graffiti?", and optionally enter additional information in text.

[1217] 4. Collecting emotional information

[1218] The user's facial expressions and tone of voice are also collected through the smart device.

[1219] Device behavior

[1220] 1. Generating the dataset

[1221] The terminal (smart device) combines the collected visual information, audio data, and text information into a single data set.

[1222] 2. Submitting the dataset

[1223] The device sends the generated data set to a server over the internet, where it is encrypted.

[1224] 3. Receiving and Displaying the Solution

[1225] The device receives solutions and emotion recognition results sent from the server, and the received information is presented to the user via text message or voice.

[1226] Server Operation

[1227] 1. Receiving Data

[1228] The server receives the data set sent from the device, stores it in a database, and begins analysis.

[1229] 2. Analysis of image data

[1230] The server uses computer vision algorithms (e.g., OpenCV) to analyze the image data, for example, to detect graffiti written in white chalk on the asphalt of a parking lot.

[1231] 3. Analysis of audio data

[1232] The server converts the voice data into text using a speech recognition API (e.g., a cloud-based speech recognition service), and then uses a natural language processing module (e.g., an open-source NLP library) to identify the user's concerns.

[1233] 4. Emotion recognition

[1234] The server uses an emotion recognition engine (e.g., a tone analyzer) to recognize the user's emotions from voice data and visual information. It determines whether the user is anxious or calm from their voice tone and facial expression.

[1235] 5. Solution Generation

[1236] The server integrates the analyzed visual information, audio data, and emotion recognition results and uses a generative AI model (e.g., an advanced language generation model) to generate an optimal solution. For example, it might suggest a quick method for removing graffiti: pour hot water over it, scrub with a brush, and finish with detergent.

[1237] 6. Submit your solution

[1238] The server sends the generated solution in a user-friendly format to the device, where the solution is presented in text and audio format.

[1239] Feedback and Learning

[1240] 1. Implementing the solution

[1241] The user follows the suggested solutions to solve the problem.

[1242] 2. Submitting Feedback

[1243] The user sends the results of the solution to the server via their device, providing feedback such as whether the graffiti has been completely removed.

[1244] 3. Processing Feedback

[1245] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine, thereby improving the system's problem-solving accuracy and emotion recognition accuracy.

[1246] Specific examples

[1247] If a user wants to remove graffiti written on the asphalt of a parking lot, they first take a picture of the graffiti with their smart device and then provide a voice instruction saying, "Please tell me how to remove this graffiti." The device then sends this visual and voice information to the server. The server analyzes this data, uses image analysis means to determine that it is "graffiti made with white chalk," and uses voice recognition means to convert the user's request into text. The server then uses an emotion recognition engine to recognize that the user is impatient and generates a solution appropriate to that situation. For example, it provides specific instructions such as, "To quickly remove graffiti, use hot water and a brush."

[1248] As such, the present invention is a system that quickly provides solutions optimized for individual situations to various problems faced by users, thereby improving user satisfaction and problem-solving efficiency.

[1249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1250] Processing step flow

[1251] Step 1:

[1252] Launching the dedicated app

[1253] The user launches a dedicated app on their smart device. The input is the operation to launch the app, and the output is the display of the app's home screen. The app launches when the user taps the app's icon.

[1254] Step 2:

[1255] Visual information input

[1256] The user activates the camera on their smart device and takes a picture of the target object. The input is the image data captured by the camera, and the output is saved as an image file on the device. The user opens the camera app and taps the shutter button to capture the image.

[1257] Step 3:

[1258] Inputting audio data

[1259] The user uses the microphone on their smart device to describe the details of the problem. The input is audio data collected by the microphone, and the output is saved as an audio file on the device. The user presses the microphone button in the app and speaks, "Please tell me how to erase this graffiti."

[1260] Step 4:

[1261] Collecting emotional information

[1262] The user's facial expressions and voice tone are collected by the device's camera and microphone. The input is facial expression data and voice tone data captured by the camera, and the output is the data necessary for analysis to identify emotions. Emotional information such as the user's impatience or calmness is collected.

[1263] Step 5:

[1264] Generating the dataset

[1265] The device combines visual information, audio data, and text information into a single dataset. The input is captured images, recorded audio, and collected emotion data, and the output is a unified dataset. The device combines these different data formats into a single file.

[1266] Step 6:

[1267] Submitting a Dataset

[1268] The terminal sends the generated dataset to the server. The input is the dataset, and the output is the transmission result to the server (such as a transmission completion message). The dataset is encrypted and sent to the server over the network.

[1269] Step 7:

[1270] Receiving data

[1271] The server receives the dataset sent from the device. The input is the received dataset, and the output is the data stored in the server's database. The server stores the received data in the database in preparation for analysis.

[1272] Step 8:

[1273] Image data analysis

[1274] The server analyzes the image data using a computer vision algorithm (e.g., OpenCV) and extracts features. The input is the image data, and the output is the analyzed feature information. For example, it can detect graffiti written in chalk and identify its location and color.

[1275] Step 9:

[1276] Analysis of audio data

[1277] The server converts the voice data into text data using a voice recognition API (e.g., a cloud-based voice recognition service). The input is voice data, and the output is text data. The user's speech, "Please tell me how to erase this graffiti," is converted into text.

[1278] Step 10:

[1279] emotion recognition

[1280] The server uses an emotion engine (e.g., tone analyzer) to recognize the user's emotion from voice tone and visual information. The input is voice data and facial expression data, and the output is the user's emotional state. It identifies whether the user is anxious or calm.

[1281] Step 11:

[1282] Integrating analysis results and generating solutions

[1283] The server integrates the analyzed visual information, audio data, and emotion recognition results, and generates an appropriate solution using a generative AI model (e.g., an advanced language generation model). The input is the integrated data, and the output is the generated solution. For example, a specific procedure such as "pour boiling water over the area, scrub with a brush, and finish with detergent" may be suggested.

[1284] Step 12:

[1285] Submit a solution

[1286] The server sends the generated solution to the terminal. The input is the solution data, and the output is a transmission completion message. The solution data is converted into a format that is easy for the user to understand before being sent.

[1287] Step 13:

[1288] Providing a solution

[1289] The terminal presents the received solutions to the user. The input is the solution data received from the server, and the output is the solution information displayed to the user. The terminal presents the proposed solutions to the user in text or voice.

[1290] Step 14:

[1291] Implementing the solution

[1292] The user executes the proposed solution. The input is the proposed solution, and the output is the execution result. The user follows specific steps to solve the problem.

[1293] Step 15:

[1294] Send Feedback

[1295] After implementing the solution, the user feeds the results back to the server via their device. The input is the implementation result, and the output is the feedback data. For example, the user may report that the graffiti has completely disappeared.

[1296] Step 16:

[1297] Processing Feedback

[1298] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine. The input is the feedback data, and the output is an updated training model. This continuously improves the accuracy and effectiveness of the system.

[1299] The above is the processing flow and specific operation of the program of this system.

[1300] (Application example 2)

[1301] 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."

[1302] Currently, many security systems face challenges in providing appropriate information and responding quickly when users feel anxious. Specifically, they are unable to fully alleviate users' anxiety because they mechanically present solutions without considering the user's emotions. Furthermore, while users who feel anxious or nervous need a quick and effective solution, current systems do not adequately support this.

