System

Abstract

An object of a system according to an embodiment is to identify a problem from a moving image captured by a user and propose an appropriate solution.SOLUTION: A system includes a moving image capturing part, an analysis part, a problem point specification part, a solution proposal part, and a display part. The moving image capturing unit captures a moving image captured by a user. The analysis unit analyzes the moving image captured by the moving image capturing unit. The problem specifying unit specifies a problem from the moving image analyzed by the analysis unit. The solution proposal unit proposes a solution based on the problem identified by the problem identification unit. The display unit displays the solution proposed by the solution proposal unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to identify problems from videos taken by users and propose appropriate solutions.

[0005] The system according to the embodiment aims to identify problems from videos taken by users and propose appropriate solutions. [Means for solving the problem]

[0006] The system according to the embodiment includes a video capture unit, an analysis unit, a problem identification unit, a solution proposal unit, and a display unit. The video capture unit captures video captured by a user. The analysis unit analyzes the video captured by the video capture unit. The problem identification unit identifies problems from the video analyzed by the analysis unit. The solution proposal unit proposes solutions based on the problems identified by the problem identification unit. The display unit displays the solutions proposed by the solution proposal unit. [Effects of the Invention]

[0007] The system according to the embodiment can identify problems from videos taken by users and propose appropriate solutions. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The application according to the embodiment of the present invention automatically imports videos taken by users, analyzes them using a generative AI, identifies problems, and proposes solutions, allowing the application to provide prompt and appropriate solutions based on the videos taken by the users.

[0029] The application according to the embodiment includes a video capture unit, an analysis unit, a problem identification unit, a solution proposal unit, and a display unit. The video capture unit captures videos captured by a user. For example, videos captured with a smartphone are uploaded to the app. Videos captured by a drone can also be captured. Furthermore, the video capture unit can stream videos in real time. For example, videos are captured in real time using a smartphone camera and sent to the analysis unit. The analysis unit uses a generation AI to analyze the captured videos. For example, the generation AI extracts important information from the videos using a text generation AI (e.g., LLM). The generation AI can also analyze the content of the videos using a multimodal generation AI. The generation AI can also recognize objects and actions in the videos using image analysis technology. For example, the text generation AI has learned large amounts of video data and has advanced analytical capabilities. The multimodal generation AI can handle multiple modalities, such as audio and text, in addition to videos. The generation AI uses image analysis technology to recognize objects and actions in the videos and perform analysis based on the recognition. The problem identification unit allows the generating AI to identify problems from the video analyzed by the analysis unit. For example, the generating AI detects cracks and damaged areas in a building. The generating AI can also detect diseases in agricultural crops. The generating AI can also detect abnormal behavior or conditions in the video. For example, the generating AI detects cracks in a building and identifies their location and size. When detecting diseases in agricultural crops, the generating AI detects abnormalities in the color and shape of the leaves and identifies the type of disease. The solution proposal unit allows the generating AI to propose solutions based on the problems identified by the problem identification unit. For example, the generating AI proposes methods for repairing buildings and materials to use. The generating AI can also propose appropriate pesticides and countermeasures for agricultural crop diseases. The generating AI can also propose multiple solutions to problems. For example, as a method for repairing a building, the generating AI proposes methods for repairing the repaired areas and a list of materials to use. For agricultural crop diseases, the generating AI proposes appropriate pesticides and countermeasures and explains how to use them. The display unit displays the solutions proposed by the solution proposal unit to the user.For example, the app may display a list of repair methods and materials to be used. It may also display methods for preventing crop diseases and a list of pesticides to be used. The display unit may also display detailed explanations and procedures for solutions. For example, the application may display step-by-step repair procedures so that the user can actually try them out. This allows the application according to the embodiment to provide quick and appropriate solutions based on videos taken by the user. For example, the application may identify areas of a building that need repair based on videos taken by the user and suggest appropriate repair methods, thereby enabling efficient repair work. Furthermore, early detection of crop diseases and the implementation of appropriate countermeasures can help maintain the health of crops.

[0030] The video capture unit uses the generation AI to evaluate video quality in real time when capturing videos and provide shooting advice to obtain optimal analysis results. For example, when capturing videos, the generation AI evaluates video quality such as resolution, brightness, and camera shake in real time and advises the user on optimal shooting conditions. For example, it may instruct the user to adjust the lighting or camera angle. The generation AI also evaluates audio quality while capturing videos and recommends re-capturing in a quieter environment if there is a lot of noise. For example, it may advise repositioning the microphone if there is a lot of wind or background noise. The generation AI also evaluates frame rate and bit rate in real time when capturing videos and instructs the user to adjust settings to obtain optimal analysis results. For example, it may advise increasing the frame rate in scenes with a lot of movement. This improves video quality and obtains optimal analysis results.

[0031] The analysis unit can integrate videos from multiple perspectives and extract more detailed information. For example, the generation AI integrates videos taken with multiple cameras and combines information from different perspectives for analysis. For example, it integrates videos of a building's exterior and interior to understand its overall condition. The generation AI also integrates videos from different devices, such as drones and fixed cameras, to perform detailed analysis. For example, it combines aerial footage of crops with footage from the ground to identify the extent of disease. The generation AI also integrates videos taken at different times of the day to analyze changes over time. For example, it can check whether cracks in a building are spreading over time. This enables information from multiple perspectives to be integrated and analyzed in detail.

[0032] The analysis unit can simultaneously analyze audio data when capturing video and use information obtained from the audio as a complement. For example, the generation AI analyzes audio data when capturing video and uses information obtained from the audio as a complement. For example, it analyzes audio information related to the sound of cracks in buildings and crop diseases. The generation AI also analyzes the audio data and converts what people say in the video into text. For example, it saves explanations of repairs on buildings and comments about crop diseases as text data. The generation AI also analyzes the audio data and uses information obtained from environmental and background sounds as a complement. For example, it analyzes information related to the environment, such as the sound of wind and birds singing. This allows more detailed information to be obtained by analyzing the audio data.