[1303] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to input visual information, voice input means for the user to input voice data, analysis means for analyzing the data input from the input means and the voice input means, generation means for generating an optimal solution based on the analyzed data, presentation means for presenting the generated solution to the user, feedback means for feeding back the results of implementing the presented solution, learning means for learning the results received from the feedback means, emotion recognition means for recognizing the user's emotion, and adjustment means for adjusting the solution based on the output of the emotion recognition means. This makes it possible to provide quick and accurate security measures according to the user's emotional state.

[1304] "Visual information" refers to images and videos that users input through devices such as cameras.

[1305] "Voice data" refers to voice information input by a user using a microphone.

[1306] "Input means" refers to devices and functions for acquiring visual information and audio data.

[1307] "Analysis means" refers to a function that processes input visual information and audio data and analyzes the content thereof.

[1308] "Generation means" refers to a function that generates an optimal solution based on the data processed by the analysis means.

[1309] "Presentation means" refers to a function for displaying the generated solution to the user.

[1310] "Feedback means" refers to the function of collecting the results of users implementing the proposed solutions.

[1311] "Learning means" refers to a function that performs learning to improve the accuracy of the system based on the results received from the feedback means.

[1312] "Emotion recognition means" refers to the function of recognizing emotions from the user's tone of voice, facial expressions, etc.

[1313] The "adjustment means" refers to a function that adjusts the generated solution according to the user's emotional state based on the output of the emotion recognition means.

[1314] To implement this invention, it is necessary to build a system that allows a user to input visual information and voice data using a smartphone, recognize emotions based on that data, and generate and present optimal solutions. To realize this system, the following hardware and software are used in combination.

[1315] Hardware

[1316] Smartphone: A device equipped with a camera and microphone that allows the user to input visual and audio data.

[1317] Server: The computational resources for analyzing data and generating and coordinating solutions.

[1318] software

[1319] Smartphone application (iOS / Android): Has the function of collecting visual information and audio data and sending it to a server.

[1320] Image analysis modules (e.g., OpenCV, TensorFlow): Analyze visual information and identify security vulnerabilities.

[1321] Speech recognition APIs (e.g., Google Speech-to-Text, Amazon Transcribe): Converts voice data into text data.

[1322] Emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition): Recognizes emotions from the user's tone of voice, facial expressions, etc.

[1323] Generative AI model: Generates optimal solutions based on analyzed data.

[1324] Feedback collection module: Collects the results of user actions and uses them as learning data for the system.

[1325] System Operation Overview

[1326] 1. Input method: The user takes visual information (e.g., images of the area around their home) using the smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using the microphone.

[1327] 2. Data transmission: The smartphone application transmits these data to the server as a dataset.

[1328] 3. Data analysis: The server analyzes visual information using an image analysis module, converts voice data into text using a voice recognition API, and analyzes the user's emotions using an emotion recognition engine.

[1329] 4. Solution generation and adjustment: The generative AI model generates optimal solutions based on the analysis data and adjusts the solutions based on emotion recognition results. For example, if the user is in a hurry, it will provide a quick and easy solution.

[1330] 5. Presenting a solution: The generated solution is sent to the user's smartphone and presented to them via text or voice.

[1331] 6. Feedback collection and learning: The user implements the proposed solution and provides feedback on the results to the server via their smartphone. The server uses this feedback to update the learning data and improve the accuracy of the system.

[1332] Specific examples

[1333] When a user feels unsure about the security situation at home at night, they can take a video of their garden with their smartphone camera and ask, "Where are you worried about tonight?" The smartphone application sends this data to a server, and the generative AI model uses the analysis and emotion recognition results to quickly and accurately generate solutions. For example, it provides specific instructions to the user via text and voice, such as, "Adding lighting to the north side of the garden and adjusting the position of the security camera would be effective."

[1334] Prompt Sentence Examples

[1335] text

[1336] Please check the security situation in the area and let us know what measures are in place to prevent crime. Users are very anxious.

[1337] Such a system will enable users to quickly resolve security concerns, and will hopefully continue to improve its accuracy and effectiveness through feedback gathering and learning.

[1338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1339] Step 1:

[1340] A user takes visual information (e.g., images of the area around their home) using a smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using a microphone. At this time, the user also includes facial expressions and tone of voice that express their emotional state.

[1341] Step 2:

[1342] The device collects the captured image data and recorded audio data and compiles them into a single dataset, which contains both visual information and audio data.

[1343] Step 3:

[1344] The device sends the dataset to the server, which stores the received dataset for analysis.

[1345] Step 4:

[1346] The server analyzes visual information using image analysis modules (e.g., OpenCV, TensorFlow), for example, to identify security vulnerabilities in image data around the home. The results of this analysis are generated as output.

[1347] Step 5:

[1348] The server converts the voice data into text data using a speech recognition API (e.g., Google Speech-to-Text, Amazon Transcribe). For example, the voice saying "Where are you worried about tonight?" is output as text data.

[1349] Step 6:

[1350] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition) to recognize the user's emotions. It identifies whether the user is anxious or calm from their tone of voice and facial expressions. The recognition results are generated as output.

[1351] Step 7:

[1352] The server uses a generative AI model to generate optimal solutions based on the analytical data and emotion recognition results, such as "Adding lighting to the north side of the garden and adjusting the position of security cameras would be effective."

[1353] Step 8:

[1354] The server sends the generated solution in text or audio format to the device, which then presents the solution to the user. Specifically, the solution is displayed as text on the smartphone screen or notified to the user by audio.

[1355] Step 9:

[1356] The user implements the proposed solution and sends the results back to the server via their smartphone, for example, "Adding lighting to the north side of the garden has improved crime prevention."

[1357] Step 10:

[1358] The server collects feedback data and stores it as training data, which updates the generative AI model and emotion recognition engine, improving the accuracy of the system.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] [Fourth embodiment]

[1363] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1364] 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.

[1365] 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).

[1366] 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.

[1367] 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.

[1368] 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).

[1369] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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."

[1376] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[1377] System Overview

[1378] User Actions

[1379] Users first launch a dedicated application on their smartphone (device), then use the camera to capture visual information (e.g., an image of the problem) and the audio microphone to describe the problem in detail. If necessary, users can also enter additional information in text.

[1380] Device behavior

[1381] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[1382] Server Operation

[1383] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[1384] 1. Analysis of imaging data:

[1385] The server uses image analysis tools (e.g., computer vision algorithms) to analyze the image data and extract features, such as determining whether graffiti in a parking lot is written in white chalk.

[1386] 2. Analysis of audio data:

[1387] The server converts the voice data into text data using a speech recognition method (e.g., a speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[1388] 3. Integration of analysis results:

[1389] The server integrates the results of the analysis of the visual information and the audio data, and generates an optimal solution using a generation means.

[1390] 4. Propose a solution:

[1391] The generated solution is converted into a user-friendly format (e.g., text, audio, image) and sent to the device.

[1392] Feedback and Learning

[1393] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1394] Specific examples

[1395] Visual information input and analysis

[1396] When a user wants to remove graffiti written on the asphalt of a parking lot, they take a picture of the graffiti with their smartphone. A voice prompt then asks, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[1397] The device sends this data to a server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti."

[1398] Solution generation and presentation

[1399] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti," suggesting specific steps such as "pour boiling water on it, scrub with a brush, and finish with detergent."

[1400] The device will provide the user with text and audio instructions.

[1401] Feedback and Learning

[1402] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[1403] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will greatly improve the efficiency and accuracy of problem solving.

[1404] The processing flow will be explained below.

[1405] Step 1:

[1406] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). Next, they use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[1407] Step 2:

[1408] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[1409] Step 3:

[1410] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the image is graffiti written in white chalk on asphalt).

[1411] Step 4:

[1412] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[1413] Step 5:

[1414] The server combines the analyzed visual and audio data and inputs the dataset into a generator, which generates an optimal solution (e.g., "How to pour hot water, scrub with a brush, and finish with detergent").

[1415] Step 6:

[1416] The server converts the generated solution into a format that is easy for the user to understand (text, image, audio, etc.), creates a data packet containing the solution, and sends it to the device as an HTTP response.

[1417] Step 7:

[1418] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in a format that is easy to understand (e.g., displaying and playing the solution in text and audio).

[1419] Step 8:

[1420] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[1421] Step 9:

[1422] The server analyzes the received feedback data, adds the analysis results to the training dataset of the generative AI model, and updates the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1423] Example 1

[1424] 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."

[1425] To quickly and effectively solve the various visual and auditory problems users encounter in their daily lives and at work, a system that can integrate and appropriately analyze multiple input data (visual information, audio data, text data) is required. However, current technology lacks the means to integrate and analyze such multiple data and present optimal solutions. As a result, users often spend a great deal of time and effort solving problems.

[1426] 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.

[1427] In this invention, the server includes an analysis means for analyzing visual information using an image analysis means, an analysis means for converting audio data into text data using a voice recognition means, a generation means for generating an optimal solution based on the analyzed visual information and audio data, a presentation means for converting the generated solution into a format that is easy for the user to understand and presenting it, a feedback means for providing feedback on the results of implementing the presented solution, and a learning means for learning from the results received from the feedback means and updating the generative AI model. This enables the analysis of visual and auditory problems and the provision of optimal solutions to be performed quickly and effectively. The user can instantly obtain a solution to the problem, and the system also learns based on the feedback, improving the accuracy of future problem-solving.

[1428] A "user" is an individual or organization that uses the system to input visual information and voice data to solve a problem.

[1429] "Input means" refers to a device or interface that allows a user to input visual information into a system.

[1430] "Audio input means" refers to a microphone or voice recording device that allows a user to input voice data into the system.

[1431] A "terminal" is an electronic device that compiles visual information and audio data entered by a user into a single data set and sends it to a server as an HTTP request.

[1432] A "server" is a computer system that receives data sets sent from terminals and processes analysis, solutions, presentation, and feedback.

[1433] "Image analysis means" refers to computer vision algorithms and software for analyzing visual information and extracting its features.

[1434] "Speech recognition means" refers to software or APIs for converting voice data into text data.

[1435] "Analysis means" is a general term for various tools and techniques for analyzing input visual information and audio data.

[1436] "Generative means" refers to AI models or algorithms that generate optimal solutions based on analyzed data.

[1437] The "presentation means" is a display or audio output device for presenting the generated solution to the user.

[1438] A "feedback means" is an interface that allows a user to report to the system the results of implementing a proposed solution.

[1439] "Learning methods" are algorithms and data processing techniques that update generative AI models based on data obtained from feedback and improve their accuracy.

[1440] A "generative AI model" is an artificial intelligence model that generates optimal solutions to users' concerns and problems.

[1441] A "prompt" is a specific text instruction for inputting instructions into a generative AI model.

[1442] This invention relates to a system in which a user inputs visual information and voice data using a smartphone, and a server analyzes the data to generate and present optimal solutions. This system operates by the user, device, and server each playing a specific role and cooperating with each other.

[1443] System configuration

[1444] User Actions

[1445] The user launches the dedicated application installed on their smartphone, then performs the following operations:

[1446] 1. Visual input: Use your smartphone camera to take a picture of the problem object, for example, graffiti on the asphalt of a parking lot.

[1447] 2. Voice input: Use your smartphone's microphone to verbally describe the problem in detail, for example, "Please tell me how to remove this graffiti."

[1448] 3. Enter text information: If necessary, enter detailed information such as the number of days since the event and the location in text.

[1449] Device behavior

[1450] The device collects visual, audio, and text input from the user into a single dataset, which is then sent to the server as an HTTP request.

[1451] Server Operation

[1452] The server receives the data set sent from the device and performs the following processes:

[1453] 1. Image data analysis: The server uses image analysis tools (e.g., computer vision algorithms) to analyze visual information. Specifically, libraries such as OpenCV can be used. For example, to identify graffiti written in white chalk on the asphalt of a parking lot.

[1454] 2. Analysis of voice data: The server converts the voice data into text data using a voice recognition method (e.g., a voice recognition API). For example, the Google Speech-to-Text API can be used. The converted text data, along with the text information entered by the user, is analyzed by a natural language processing module (e.g., spaCy) to identify the user's concerns.

[1455] 3. Integrating the analysis results: Integrating the analyzed visual information and audio data and generating an optimal solution using a generative AI model (e.g., GPT-4).

[1456] 4. Presenting the solution: The generated solution is converted into a format that is easy for the user to understand (e.g., text, audio, image) and sent to the device.

[1457] Feedback and Learning

[1458] The user implements the proposed solution and provides feedback on the results to the server via their device. The server then analyzes this feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1459] Specific examples

[1460] Visual information input and analysis

[1461] If a user wants to remove graffiti written on the asphalt of a parking lot, they take a photo of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." They then enter detailed information such as the number of days since the graffiti was written and its location in text.

[1462] Solution generation and presentation

[1463] Based on the integrated analysis results, the server uses a generative AI model to generate a "method for removing graffiti." For example, it might suggest specific steps such as "pour hot water, scrub with a brush, and finish with detergent." The device then presents these steps to the user in text and voice.

[1464] Feedback and Learning

[1465] After implementing the solution, the user provides feedback on the result via their device, saying, "The graffiti has completely disappeared." The server receives this feedback and updates the generative AI model, enabling it to provide more accurate solutions in the future.

[1466] Prompt Sentence Examples

[1467] Below is an example of a prompt sentence to input to the generative AI model.

[1468] "How do I remove graffiti written in white chalk on asphalt?"

[1469] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems encountered in daily life, and this system will significantly improve the efficiency and accuracy of problem solving.

[1470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1471] Step 1: User enters visual information

[1472] What it does: The user uses their smartphone camera to take an image of the problem they want to solve.

[1473] Input: Visual information (image) of the problem

[1474] Output: Captured image data

[1475] Step 2: User enters voice data

[1476] What it does: The user uses their smartphone's microphone to verbally describe the details of the problem they want to solve.

[1477] Input: User's voice data

[1478] Output: Recorded audio data

[1479] Step 3: User enters text information

[1480] Specific Action: The user enters additional information related to the issue (e.g., number of days since issue occurred or detailed situation) via text into their smartphone, if necessary.

[1481] Input: User's text information

[1482] Output: The input text data

[1483] Step 4: Data integration by terminal

[1484] Specific operation: The device combines visual information, audio data, and text information input by the user into a single data set.