[0033] The analysis unit can integrate the results of video analysis with other sensor data (e.g., temperature and humidity sensors) to perform more accurate analysis. For example, the analysis unit can integrate the results of video analysis with temperature sensor data to analyze temperature changes in buildings and temperature stress on crops. For example, it can identify cracks and the occurrence of disease in high-temperature areas. The generation AI can also integrate humidity sensor data with the results of video analysis to analyze the impact of humidity changes. For example, it can identify building deterioration and crop disease in high-humidity environments. The generation AI can also integrate other sensor data (e.g., vibration and light sensors) with the results of video analysis to perform more accurate analysis. For example, it can identify damage to buildings in areas with a lot of vibration or crop disease caused by the amount of light it receives. In this way, the integration of sensor data improves the accuracy of the analysis.

[0034] When the generation AI identifies problems, the problem identification unit can refer to similar past cases to identify problems with greater accuracy. For example, the generation AI searches a database for similar past cases and compares them with the current video. For example, it identifies problems by referring to past cases of cracks in buildings or past cases of disease in crops. The generation AI also improves the accuracy of problem identification based on similar past cases. For example, it learns from past data and recognizes patterns of cracks and disease. The generation AI also refers to similar past cases and extracts features that are useful for identifying problems. For example, it identifies problems based on the shape of a specific crack or the color change of disease. In this way, by referring to similar past cases, the accuracy of problem identification is improved.

[0035] The problem identification unit allows the generation AI to identify problems according to the environment by taking into account different environmental conditions (e.g., day / night and weather) when identifying problems. For example, the generation AI can analyze videos taken at night or in the rain to identify problems according to the environment. The generation AI also improves the accuracy of problem identification based on different environmental conditions. For example, it can analyze how cracks look differently during the day and night, or how disease progresses. The generation AI also analyzes environmental conditions in real time to identify problems. For example, it can identify problems by taking into account changes in weather and the effects of time of day. This makes it possible to identify problems according to the environment by taking into account different environmental conditions.

[0036] When the generation AI identifies a problem, the problem identification unit can refer to other data sources (e.g., geographic information or historical data) to identify the problem from a broader perspective. For example, the generation AI refers to geographic information to identify a problem. For example, it identifies a problem based on the location information of a building or the growing area of ​​agricultural crops. The generation AI also improves the accuracy of problem identification based on historical data. For example, it identifies damaged areas of a building by referring to the history of past earthquakes and floods. The generation AI also refers to other data sources (e.g., weather data or soil data) to identify problems. For example, it identifies crop diseases based on weather conditions and soil conditions. In this way, by referring to other data sources, problems can be identified from a broader perspective.

[0037] When the generation AI proposes a solution, the solution proposal unit can refer to past success stories and propose the most effective solution. For example, the generation AI searches a database of past success stories and proposes the optimal solution to the current problem. For example, it refers to past cases of building repairs or cases of crop disease control. The generation AI also predicts the effectiveness of solutions based on past success stories and proposes the most effective solution. For example, it learns from past data and predicts the effectiveness of repair methods or pesticides. The generation AI also refers to past success stories and extracts features that are useful for proposing solutions. For example, it proposes solutions based on specific repair methods or pesticide use conditions. In this way, effective solutions can be proposed by referring to past success stories.

[0038] When the generation AI proposes a solution, the solution proposal unit can simulate multiple solutions and select the optimal solution. For example, the generation AI simulates multiple solutions and compares their effectiveness. For example, it simulates different repair methods or pesticide application methods and selects the optimal solution. The generation AI also proposes the optimal solution based on the simulation results. For example, it compares the costs and effectiveness of repair methods and proposes the most effective method. The generation AI also performs simulations in real time and presents the optimal solution to the user. For example, it performs simulations under different conditions and selects the optimal solution. In this way, the optimal solution can be selected by simulating multiple solutions.

[0039] The solution proposal unit allows the generative AI to integrate knowledge from different fields when proposing a solution and propose innovative solutions. For example, the solution proposal unit allows the generative AI to integrate knowledge from different fields and propose innovative solutions. For example, it can combine knowledge from the fields of architecture and agriculture to propose new repair methods or disease prevention measures. The generative AI can also propose new solutions based on data from different fields. For example, it can propose how to apply medical technology to building repairs. The generative AI can also incorporate the opinions of experts from different fields to propose innovative solutions. For example, it can integrate the knowledge of architectural engineers and agricultural experts to propose new solutions. This makes it possible to propose innovative solutions by integrating knowledge from different fields.

[0040] When the generation AI proposes a solution, the solution proposal unit can refer to the user's past behavioral history and customize the optimal solution for the user. For example, the generation AI analyzes the user's past behavioral history and proposes the optimal solution. For example, the solution is customized based on the effects of repair methods or pesticides used in the past. The generation AI also personalizes the solution proposal based on the user's behavioral history. For example, it prioritizes suggesting repair methods or pesticides that the user prefers. The generation AI also refers to the user's past behavioral data and proposes the optimal solution. For example, it customizes the solution based on past successes and failures. In this way, the optimal solution can be customized by referring to the user's past behavioral history.

[0041] When displaying the proposed content, the generating AI can incorporate interactive elements to allow the user to try out the proposed content. For example, the display unit can incorporate interactive elements to allow the user to try out the proposed content. For example, the generating AI can simulate a repair method or try out a method of using pesticides. The display unit also provides an interface that allows the user to try out the proposed content. For example, the procedure for a repair method can be displayed step by step, allowing the user to actually try it out. The generating AI can also incorporate interactive elements to allow the user to try out the proposed content. For example, the method of using pesticides can be simulated to confirm the effects. This allows the user to try out the proposed content, thereby deepening their understanding.