[1485] Input: image data, audio data, text data

[1486] Output: A consolidated dataset

[1487] Step 5: Send data by device

[1488] Specific operation: The terminal sends the integrated data set to the server as an HTTP request.

[1489] Input: Integrated dataset

[1490] Output: HTTP request sent to the server

[1491] Step 6: Image data analysis by the server

[1492] Specific operation: The server extracts image data from the received dataset and extracts features using image analysis means (e.g., OpenCV).

[1493] Input: Image data

[1494] Data processing or calculation: feature extraction by image analysis means

[1495] Output: Image analysis results (e.g., "Graffiti written in white chalk on asphalt")

[1496] Step 7: Server analyzes the audio data

[1497] Specific operation: The server converts the received voice data into text data using a speech recognition tool (e.g., Google Speech-to-Text API), and then uses a natural language processing module (e.g., spaCy) to identify the user's concerns.

[1498] Input: Audio data

[1499] Data processing or computation: Speech-to-text conversion and natural language processing

[1500] Output: Text data of the speech analysis results (e.g., "Please tell me how to erase this graffiti.")

[1501] Step 8: Server integration of analysis results

[1502] Specific operation: The server integrates the image analysis results and audio analysis results and generates the optimal solution using a generative AI model (e.g., GPT-4).

[1503] Input: Image analysis results, audio analysis results

[1504] Data manipulation or computation: Generating solutions using generative AI models

[1505] Output: The generated solution (e.g., "Pour hot water on it, scrub with a brush, and finish with detergent")

[1506] Step 9: Server converts and sends the solution

[1507] Specific operation: The server converts the generated solution into a format that is easy for the user to understand (e.g., text, audio, image) and sends it to the terminal.

[1508] Input: Generated solution

[1509] Data processing or calculation: transformation of the solution

[1510] Output: Solution data to present to the user

[1511] Step 10: Providing a solution via terminal

[1512] Specific operation: The device presents the received solution to the user via text or voice.

[1513] Input: Data for the proposed solution

[1514] Output: Present the solution to the user

[1515] Step 11: User feedback

[1516] Specific operation: After the user implements the solution, the results are fed back through the terminal.

[1517] Input: Execution result feedback (text or audio data)

[1518] Output: Feedback data

[1519] Step 12: Server analyzes feedback and learns

[1520] Specific operation: The server analyzes the feedback data and uses it as training data for the generative AI model.

[1521] Input: Feedback data

[1522] Data processing or computation: analyzing feedback data and updating generative AI models

[1523] Output: An updated generative AI model

[1524] (Application example 1)

[1525] 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."

[1526] On traditional online shopping sites, users often have problems selecting products because they cannot instantly grasp the product's features or because the means to resolve questions about the product's details are not immediately provided. Furthermore, because information from multiple data input methods is not integrated and analyzed, it is difficult to present optimal solutions to the problems users face.

[1527] 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.

[1528] In this invention, the server includes an input means for a user to input visual information, a voice input means for a user to input voice data, an analysis means for analyzing the data input from the input means and the voice input means, a generation means for generating an optimal solution based on the analyzed data, a presentation means for presenting the generated solution to the user, a feedback means for feeding back the results of implementing the presented solution, a learning means for learning the results received from the feedback means, an image analysis means for extracting product features using images, a voice recognition means for converting voice data into text data, a means for analyzing the text data using natural language processing means and understanding the user's question, and a means for presenting the user with a generated solution related to the product using a generative AI model. This makes it possible to quickly and effectively solve problems users have when selecting products.

[1529] A "user" is a person who uses this system to select products or resolve questions.

[1530] A "smartphone" is a portable information terminal that allows a user to input visual and audio data.

[1531] "Visual information" refers to product images and related images that are input by the user using a camera.

[1532] "Voice data" refers to voice information uttered by a user using a microphone, including questions and instructions.

[1533] "Input means" refers to tools or devices that allow a user to input visual information or audio data.

[1534] "Analysis means" refers to algorithms or programs for analyzing and understanding input visual information and audio data.

[1535] "Generation means" refers to the methods and mechanisms for generating optimal solutions based on the analyzed data.

[1536] "Presentation means" refers to a method or device for presenting the generated solution to the user in an easy-to-understand form.

[1537] "Feedback means" refers to the techniques and tools that allow users to return the results of their actions to the system.

[1538] "Learning tools" refers to machine learning models that analyze data from feedback and aim to improve the accuracy of future solutions.

[1539] "Image analysis means" refers to algorithms or software for analyzing visual information and recognizing products and their features.

[1540] "Speech recognition means" refers to techniques and tools for converting voice data into text.

[1541] "Natural language processing means" refers to algorithms and technologies used to analyze text data and understand users' questions and intent.

[1542] A "generative AI model" refers to an artificial intelligence model that generates optimal solutions based on analysis results.

[1543] "Prompt sentence" refers to predefined text that is input into a generative AI model.

[1544] The present invention relates to a system that allows a user to input visual information and voice data using a smartphone, analyzes the data, and generates and provides optimal solutions. In this system, the user, terminal, and server each play specific roles and work in cooperation with each other.

[1545] System Overview

[1546] User Actions

[1547] Users first launch the dedicated application on their smartphone (device), then use the camera to take a picture of the product packaging, and then use the audio microphone to ask questions or provide details. If necessary, they can also enter additional information via text.

[1548] Device behavior

[1549] The device collects visual, audio, and textual information from the user into a single dataset, which it then sends to the server as an HTTP request. The device is also responsible for the server's solution and how it presents it.

[1550] Server Operation

[1551] The server receives the data set sent from the terminal and analyzes each data. Specifically, it performs the following processes.

[1552] 1. Analysis of imaging data:

[1553] The server analyzes the image data using image analysis tools (e.g., TensorFlow or OpenCV) to extract product features. For example, it identifies specific features such as "Brand A shampoo."

[1554] 2. Analysis of audio data:

[1555] The server converts the voice data into text using a speech recognition tool (e.g., Google Cloud Speech-to-Text API), then analyzes the converted text using a natural language processing tool (e.g., GPT-4) to understand the user's question.

[1556] 3. Integration of analysis results:

[1557] The server integrates the results of the analysis of visual information and audio data and generates an optimal solution using a generation means (e.g., a generative AI model).

[1558] 4. Propose a solution:

[1559] The generated solution is converted into a user-friendly format (e.g., text, voice) and sent to the device.

[1560] Feedback and Learning

[1561] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes the feedback data and uses it as training data for the generative AI model, thereby improving the accuracy of solutions to similar problems in the future.

[1562] Specific examples

[1563] A user wants to know information about "Brand A Shampoo," so they take a picture of the product package with their smartphone. They also ask aloud, "Please tell me the reviews and stock information for this product." An example of a prompt sentence is as follows:

[1564] Example prompt sentence:

[1565] A user uploaded an image of a product package and asked, "Please tell me the reviews and stock information for this product." Image analysis determined that the product was "Brand A Shampoo." Based on this, please generate the best answer for the user.

[1566] The server performs the above process, generates the optimal solution to the user's question, and sends it back to the terminal. The terminal then presents this solution to the user in text and voice. This process allows the user to quickly and accurately obtain product information.

[1567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1568] Step 1:

[1569] The user launches a dedicated application on their smartphone (device), takes a picture of the product packaging with the camera, and then uses the audio microphone to input a question such as, "Please tell me the reviews and stock information for this product." The input data consists of visual information (product image) and audio data (user question).

[1570] Step 2:

[1571] The device acquires visual information (product images) and audio data input by the user, compiles it into a single dataset, and sends it to the server as an HTTP request. The input is a set of product images and audio data, and the output is a dataset in HTTP request format.

[1572] Step 3:

[1573] The server analyzes the dataset received from the device. First, it analyzes the product image using image analysis tools (such as TensorFlow or OpenCV) to extract product features (e.g., "Brand A shampoo"). The input is the product image, and the output is the extracted product features. This step also involves preprocessing the product image (resizing and noise removal).

[1574] Step 4:

[1575] The server converts the voice data into text data using a speech recognition tool (such as the Google Cloud Speech-to-Text API). The input is the voice data, and the output is the text data converted from the voice (e.g., "Please tell me the reviews and stock information for this product."). The converted text data is further analyzed using natural language processing tools to clarify the user's question and intent.

[1576] Step 5:

[1577] The server integrates the results of analysis of visual information (extracted product features) and audio data (text data converted from audio) and generates the optimal solution using a generation method (generative AI model). Specifically, it extracts product-related reviews and inventory information, and generates the information the user is looking for. The input is the integrated analysis results, and the output is the optimal solution (answer in text format).

[1578] Step 6:

[1579] The server converts the generated solution into a user-understandable format (e.g., text or voice) and sends it to the device. The input is the textual solution, and the output is the formatted data for presentation to the user.

[1580] Step 7:

[1581] The device receives the solution sent from the server and presents it to the user. Specifically, it displays the solution as text on the smartphone screen and, in some cases, uses speech synthesis to read it aloud to the user. The input is the formatted solution sent from the server, and the output is the content presented to the user.

[1582] Step 8:

[1583] The user implements the proposed solution and feeds the results back to the server via the terminal. The input is the result of the user's implementation, and the output is the feedback data.

[1584] Step 9:

[1585] The server analyzes the feedback data and uses it as training data for the generative AI model. Here, the formatted data is added to the database to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model.

[1586] 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.

[1587] The following describes in detail the embodiments of the present invention. This invention relates to a system in which a user inputs visual information and voice data using a smartphone, recognizes the user's emotions based on this data, and generates and provides optimal solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. An emotion engine is also integrated to recognize the user's emotions.

[1588] System Overview

[1589] User Actions

[1590] The user first launches a dedicated application using their smartphone (device). Next, they use the camera to capture visual information (e.g., an image of the problem) and use the audio microphone to describe the problem in detail. The user's facial expressions and tone obtained from audio and visual information are also collected to identify the user's emotions. If necessary, additional information can be entered as text.

[1591] Device behavior

[1592] The device compiles the visual, audio, and textual information input by the user into a single dataset, then sends the dataset to the server, which is also responsible for presenting the server's solutions and the user's emotion recognition results.

[1593] Server Operation

[1594] The server receives the data set sent from the terminal and processes it as follows.

[1595] 1. Analysis of imaging data:

[1596] The server uses an image analysis module (e.g., computer vision algorithms) to analyze the image data and extract its features, for example, to determine whether graffiti in a parking lot is written in white chalk.

[1597] 2. Analysis of audio data:

[1598] The server converts the voice data into text data using a speech recognition module (e.g., speech recognition API), and then uses a natural language processing module to identify the user's concerns based on the converted text and the text information entered by the user.

[1599] 3. Emotion Recognition:

[1600] The server uses an emotion engine to identify the user's emotions from the audio data and visual information, for example, determining whether the user is anxious or calm from the tone of their voice and facial expressions.

[1601] 4. Integrating the analysis results and generating solutions:

[1602] The server combines the analyzed visual information, audio data, and emotion recognition results to generate an optimal solution. The generated solution is adjusted according to the user's emotions. For example, if the user is impatient, a simpler and faster solution will be presented.

[1603] 5. Propose a solution:

[1604] The generated solution is converted into a user-friendly format (text, audio, image) and sent to the device.

[1605] Feedback and Learning

[1606] The user implements the proposed solution and feeds the results back to the server via their device. The server analyzes this feedback data and uses it as training data for the generative AI model and emotion engine. This will improve the accuracy of solutions to similar problems and emotion recognition in the future.

[1607] Specific examples

[1608] Input and analysis of visual information and emotion recognition

[1609] If a user wants to remove graffiti from the asphalt of a parking lot, they can take a picture of the graffiti with their smartphone. A voice prompt will then ask, "Please tell me how to remove this graffiti." Furthermore, if the user is anxious, the system will recognize their emotion from their facial expression and tone of voice.

[1610] The device sends this data to the server, which uses image analysis to determine that the graffiti is "graffiti written in white chalk on asphalt," and uses voice recognition to convert the voice data into text such as "Please tell me how to remove this graffiti." The emotion engine then recognizes that the user is anxious.

[1611] Solution generation and presentation

[1612] Based on the integrated analysis and emotion recognition results, the server uses a generative AI model to generate solutions, such as suggesting specific steps to quickly remove graffiti: pour boiling water over it, scrub with a brush, and finish with detergent.

[1613] The device will explain these steps to the user in text and audio, and will simplify the steps to accommodate the user's impatience.

[1614] Feedback and Learning

[1615] After implementing the solution, the user provides feedback on the results to the server via their device (e.g., "The graffiti has completely disappeared"). The server receives this feedback and updates the generative AI model and emotion engine to improve the accuracy of problem-solving in future.

[1616] Thus, the present invention provides a means for users to quickly and effectively solve visual and auditory problems they encounter in their daily lives, incorporating emotion recognition, which will significantly improve the efficiency and accuracy of problem-solving.

[1617] The processing flow will be explained below.

[1618] Step 1:

[1619] The user starts up their smartphone (device) and opens a dedicated app. They use the camera to take a picture of the visual information in question (e.g., an image of graffiti). They also use the microphone to describe the situation verbally (e.g., "I want to remove this graffiti"). If necessary, they can enter detailed information (such as the number of days since the problem occurred and its location) in text.

[1620] Step 2:

[1621] The device compiles the visual, audio, and text information input by the user into a single dataset. It then uses an emotion engine to recognize the user's emotions from the audio and visual information. The dataset, which also includes the emotion recognition results, is then sent to the server.

[1622] Step 3:

[1623] The server receives the data set sent from the device. First, it extracts the image data and inputs it into an image analysis module (e.g., a computer vision algorithm) to extract visual features (e.g., determine that the data is graffiti written in white chalk on asphalt).

[1624] Step 4:

[1625] The server extracts the voice data and converts it into text using a speech recognition module (e.g., speech recognition API). Based on the converted text and the text information entered by the user, a natural language processing module identifies the user's concerns.

[1626] Step 5:

[1627] The server analyzes the results of the emotion engine to identify the user's emotional state (e.g., anxious, calm). The server then combines the analyzed visual information, audio data, and emotion recognition results and inputs the resulting dataset into the generator.

[1628] Step 6:

[1629] The generator generates an optimal solution based on the integrated data (e.g., "Pour hot water, scrub with a brush, and finish with detergent"), which is customized according to the user's emotional state (e.g., if the user is impatient, simplify the steps).

[1630] Step 7:

[1631] The server converts the generated solution into a user-friendly format (text, image, audio), creates a data packet containing the converted solution, and sends it to the device as an HTTP response.