[0042] When displaying the proposed content, the display unit allows the generation AI to work with other devices (e.g., a smartwatch or AR glasses) to realize multi-device display. For example, the generation AI works with a smartwatch or AR glasses to display the proposed content on multiple devices. For example, the repair procedure is checked on the smartwatch while the work is performed. The generation AI also works with other devices to display the proposed content. For example, AR glasses are used to visually check the areas of the building that need repair. The generation AI also realizes multi-device display, allowing the user to check the proposed content on various devices. For example, the proposed content is displayed on a smartphone or tablet. This realizes multi-device display, allowing the user to check the proposed content on various devices.

[0043] When displaying the proposed content, the generation AI can refer to the user's past feedback and customize the optimal display method for the user. In the display unit, for example, the generation AI analyzes the user's past feedback and suggests the optimal display method. For example, the display method is customized based on the user's preferred display format and amount of information. The generation AI also adjusts the display method based on the user's feedback. For example, if the user requests more detailed information, it provides additional explanations and illustrations. The generation AI also refers to the user's past feedback and suggests the optimal display method. For example, it provides information in a format that is easy for the user to understand. In this way, the optimal display method can be customized by referring to the user's past feedback.

[0044] The feedback collection unit allows the generation AI to analyze the user's behavioral data when collecting feedback and evaluate the reliability of the feedback. In the feedback collection unit, for example, the generation AI analyzes the user's behavioral data and evaluates the reliability of the feedback. For example, it checks whether the user actually implemented the proposed solution. The generation AI also evaluates the reliability of the feedback based on the user's behavioral data. For example, it analyzes the results of the user implementing the proposed solution. The generation AI also refers to the user's behavioral data and evaluates the reliability of the feedback. For example, it evaluates the reliability of the feedback based on the results after the user implemented the proposed solution. In this way, the reliability of the feedback can be evaluated by analyzing the user's behavioral data.

[0045] The feedback collection unit allows the generation AI to automatically categorize the user's feedback content when collecting feedback and organize the data in a format that is easy to analyze. For example, the feedback collection unit allows the generation AI to automatically categorize the user's feedback content and organize the data in a format that is easy to analyze. For example, positive feedback and negative feedback are stored separately. The generation AI also automatically sets categories based on the feedback content and organizes the data. For example, feedback about repair methods is classified separately from feedback about pesticide use. The generation AI also analyzes the feedback content, extracts important information, and organizes the data. For example, it automatically extracts the effects and problems of solutions proposed by the user. In this way, by automatically categorizing the feedback content, the data can be organized in a format that is easy to analyze.

[0046] The feedback collection unit allows the generation AI to compare the feedback collected with that of other users and identify common problems and areas for improvement. For example, the feedback collection unit allows the generation AI to compare the feedback collected with that of other users and identify common problems and areas for improvement. For example, if multiple users point out the same problem, it prioritizes improving that problem. The generation AI also identifies common problems and areas for improvement based on the feedback content. For example, if multiple users provide feedback on the same repair method, it improves that method. The generation AI also analyzes the feedback of other users and identifies common problems and areas for improvement. For example, if multiple users provide feedback on the effectiveness of the same pesticide, it improves the method of using that pesticide. In this way, by comparing with the feedback of other users, it is possible to identify common problems and areas for improvement.

[0047] The feedback collection unit allows the generation AI to accept different feedback formats (e.g., audio and images) when collecting feedback, thereby collecting multimodal feedback. In the feedback collection unit, for example, the generation AI analyzes audio feedback, converts it into text data, and saves it. For example, it automatically converts audio feedback provided by the user into text. The generation AI also analyzes image feedback, extracts important information, and organizes the data. For example, it analyzes images of repair areas provided by the user and identifies problems. The generation AI also collects multimodal feedback and organizes the data in a format that is easy to analyze. For example, it integrates and saves audio, image, and text feedback. This allows multimodal feedback to be collected by accepting different feedback formats.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The analysis unit can simultaneously analyze audio data when capturing video and use information obtained from the audio as a complement. For example, the generation AI analyzes audio data when capturing video and uses information obtained from the audio as a complement. For example, it analyzes audio information related to the sound of cracks in buildings and crop diseases. The generation AI also analyzes the audio data and converts what people say in the video into text. For example, it saves explanations of repairs on buildings and comments about crop diseases as text data. The generation AI also analyzes the audio data and uses information obtained from environmental and background sounds as a complement. For example, it analyzes information related to the environment, such as the sound of wind and birds singing. This allows more detailed information to be obtained by analyzing the audio data.

[0050] The analysis unit can integrate the results of video analysis with other sensor data (e.g., temperature and humidity sensors) to perform more accurate analysis. For example, the analysis unit can integrate the results of video analysis with temperature sensor data to analyze temperature changes in buildings and temperature stress on crops. For example, it can identify cracks and the occurrence of disease in high-temperature areas. The generation AI can also integrate humidity sensor data with the results of video analysis to analyze the impact of humidity changes. For example, it can identify building deterioration and crop disease in high-humidity environments. The generation AI can also integrate other sensor data (e.g., vibration and light sensors) with the results of video analysis to perform more accurate analysis. For example, it can identify damage to buildings in areas with a lot of vibration or crop disease caused by the amount of light it receives. In this way, the integration of sensor data improves the accuracy of the analysis.