[1632] Step 8:

[1633] The device analyzes the data packets received from the server, extracts the data containing the solution, and presents it to the user in an easy-to-understand format (e.g., displaying and playing the solution in text and audio). At this time, it also displays the emotion recognition results so that the user can understand their own emotional state.

[1634] Step 9:

[1635] The user implements the proposed solution, records the results (e.g., "The graffiti has completely disappeared") in text, images, and audio, and sends the feedback data to the server via the device.

[1636] Step 10:

[1637] The server analyzes the received feedback data and adds the analysis results to the training datasets of the generative AI model and emotion engine, updating them to improve the accuracy of solutions to similar problems in the future and the accuracy of emotion recognition.

[1638] Example 2

[1639] 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."

[1640] In modern life, it is important to provide quick and effective solutions to the various problems users face. However, with conventional methods, it has been difficult to provide solutions that take into account the user's emotional state. For example, it is difficult to present different solutions depending on whether the user is anxious or calm. In addition, there are limited means to continuously train the system through feedback and improve its accuracy. To solve these challenges, a system that recognizes the user's emotions and provides optimal solutions based on those emotions is needed.

[1641] 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.

[1642] In this invention, the server includes an analysis means, an emotion recognition means, and a generation means. This makes it possible to analyze the visual information and voice data input by the user, recognize the user's emotions, and generate and present optimal solutions according to that state. Furthermore, feedback from users can be collected and analyzed by a learning means, and the accuracy of the system can be continuously improved. In this way, a system is realized that can provide solutions optimized for individual situations for the various problems faced by users.

[1643] "Image input means" refers to a function that allows the user to input visual information.

[1644] "Voice input means" refers to a function that allows a user to input voice data.

[1645] The "data set generating means" refers to a function that combines data input from the image input means and the voice input means into one data set.

[1646] "Data transmission means" refers to a function for transmitting the data set to the server.

[1647] "Analysis means" refers to a function in the server that analyzes the dataset.

[1648] The "emotion recognition means" refers to a function that recognizes the user's emotions based on the data analyzed by the analysis means.

[1649] The "generation means" refers to a function that generates an optimal solution by taking into account the results of the emotion recognition means.

[1650] The "presentation means" refers to a function that presents the generated solution to the user.

[1651] The "feedback means" refers to a function for reflecting the results of implementing the proposed solution.

[1652] The "learning means" refers to a function that learns the system based on the results received from the feedback means and improves accuracy.

[1653] "Image analysis means" refers to a function for analyzing visual information.

[1654] "Speech recognition means" refers to a function that converts voice data into text data.

[1655] The present invention relates to a system that allows a user to input visual information and voice data using a smart device, recognizes the user's emotions based on this data, and generates and provides appropriate solutions. This system achieves effective problem solving by having the user, terminal, and server work together and fulfill their respective roles. Specific embodiments are described in detail below.

[1656] User Actions

[1657] 1. Launch the dedicated app

[1658] The user launches a dedicated app on a smart device (e.g., a smartphone). The app's generic name is "Problem Solving Assistant."

[1659] 2. Visual information input

[1660] Users use their smart device's camera to take an image of the problem, for example, graffiti in a parking lot.

[1661] 3. Inputting voice data

[1662] Users can use the microphone to verbally describe the problem in detail, such as "How do I remove this graffiti?", and optionally enter additional information in text.

[1663] 4. Collecting emotional information

[1664] The user's facial expressions and tone of voice are also collected through the smart device.

[1665] Device behavior

[1666] 1. Generating the dataset

[1667] The terminal (smart device) combines the collected visual information, audio data, and text information into a single data set.

[1668] 2. Submitting the dataset

[1669] The device sends the generated data set to a server over the internet, where it is encrypted.

[1670] 3. Receiving and Displaying the Solution

[1671] The device receives solutions and emotion recognition results sent from the server, and the received information is presented to the user via text message or voice.

[1672] Server Operation

[1673] 1. Receiving Data

[1674] The server receives the data set sent from the device, stores it in a database, and begins analysis.

[1675] 2. Analysis of image data

[1676] The server uses computer vision algorithms (e.g., OpenCV) to analyze the image data, for example, to detect graffiti written in white chalk on the asphalt of a parking lot.

[1677] 3. Analysis of audio data

[1678] The server converts the voice data into text using a speech recognition API (e.g., a cloud-based speech recognition service), and then uses a natural language processing module (e.g., an open-source NLP library) to identify the user's concerns.

[1679] 4. Emotion recognition

[1680] The server uses an emotion recognition engine (e.g., a tone analyzer) to recognize the user's emotions from voice data and visual information. It determines whether the user is anxious or calm from their voice tone and facial expression.

[1681] 5. Solution Generation

[1682] The server integrates the analyzed visual information, audio data, and emotion recognition results and uses a generative AI model (e.g., an advanced language generation model) to generate an optimal solution. For example, it might suggest a quick method for removing graffiti: pour hot water over it, scrub with a brush, and finish with detergent.

[1683] 6. Submit your solution

[1684] The server sends the generated solution in a user-friendly format to the device, where the solution is presented in text and audio format.

[1685] Feedback and Learning

[1686] 1. Implementing the solution

[1687] The user follows the suggested solutions to solve the problem.

[1688] 2. Submitting Feedback

[1689] The user sends the results of the solution to the server via their device, providing feedback such as whether the graffiti has been completely removed.

[1690] 3. Processing Feedback

[1691] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine, thereby improving the system's problem-solving accuracy and emotion recognition accuracy.

[1692] Specific examples

[1693] If a user wants to remove graffiti written on the asphalt of a parking lot, they first take a picture of the graffiti with their smart device and then provide a voice instruction saying, "Please tell me how to remove this graffiti." The device then sends this visual and voice information to the server. The server analyzes this data, uses image analysis means to determine that it is "graffiti made with white chalk," and uses voice recognition means to convert the user's request into text. The server then uses an emotion recognition engine to recognize that the user is impatient and generates a solution appropriate to that situation. For example, it provides specific instructions such as, "To quickly remove graffiti, use hot water and a brush."

[1694] As such, the present invention is a system that quickly provides solutions optimized for individual situations to various problems faced by users, thereby improving user satisfaction and problem-solving efficiency.

[1695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1696] Processing step flow

[1697] Step 1:

[1698] Launching the dedicated app

[1699] The user launches a dedicated app on their smart device. The input is the operation to launch the app, and the output is the display of the app's home screen. The app launches when the user taps the app's icon.

[1700] Step 2:

[1701] Visual information input

[1702] The user activates the camera on their smart device and takes a picture of the target object. The input is the image data captured by the camera, and the output is saved as an image file on the device. The user opens the camera app and taps the shutter button to capture the image.

[1703] Step 3:

[1704] Inputting audio data

[1705] The user uses the microphone on their smart device to describe the details of the problem. The input is audio data collected by the microphone, and the output is saved as an audio file on the device. The user presses the microphone button in the app and speaks, "Please tell me how to erase this graffiti."

[1706] Step 4:

[1707] Collecting emotional information

[1708] The user's facial expressions and voice tone are collected by the device's camera and microphone. The input is facial expression data and voice tone data captured by the camera, and the output is the data necessary for analysis to identify emotions. Emotional information such as the user's impatience or calmness is collected.