[0051] When the generation AI identifies problems, the problem identification unit can refer to similar past cases to identify problems with greater accuracy. For example, the generation AI searches a database for similar past cases and compares them with the current video. For example, it identifies problems by referring to past cases of cracks in buildings or past cases of disease in crops. The generation AI also improves the accuracy of problem identification based on similar past cases. For example, it learns from past data and recognizes patterns of cracks and disease. The generation AI also refers to similar past cases and extracts features that are useful for identifying problems. For example, it identifies problems based on the shape of a specific crack or the color change of disease. In this way, by referring to similar past cases, the accuracy of problem identification is improved.

[0052] When the generation AI proposes a solution, the solution proposal unit can refer to past success stories and propose the most effective solution. For example, the generation AI searches a database of past success stories and proposes the optimal solution to the current problem. For example, it refers to past cases of building repairs or cases of crop disease control. The generation AI also predicts the effectiveness of solutions based on past success stories and proposes the most effective solution. For example, it learns from past data and predicts the effectiveness of repair methods or pesticides. The generation AI also refers to past success stories and extracts features that are useful for proposing solutions. For example, it proposes solutions based on specific repair methods or pesticide use conditions. In this way, effective solutions can be proposed by referring to past success stories.

[0053] When the generation AI proposes a solution, the solution proposal unit can simulate multiple solutions and select the optimal solution. For example, the generation AI simulates multiple solutions and compares their effectiveness. For example, it simulates different repair methods or pesticide application methods and selects the optimal solution. The generation AI also proposes the optimal solution based on the simulation results. For example, it compares the costs and effectiveness of repair methods and proposes the most effective method. The generation AI also performs simulations in real time and presents the optimal solution to the user. For example, it performs simulations under different conditions and selects the optimal solution. In this way, the optimal solution can be selected by simulating multiple solutions.

[0054] When displaying the proposed content, the generating AI can incorporate interactive elements to allow the user to try out the proposed content. For example, the display unit can incorporate interactive elements to allow the user to try out the proposed content. For example, the generating AI can simulate a repair method or try out a method of using pesticides. The display unit also provides an interface that allows the user to try out the proposed content. For example, the procedure for a repair method can be displayed step by step, allowing the user to actually try it out. The generating AI can also incorporate interactive elements to allow the user to try out the proposed content. For example, the method of using pesticides can be simulated to confirm the effects. This allows the user to try out the proposed content, thereby deepening their understanding.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The video capture unit captures videos taken by the user. For example, videos taken with a smartphone can be uploaded to the app. Videos taken by drones can also be captured. The video capture unit can also stream videos in real time. For example, videos can be captured in real time using a smartphone camera and sent to the analysis unit. Step 2: In the analysis unit, the generation AI analyzes the captured video. For example, the generation AI uses text generation AI (e.g., LLM) to extract important information from the video. The generation AI can also use multimodal generation AI to analyze the content of the video. The generation AI can also use image analysis technology to recognize objects and actions in the video. For example, text generation AI has learned from large amounts of video data and has advanced analytical capabilities. Multimodal generation AI can handle multiple modalities, including not only video but also audio and text. The generation AI uses image analysis technology to recognize objects and actions in the video and perform analysis based on that. Step 3: In the problem identification section, the generation AI identifies problems from the video analyzed by the analysis section. For example, the generation AI detects cracks and damaged areas in a building. The generation AI can also detect diseases in agricultural crops. The generation AI can also detect abnormal behavior or conditions within the video. For example, the generation AI detects cracks in a building and identifies their location and size. When detecting diseases in agricultural crops, the generation AI detects abnormalities in the color and shape of the leaves and identifies the type of disease. Step 4: In the solution proposal section, the generation AI proposes solutions based on the problems identified by the problem identification section. For example, the generation AI proposes methods for repairing buildings and the materials to be used. The generation AI can also propose appropriate pesticides and countermeasures for crop diseases. The generation AI can also propose multiple solutions to a problem. For example, as a method for repairing a building, the generation AI proposes how to repair the repair area and a list of materials to be used. For crop diseases, the generation AI proposes appropriate pesticides and countermeasures and explains how to use them. Step 5: The display unit displays the solutions proposed by the solution proposal unit to the user. For example, the display unit may display a list of repair methods and materials to be used within the app. It may also display methods for preventing crop diseases and a list of pesticides to be used. The display unit may also display detailed explanations and procedures for the solutions. For example, the display unit may display step-by-step procedures for repair methods so that the user can actually try them out.

[0057] (Example 2) The application according to the embodiment of the present invention automatically imports videos taken by users, analyzes them using a generative AI, identifies problems, and proposes solutions, allowing the application to provide prompt and appropriate solutions based on the videos taken by the users.

[0058] The application according to the embodiment includes a video capture unit, an analysis unit, a problem identification unit, a solution proposal unit, and a display unit. The video capture unit captures videos captured by a user. For example, videos captured with a smartphone are uploaded to the app. Videos captured by a drone can also be captured. Furthermore, the video capture unit can stream videos in real time. For example, videos are captured in real time using a smartphone camera and sent to the analysis unit. The analysis unit uses a generation AI to analyze the captured videos. For example, the generation AI extracts important information from the videos using a text generation AI (e.g., LLM). The generation AI can also analyze the content of the videos using a multimodal generation AI. The generation AI can also recognize objects and actions in the videos using image analysis technology. For example, the text generation AI has learned large amounts of video data and has advanced analytical capabilities. The multimodal generation AI can handle multiple modalities, such as audio and text, in addition to videos. The generation AI uses image analysis technology to recognize objects and actions in the videos and perform analysis based on the recognition. The problem identification unit allows the generating AI to identify problems from the video analyzed by the analysis unit. For example, the generating AI detects cracks and damaged areas in a building. The generating AI can also detect diseases in agricultural crops. The generating AI can also detect abnormal behavior or conditions in the video. For example, the generating AI detects cracks in a building and identifies their location and size. When detecting diseases in agricultural crops, the generating AI detects abnormalities in the color and shape of the leaves and identifies the type of disease. The solution proposal unit allows the generating AI to propose solutions based on the problems identified by the problem identification unit. For example, the generating AI proposes methods for repairing buildings and materials to use. The generating AI can also propose appropriate pesticides and countermeasures for agricultural crop diseases. The generating AI can also propose multiple solutions to problems. For example, as a method for repairing a building, the generating AI proposes methods for repairing the repaired areas and a list of materials to use. For agricultural crop diseases, the generating AI proposes appropriate pesticides and countermeasures and explains how to use them. The display unit displays the solutions proposed by the solution proposal unit to the user.For example, the app may display a list of repair methods and materials to be used. It may also display methods for preventing crop diseases and a list of pesticides to be used. The display unit may also display detailed explanations and procedures for solutions. For example, the application may display step-by-step repair procedures so that the user can actually try them out. This allows the application according to the embodiment to provide quick and appropriate solutions based on videos taken by the user. For example, the application may identify areas of a building that need repair based on videos taken by the user and suggest appropriate repair methods, thereby enabling efficient repair work. Furthermore, early detection of crop diseases and the implementation of appropriate countermeasures can help maintain the health of crops.

[0059] The video capture unit uses the generation AI to evaluate video quality in real time when capturing videos and provide shooting advice to obtain optimal analysis results. For example, when capturing videos, the generation AI evaluates video quality such as resolution, brightness, and camera shake in real time and advises the user on optimal shooting conditions. For example, it may instruct the user to adjust the lighting or camera angle. The generation AI also evaluates audio quality while capturing videos and recommends re-capturing in a quieter environment if there is a lot of noise. For example, it may advise repositioning the microphone if there is a lot of wind or background noise. The generation AI also evaluates frame rate and bit rate in real time when capturing videos and instructs the user to adjust settings to obtain optimal analysis results. For example, it may advise increasing the frame rate in scenes with a lot of movement. This improves video quality and obtains optimal analysis results.

[0060] The analysis unit can integrate videos from multiple perspectives and extract more detailed information. For example, the generation AI integrates videos taken with multiple cameras and combines information from different perspectives for analysis. For example, it integrates videos of a building's exterior and interior to understand its overall condition. The generation AI also integrates videos from different devices, such as drones and fixed cameras, to perform detailed analysis. For example, it combines aerial footage of crops with footage from the ground to identify the extent of disease. The generation AI also integrates videos taken at different times of the day to analyze changes over time. For example, it can check whether cracks in a building are spreading over time. This enables information from multiple perspectives to be integrated and analyzed in detail.

[0061] The analysis unit uses the emotion estimation function to analyze the emotions of people in the video and can prioritize problems based on those emotions. For example, the generation AI analyzes the facial expressions and voices of people in the video and calculates an emotion score. For example, if stress or anxiety is high, it will prioritize analyzing those problems. The generation AI also monitors the emotional changes of people in the video in real time and focuses on analyzing parts where emotions fluctuate greatly. For example, it prioritizes analysis of scenes where expressions of surprise or anger are seen. The generation AI also uses the emotion estimation function to identify the problems that people in the video are most concerned about and prioritizes proposing solutions to those problems. For example, it will focus analysis on scenes where sad expressions are prevalent. This allows the system to prioritize problems based on emotion, allowing it to prioritize analysis of important problems.

[0062] The analysis unit can simultaneously analyze audio data when capturing video and use information obtained from the audio as a complement. For example, the generation AI analyzes audio data when capturing video and uses information obtained from the audio as a complement. For example, it analyzes audio information related to the sound of cracks in buildings and crop diseases. The generation AI also analyzes the audio data and converts what people say in the video into text. For example, it saves explanations of repairs on buildings and comments about crop diseases as text data. The generation AI also analyzes the audio data and uses information obtained from environmental and background sounds as a complement. For example, it analyzes information related to the environment, such as the sound of wind and birds singing. This allows more detailed information to be obtained by analyzing the audio data.

[0063] The analysis unit can integrate the results of video analysis with other sensor data (e.g., temperature and humidity sensors) to perform more accurate analysis. For example, the analysis unit can integrate the results of video analysis with temperature sensor data to analyze temperature changes in buildings and temperature stress on crops. For example, it can identify cracks and the occurrence of disease in high-temperature areas. The generation AI can also integrate humidity sensor data with the results of video analysis to analyze the impact of humidity changes. For example, it can identify building deterioration and crop disease in high-humidity environments. The generation AI can also integrate other sensor data (e.g., vibration and light sensors) with the results of video analysis to perform more accurate analysis. For example, it can identify damage to buildings in areas with a lot of vibration or crop disease caused by the amount of light it receives. In this way, the integration of sensor data improves the accuracy of the analysis.

[0064] The analysis unit uses the emotion estimation function to analyze the emotions of the user who shot the video and can adjust the presentation method of the analysis results according to the user's emotions. For example, the generation AI analyzes the facial expressions and voice of the user who shot the video and calculates an emotion score. For example, if the user is feeling stressed, the analysis results are presented concisely. The generation AI also adjusts the presentation method of the analysis results according to the user's emotions. For example, if the user is feeling anxious, detailed explanations and support information are added. The generation AI also uses the emotion estimation function to select the presentation method of the analysis results based on the user's emotions. For example, if the user is feeling positive, the analysis results are presented in a positive tone. This makes it possible to present analysis results according to the user's emotions.