[1709] Step 5:

[1710] Generating the dataset

[1711] The device combines visual information, audio data, and text information into a single dataset. The input is captured images, recorded audio, and collected emotion data, and the output is a unified dataset. The device combines these different data formats into a single file.

[1712] Step 6:

[1713] Submitting a Dataset

[1714] The terminal sends the generated dataset to the server. The input is the dataset, and the output is the transmission result to the server (such as a transmission completion message). The dataset is encrypted and sent to the server over the network.

[1715] Step 7:

[1716] Receiving data

[1717] The server receives the dataset sent from the device. The input is the received dataset, and the output is the data stored in the server's database. The server stores the received data in the database in preparation for analysis.

[1718] Step 8:

[1719] Image data analysis

[1720] The server analyzes the image data using a computer vision algorithm (e.g., OpenCV) and extracts features. The input is the image data, and the output is the analyzed feature information. For example, it can detect graffiti written in chalk and identify its location and color.

[1721] Step 9:

[1722] Analysis of audio data

[1723] The server converts the voice data into text data using a voice recognition API (e.g., a cloud-based voice recognition service). The input is voice data, and the output is text data. The user's speech, "Please tell me how to erase this graffiti," is converted into text.

[1724] Step 10:

[1725] emotion recognition

[1726] The server uses an emotion engine (e.g., tone analyzer) to recognize the user's emotion from voice tone and visual information. The input is voice data and facial expression data, and the output is the user's emotional state. It identifies whether the user is anxious or calm.

[1727] Step 11:

[1728] Integrating analysis results and generating solutions

[1729] The server integrates the analyzed visual information, audio data, and emotion recognition results, and generates an appropriate solution using a generative AI model (e.g., an advanced language generation model). The input is the integrated data, and the output is the generated solution. For example, a specific procedure such as "pour boiling water over the area, scrub with a brush, and finish with detergent" may be suggested.

[1730] Step 12:

[1731] Submit a solution

[1732] The server sends the generated solution to the terminal. The input is the solution data, and the output is a transmission completion message. The solution data is converted into a format that is easy for the user to understand before being sent.

[1733] Step 13:

[1734] Providing a solution

[1735] The terminal presents the received solutions to the user. The input is the solution data received from the server, and the output is the solution information displayed to the user. The terminal presents the proposed solutions to the user in text or voice.

[1736] Step 14:

[1737] Implementing the solution

[1738] The user executes the proposed solution. The input is the proposed solution, and the output is the execution result. The user follows specific steps to solve the problem.

[1739] Step 15:

[1740] Send Feedback

[1741] After implementing the solution, the user feeds the results back to the server via their device. The input is the implementation result, and the output is the feedback data. For example, the user may report that the graffiti has completely disappeared.

[1742] Step 16:

[1743] Processing Feedback

[1744] The server analyzes the feedback data and uses it as training data for the generative AI model and emotion recognition engine. The input is the feedback data, and the output is an updated training model. This continuously improves the accuracy and effectiveness of the system.

[1745] The above is the processing flow and specific operation of the program of this system.

[1746] (Application example 2)

[1747] 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."

[1748] Currently, many security systems face challenges in providing appropriate information and responding quickly when users feel anxious. Specifically, they are unable to fully alleviate users' anxiety because they mechanically present solutions without considering the user's emotions. Furthermore, while users who feel anxious or nervous need a quick and effective solution, current systems do not adequately support this.

[1749] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means for the user to input visual information, voice input means for the user to input voice data, analysis means for analyzing the data input from the input means and the voice input means, generation means for generating an optimal solution based on the analyzed data, presentation means for presenting the generated solution to the user, feedback means for feeding back the results of implementing the presented solution, learning means for learning the results received from the feedback means, emotion recognition means for recognizing the user's emotion, and adjustment means for adjusting the solution based on the output of the emotion recognition means. This makes it possible to provide quick and accurate security measures according to the user's emotional state.

[1750] "Visual information" refers to images and videos that users input through devices such as cameras.

[1751] "Voice data" refers to voice information input by a user using a microphone.

[1752] "Input means" refers to devices and functions for acquiring visual information and audio data.

[1753] "Analysis means" refers to a function that processes input visual information and audio data and analyzes the content thereof.

[1754] "Generation means" refers to a function that generates an optimal solution based on the data processed by the analysis means.

[1755] "Presentation means" refers to a function for displaying the generated solution to the user.

[1756] "Feedback means" refers to the function of collecting the results of users implementing the proposed solutions.

[1757] "Learning means" refers to a function that performs learning to improve the accuracy of the system based on the results received from the feedback means.

[1758] "Emotion recognition means" refers to the function of recognizing emotions from the user's tone of voice, facial expressions, etc.

[1759] The "adjustment means" refers to a function that adjusts the generated solution according to the user's emotional state based on the output of the emotion recognition means.

[1760] To implement this invention, it is necessary to build a system that allows a user to input visual information and voice data using a smartphone, recognize emotions based on that data, and generate and present optimal solutions. To realize this system, the following hardware and software are used in combination.

[1761] Hardware

[1762] Smartphone: A device equipped with a camera and microphone that allows the user to input visual and audio data.

[1763] Server: The computational resources for analyzing data and generating and coordinating solutions.

[1764] software

[1765] Smartphone application (iOS / Android): Has the function of collecting visual information and audio data and sending it to a server.

[1766] Image analysis modules (e.g., OpenCV, TensorFlow): Analyze visual information and identify security vulnerabilities.

[1767] Speech recognition APIs (e.g., Google Speech-to-Text, Amazon Transcribe): Converts voice data into text data.

[1768] Emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition): Recognizes emotions from the user's tone of voice, facial expressions, etc.

[1769] Generative AI model: Generates optimal solutions based on analyzed data.

[1770] Feedback collection module: Collects the results of user actions and uses them as learning data for the system.

[1771] System Operation Overview

[1772] 1. Input method: The user takes visual information (e.g., images of the area around their home) using the smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using the microphone.

[1773] 2. Data transmission: The smartphone application transmits these data to the server as a dataset.

[1774] 3. Data analysis: The server analyzes visual information using an image analysis module, converts voice data into text using a voice recognition API, and analyzes the user's emotions using an emotion recognition engine.

[1775] 4. Solution generation and adjustment: The generative AI model generates optimal solutions based on the analysis data and adjusts the solutions based on emotion recognition results. For example, if the user is in a hurry, it will provide a quick and easy solution.

[1776] 5. Presenting a solution: The generated solution is sent to the user's smartphone and presented to them via text or voice.

[1777] 6. Feedback collection and learning: The user implements the proposed solution and provides feedback on the results to the server via their smartphone. The server uses this feedback to update the learning data and improve the accuracy of the system.

[1778] Specific examples

[1779] When a user feels unsure about the security situation at home at night, they can take a video of their garden with their smartphone camera and ask, "Where are you worried about tonight?" The smartphone application sends this data to a server, and the generative AI model uses the analysis and emotion recognition results to quickly and accurately generate solutions. For example, it provides specific instructions to the user via text and voice, such as, "Adding lighting to the north side of the garden and adjusting the position of the security camera would be effective."

[1780] Prompt Sentence Examples

[1781] text

[1782] Please check the security situation in the area and let us know what measures are in place to prevent crime. Users are very anxious.