[0065] When the generation AI identifies problems, the problem identification unit can refer to similar past cases to identify problems with greater accuracy. For example, the generation AI searches a database for similar past cases and compares them with the current video. For example, it identifies problems by referring to past cases of cracks in buildings or past cases of disease in crops. The generation AI also improves the accuracy of problem identification based on similar past cases. For example, it learns from past data and recognizes patterns of cracks and disease. The generation AI also refers to similar past cases and extracts features that are useful for identifying problems. For example, it identifies problems based on the shape of a specific crack or the color change of disease. In this way, by referring to similar past cases, the accuracy of problem identification is improved.

[0066] The problem identification unit can use the emotion estimation function to analyze emotional changes of people in the video and prioritize identifying emotionally significant problems. In the problem identification unit, for example, the generation AI analyzes emotional changes of people in the video and identifies emotionally significant problems. For example, it prioritizes analyzing scenes in which people feel surprised or anxious. The generation AI also uses the emotion estimation function to monitor emotional changes of people in the video in real time and identify emotionally significant problems. For example, it focuses on analyzing scenes in which people show strong emotions. The generation AI also prioritizes identifying emotionally significant problems based on the emotion estimation data. For example, it prioritizes analyzing scenes in which people feel sadness or anger. This prioritizes identifying emotionally significant problems, making it possible to perform analysis that meets the user's interests.

[0067] The problem identification unit allows the generation AI to identify problems according to the environment by taking into account different environmental conditions (e.g., day / night and weather) when identifying problems. For example, the generation AI can analyze videos taken at night or in the rain to identify problems according to the environment. The generation AI also improves the accuracy of problem identification based on different environmental conditions. For example, it can analyze how cracks look differently during the day and night, or how disease progresses. The generation AI also analyzes environmental conditions in real time to identify problems. For example, it can identify problems by taking into account changes in weather and the effects of time of day. This makes it possible to identify problems according to the environment by taking into account different environmental conditions.

[0068] When the generation AI identifies a problem, the problem identification unit can refer to other data sources (e.g., geographic information or historical data) to identify the problem from a broader perspective. For example, the generation AI refers to geographic information to identify a problem. For example, it identifies a problem based on the location information of a building or the growing area of ​​agricultural crops. The generation AI also improves the accuracy of problem identification based on historical data. For example, it identifies damaged areas of a building by referring to the history of past earthquakes and floods. The generation AI also refers to other data sources (e.g., weather data or soil data) to identify problems. For example, it identifies crop diseases based on weather conditions and soil conditions. In this way, by referring to other data sources, problems can be identified from a broader perspective.

[0069] The problem identification unit can use the emotion estimation function to identify the problems that the user is most interested in and prioritize suggesting solutions to those problems. In the problem identification unit, for example, the generation AI analyzes the user's emotion data to identify the problems that the user is most interested in. For example, it prioritizes analyzing scenes in which the user shows strong interest. The generation AI also uses the emotion estimation function to identify problems based on the user's emotions and prioritize suggesting solutions to those problems. For example, it focuses on analyzing problems that make the user feel anxious. The generation AI also identifies the problems that the user is most interested in based on the emotion data and prioritizes suggesting solutions to those problems. For example, it focuses on analyzing scenes in which the user shows surprise or interest. This makes it possible to identify problems that match the user's interests and prioritize suggesting solutions.

[0070] When the generation AI proposes a solution, the solution proposal unit can refer to past success stories and propose the most effective solution. For example, the generation AI searches a database of past success stories and proposes the optimal solution to the current problem. For example, it refers to past cases of building repairs or cases of crop disease control. The generation AI also predicts the effectiveness of solutions based on past success stories and proposes the most effective solution. For example, it learns from past data and predicts the effectiveness of repair methods or pesticides. The generation AI also refers to past success stories and extracts features that are useful for proposing solutions. For example, it proposes solutions based on specific repair methods or pesticide use conditions. In this way, effective solutions can be proposed by referring to past success stories.

[0071] When the generation AI proposes a solution, the solution proposal unit can simulate multiple solutions and select the optimal solution. For example, the generation AI simulates multiple solutions and compares their effectiveness. For example, it simulates different repair methods or pesticide application methods and selects the optimal solution. The generation AI also proposes the optimal solution based on the simulation results. For example, it compares the costs and effectiveness of repair methods and proposes the most effective method. The generation AI also performs simulations in real time and presents the optimal solution to the user. For example, it performs simulations under different conditions and selects the optimal solution. In this way, the optimal solution can be selected by simulating multiple solutions.

[0072] The solution proposal unit uses the emotion estimation function to propose solutions according to the user's emotions, and can provide solutions that are easy for the user to accept. In the solution proposal unit, for example, the generation AI analyzes the user's emotion data and proposes solutions according to the emotions. For example, if the user is feeling anxious, it proposes a solution that gives the user a sense of security. The generation AI also uses the emotion estimation function to propose solutions based on the user's emotions. For example, if the user is feeling positive, it proposes a positive solution. The generation AI also provides solutions that are easy for the user to accept based on the emotion data. For example, if the user is feeling stressed, it proposes a simple and effective solution. In this way, by proposing solutions according to the user's emotions, it is possible to provide solutions that are easy for the user to accept.

[0073] The solution proposal unit allows the generative AI to integrate knowledge from different fields when proposing a solution and propose innovative solutions. For example, the solution proposal unit allows the generative AI to integrate knowledge from different fields and propose innovative solutions. For example, it can combine knowledge from the fields of architecture and agriculture to propose new repair methods or disease prevention measures. The generative AI can also propose new solutions based on data from different fields. For example, it can propose how to apply medical technology to building repairs. The generative AI can also incorporate the opinions of experts from different fields to propose innovative solutions. For example, it can integrate the knowledge of architectural engineers and agricultural experts to propose new solutions. This makes it possible to propose innovative solutions by integrating knowledge from different fields.

[0074] When the generation AI proposes a solution, the solution proposal unit can refer to the user's past behavioral history and customize the optimal solution for the user. For example, the generation AI analyzes the user's past behavioral history and proposes the optimal solution. For example, the solution is customized based on the effects of repair methods or pesticides used in the past. The generation AI also personalizes the solution proposal based on the user's behavioral history. For example, it prioritizes suggesting repair methods or pesticides that the user prefers. The generation AI also refers to the user's past behavioral data and proposes the optimal solution. For example, it customizes the solution based on past successes and failures. In this way, the optimal solution can be customized by referring to the user's past behavioral history.

[0075] The solution proposal unit can use the emotion estimation function to monitor the user's emotional reactions in real time when proposing a solution and adjust the proposed content. In the solution proposal unit, for example, the generation AI monitors the user's emotional reactions in real time and adjusts the proposed content of the solution. For example, if the user is feeling anxious, a detailed explanation is added. The generation AI also uses the emotion estimation function to propose solutions according to the user's emotions. For example, if the user is feeling positive, a proactive solution is proposed. The generation AI also provides solutions according to the user's emotions based on the emotion data. For example, if the user is feeling stressed, a simple and effective solution is proposed. In this way, the proposed content can be adjusted by monitoring the user's emotional reactions in real time.

[0076] When displaying the proposed content, the generating AI can incorporate interactive elements to allow the user to try out the proposed content. For example, the display unit can incorporate interactive elements to allow the user to try out the proposed content. For example, the generating AI can simulate a repair method or try out a method of using pesticides. The display unit also provides an interface that allows the user to try out the proposed content. For example, the procedure for a repair method can be displayed step by step, allowing the user to actually try it out. The generating AI can also incorporate interactive elements to allow the user to try out the proposed content. For example, the method of using pesticides can be simulated to confirm the effects. This allows the user to try out the proposed content, thereby deepening their understanding.

[0077] The display unit uses the emotion estimation function to select a display method according to the user's emotions and can display the proposal content in a format that is most acceptable to the user. In the display unit, for example, the generation AI analyzes the user's emotion data and selects a display method according to the emotion. For example, if the user is feeling anxious, a display method that gives a sense of security is selected. The generation AI also uses the emotion estimation function to select a display method based on the user's emotions. For example, if the user is feeling positive, a positive display method is selected. The generation AI also displays the proposal content in a format that is most acceptable to the user based on the emotion data. For example, if the user is feeling stressed, a simple and easy-to-understand display method is selected. In this way, by selecting a display method according to the user's emotions, the proposal content can be displayed in a format that is most acceptable to the user.

[0078] When displaying the proposed content, the display unit allows the generation AI to work with other devices (e.g., a smartwatch or AR glasses) to realize multi-device display. For example, the generation AI works with a smartwatch or AR glasses to display the proposed content on multiple devices. For example, the repair procedure is checked on the smartwatch while the work is performed. The generation AI also works with other devices to display the proposed content. For example, AR glasses are used to visually check the areas of the building that need repair. The generation AI also realizes multi-device display, allowing the user to check the proposed content on various devices. For example, the proposed content is displayed on a smartphone or tablet. This realizes multi-device display, allowing the user to check the proposed content on various devices.

[0079] When displaying the proposed content, the generation AI can refer to the user's past feedback and customize the optimal display method for the user. In the display unit, for example, the generation AI analyzes the user's past feedback and suggests the optimal display method. For example, the display method is customized based on the user's preferred display format and amount of information. The generation AI also adjusts the display method based on the user's feedback. For example, if the user requests more detailed information, it provides additional explanations and illustrations. The generation AI also refers to the user's past feedback and suggests the optimal display method. For example, it provides information in a format that is easy for the user to understand. In this way, the optimal display method can be customized by referring to the user's past feedback.

[0080] The display unit can use the emotion estimation function to monitor the user's emotional reactions in real time when displaying suggested content and adjust the display content. For example, the generation AI in the display unit monitors the user's emotional reactions in real time and adjusts the display content. For example, if the user is feeling anxious, a detailed explanation is added. The generation AI also uses the emotion estimation function to provide display content according to the user's emotions. For example, if the user is feeling positive, it provides positive display content. The generation AI also provides display content according to the user's emotions based on the emotion data. For example, if the user is feeling stressed, it provides simple and easy-to-understand display content. In this way, the display content can be adjusted by monitoring the user's emotional reactions in real time.

[0081] The feedback collection unit allows the generation AI to analyze the user's behavioral data when collecting feedback and evaluate the reliability of the feedback. In the feedback collection unit, for example, the generation AI analyzes the user's behavioral data and evaluates the reliability of the feedback. For example, it checks whether the user actually implemented the proposed solution. The generation AI also evaluates the reliability of the feedback based on the user's behavioral data. For example, it analyzes the results of the user implementing the proposed solution. The generation AI also refers to the user's behavioral data and evaluates the reliability of the feedback. For example, it evaluates the reliability of the feedback based on the results after the user implemented the proposed solution. In this way, the reliability of the feedback can be evaluated by analyzing the user's behavioral data.

[0082] The feedback collection unit allows the generation AI to automatically categorize the user's feedback content when collecting feedback and organize the data in a format that is easy to analyze. For example, the feedback collection unit allows the generation AI to automatically categorize the user's feedback content and organize the data in a format that is easy to analyze. For example, positive feedback and negative feedback are stored separately. The generation AI also automatically sets categories based on the feedback content and organizes the data. For example, feedback about repair methods is classified separately from feedback about pesticide use. The generation AI also analyzes the feedback content, extracts important information, and organizes the data. For example, it automatically extracts the effects and problems of solutions proposed by the user. In this way, by automatically categorizing the feedback content, the data can be organized in a format that is easy to analyze.