[1783] Such a system will enable users to quickly resolve security concerns, and will hopefully continue to improve its accuracy and effectiveness through feedback gathering and learning.

[1784] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1785] Step 1:

[1786] A user takes visual information (e.g., images of the area around their home) using a smartphone camera and inputs voice data (e.g., "Where are you worried about tonight?") using a microphone. At this time, the user also includes facial expressions and tone of voice that express their emotional state.

[1787] Step 2:

[1788] The device collects the captured image data and recorded audio data and compiles them into a single dataset, which contains both visual information and audio data.

[1789] Step 3:

[1790] The device sends the dataset to the server, which stores the received dataset for analysis.

[1791] Step 4:

[1792] The server analyzes visual information using image analysis modules (e.g., OpenCV, TensorFlow), for example, to identify security vulnerabilities in image data around the home. The results of this analysis are generated as output.

[1793] Step 5:

[1794] The server converts the voice data into text data using a speech recognition API (e.g., Google Speech-to-Text, Amazon Transcribe). For example, the voice saying "Where are you worried about tonight?" is output as text data.

[1795] Step 6:

[1796] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API, Amazon Rekognition) to recognize the user's emotions. It identifies whether the user is anxious or calm from their tone of voice and facial expressions. The recognition results are generated as output.

[1797] Step 7:

[1798] The server uses a generative AI model to generate optimal solutions based on the analytical data and emotion recognition results, such as "Adding lighting to the north side of the garden and adjusting the position of security cameras would be effective."

[1799] Step 8:

[1800] The server sends the generated solution in text or audio format to the device, which then presents the solution to the user. Specifically, the solution is displayed as text on the smartphone screen or notified to the user by audio.

[1801] Step 9:

[1802] The user implements the proposed solution and sends the results back to the server via their smartphone, for example, "Adding lighting to the north side of the garden has improved crime prevention."

[1803] Step 10:

[1804] The server collects feedback data and stores it as training data, which updates the generative AI model and emotion recognition engine, improving the accuracy of the system.

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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).

[1812] 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.

[1813] 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."

[1814] 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.

[1815] 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).

[1816] 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.

[1817] 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.

[1818] 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.

[1819] 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.

[1820] 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.

[1821] 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.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] 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.

[1826] The following is further disclosed regarding the above embodiment.

[1827] (Claim 1)

[1828] an input means for a user to input visual information;

[1829] a voice input means for a user to input voice data;

[1830] analysis means for analyzing data input from the input means and the voice input means;

[1831] generating means for generating an optimal solution based on the analyzed data;

[1832] a presentation means for presenting the generated solution to a user;

[1833] a feedback means for feeding back the results of implementing the proposed solution;

[1834] learning means for learning results received from said feedback means;

[1835] A system including:

[1836] (Claim 2)

[1837] The system of claim 1 , further comprising image analysis means for analyzing said visual information.

[1838] (Claim 3)

[1839] 10. The system of claim 1, further comprising a speech recognition means for converting said speech data into text data.

[1840] "Example 1"

[1841] (Claim 1)

[1842] an input means for a user to input visual information;

[1843] a voice input means for a user to input voice data;

[1844] a terminal that combines the data input from the input means and the voice input means into one data set and transmits the data set as an HTTP request;

[1845] analysis means for receiving the data set and analyzing the visual information using image analysis means;

[1846] analysis means for converting voice data into text data using voice recognition means;

[1847] generating means for generating an optimal solution based on the analyzed visual and audio data;

[1848] a presentation means for converting the generated solution into a format that is easy for a user to understand and presenting the solution;

[1849] a feedback means for feeding back the results of implementing the proposed solution;

[1850] a learning means for learning the results received from the feedback means and updating the generative AI model;

[1851] A system including:

[1852] (Claim 2)

[1853] The system of claim 1 , further comprising image analysis means for analyzing said visual information.

[1854] (Claim 3)

[1855] 10. The system of claim 1, further comprising a speech recognition means for converting said speech data into text data.

[1856] "Application Example 1"

[1857] (Claim 1)

[1858] an input means for a user to input visual information;

[1859] a voice input means for a user to input voice data;

[1860] analysis means for analyzing data input from the input means and the voice input means;

[1861] generating means for generating an optimal solution based on the analyzed data;

[1862] a presentation means for presenting the generated solution to a user;

[1863] a feedback means for feeding back the results of implementing the proposed solution;

[1864] learning means for learning results received from said feedback means;

[1865] image analysis means for extracting product features using images;

[1866] a speech recognition means for converting speech data into text data;

[1867] A means for analyzing the text data using natural language processing means to understand the user's question;

[1868] a means for presenting generated solutions related to the product to the user using the generative AI model;

[1869] A system including:

[1870] (Claim 2)

[1871] The system of claim 1 , further comprising image analysis means for analyzing product characteristics using the visual information.

[1872] (Claim 3)

[1873] 10. The system of claim 1, further comprising a speech recognition means for converting said speech data into text data.

[1874] "Example 2: Combining Emotion Engines"

[1875] (Claim 1)

[1876] an image input means for a user to input visual information;

[1877] a voice input means for a user to input voice data;

[1878] a data set generating means for combining data input from the image input means and the voice input means into one data set;

[1879] a data transmission means for transmitting the data set to a server;

[1880] analysis means for analyzing the data set at the server;

[1881] emotion recognition means for recognizing an emotion of a user based on the data analyzed by the analysis means;

[1882] generating means for generating an optimal solution taking into account the results of the emotion recognition means;

[1883] a presentation means for presenting the generated solution to a user;

[1884] a feedback means for feeding back the results of implementing the proposed solution;

[1885] learning means for learning results received from said feedback means;

[1886] A system including:

[1887] (Claim 2)

[1888] The system of claim 1 , further comprising image analysis means for analyzing said visual information.

[1889] (Claim 3)

[1890] 10. The system of claim 1, further comprising a speech recognition means for converting said speech data into text data.

[1891] "Application example 2 when combining emotion engines"

[1892] (Claim 1)

[1893] an input means for a user to input visual information;

[1894] a voice input means for a user to input voice data;

[1895] analysis means for analyzing data input from the input means and the voice input means;

[1896] generating means for generating an optimal solution based on the analyzed data;

[1897] a presentation means for presenting the generated solution to a user;

[1898] a feedback means for feeding back the results of implementing the proposed solution;

[1899] learning means for learning results received from said feedback means;

[1900] an emotion recognition means for recognizing an emotion of a user;

[1901] an adjustment means for adjusting a solution based on the output of the emotion recognition means;

[1902] A system including:

[1903] (Claim 2)

[1904] The system of claim 1 , further comprising image analysis means for analyzing said visual information.

[1905] (Claim 3)

[1906] 10. The system of claim 1, further comprising a speech recognition means for converting said speech data into text data. [Explanation of symbols]

[1907] 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. an input means for a user to input visual information; a voice input means for a user to input voice data; analysis means for analyzing data input from the input means and the voice input means; generating means for generating an optimal solution based on the analyzed data; a presentation means for presenting the generated solution to a user; a feedback means for feeding back the results of implementing the proposed solution; learning means for learning results received from said feedback means; A system including:

2. The system of claim 1 further comprising image analysis means for analyzing said visual information.

3. 2. The system of claim 1, further comprising speech recognition means for converting said speech data into text data.

Images