[0083] The feedback collection unit uses the emotion estimation function to collect feedback based on the user's emotions and can make improvements that take emotional factors into consideration. In the feedback collection unit, for example, the generation AI analyzes the user's emotion data and collects emotion-based feedback. For example, if the user is feeling anxious, the generation AI collects feedback that takes that emotion into consideration. The generation AI also uses the emotion estimation function to collect feedback based on the user's emotions and makes improvements that take emotional factors into consideration. For example, if the user has positive emotions, the generation AI makes improvements that reflect those emotions. The generation AI also collects feedback according to the user's emotions based on the emotion data and makes improvements that take emotional factors into consideration. For example, if the user is feeling stressed, the generation AI makes improvements that take those emotions into consideration. In this way, by collecting feedback based on the user's emotions, improvements that take emotional factors into consideration are possible.

[0084] The feedback collection unit allows the generation AI to compare the feedback collected with that of other users and identify common problems and areas for improvement. For example, the feedback collection unit allows the generation AI to compare the feedback collected with that of other users and identify common problems and areas for improvement. For example, if multiple users point out the same problem, it prioritizes improving that problem. The generation AI also identifies common problems and areas for improvement based on the feedback content. For example, if multiple users provide feedback on the same repair method, it improves that method. The generation AI also analyzes the feedback of other users and identifies common problems and areas for improvement. For example, if multiple users provide feedback on the effectiveness of the same pesticide, it improves the method of using that pesticide. In this way, by comparing with the feedback of other users, it is possible to identify common problems and areas for improvement.

[0085] The feedback collection unit allows the generation AI to accept different feedback formats (e.g., audio and images) when collecting feedback, thereby collecting multimodal feedback. In the feedback collection unit, for example, the generation AI analyzes audio feedback, converts it into text data, and saves it. For example, it automatically converts audio feedback provided by the user into text. The generation AI also analyzes image feedback, extracts important information, and organizes the data. For example, it analyzes images of repair areas provided by the user and identifies problems. The generation AI also collects multimodal feedback and organizes the data in a format that is easy to analyze. For example, it integrates and saves audio, image, and text feedback. This allows multimodal feedback to be collected by accepting different feedback formats.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The analysis unit uses the emotion estimation function to analyze the emotions of people in the video and can prioritize problems based on those emotions. For example, the generation AI analyzes the facial expressions and voices of people in the video and calculates an emotion score. For example, if stress or anxiety is high, it will prioritize analyzing those problems. The generation AI also monitors the emotional changes of people in the video in real time and focuses on analyzing parts where emotions fluctuate greatly. For example, it prioritizes analysis of scenes where expressions of surprise or anger are seen. The generation AI also uses the emotion estimation function to identify the problems that people in the video are most concerned about and prioritizes proposing solutions to those problems. For example, it will focus analysis on scenes where sad expressions are prevalent. This allows the system to prioritize problems based on emotion, allowing it to prioritize analysis of important problems.

[0088] The analysis unit can simultaneously analyze audio data when capturing video and use information obtained from the audio as a complement. For example, the generation AI analyzes audio data when capturing video and uses information obtained from the audio as a complement. For example, it analyzes audio information related to the sound of cracks in buildings and crop diseases. The generation AI also analyzes the audio data and converts what people say in the video into text. For example, it saves explanations of repairs on buildings and comments about crop diseases as text data. The generation AI also analyzes the audio data and uses information obtained from environmental and background sounds as a complement. For example, it analyzes information related to the environment, such as the sound of wind and birds singing. This allows more detailed information to be obtained by analyzing the audio data.

[0089] The analysis unit can integrate the results of video analysis with other sensor data (e.g., temperature and humidity sensors) to perform more accurate analysis. For example, the analysis unit can integrate the results of video analysis with temperature sensor data to analyze temperature changes in buildings and temperature stress on crops. For example, it can identify cracks and the occurrence of disease in high-temperature areas. The generation AI can also integrate humidity sensor data with the results of video analysis to analyze the impact of humidity changes. For example, it can identify building deterioration and crop disease in high-humidity environments. The generation AI can also integrate other sensor data (e.g., vibration and light sensors) with the results of video analysis to perform more accurate analysis. For example, it can identify damage to buildings in areas with a lot of vibration or crop disease caused by the amount of light it receives. In this way, the integration of sensor data improves the accuracy of the analysis.

[0090] The analysis unit uses the emotion estimation function to analyze the emotions of the user who shot the video and can adjust the presentation method of the analysis results according to the user's emotions. For example, the generation AI analyzes the facial expressions and voice of the user who shot the video and calculates an emotion score. For example, if the user is feeling stressed, the analysis results are presented concisely. The generation AI also adjusts the presentation method of the analysis results according to the user's emotions. For example, if the user is feeling anxious, detailed explanations and support information are added. The generation AI also uses the emotion estimation function to select the presentation method of the analysis results based on the user's emotions. For example, if the user is feeling positive, the analysis results are presented in a positive tone. This makes it possible to present analysis results according to the user's emotions.

[0091] When the generation AI identifies problems, the problem identification unit can refer to similar past cases to identify problems with greater accuracy. For example, the generation AI searches a database for similar past cases and compares them with the current video. For example, it identifies problems by referring to past cases of cracks in buildings or past cases of disease in crops. The generation AI also improves the accuracy of problem identification based on similar past cases. For example, it learns from past data and recognizes patterns of cracks and disease. The generation AI also refers to similar past cases and extracts features that are useful for identifying problems. For example, it identifies problems based on the shape of a specific crack or the color change of disease. In this way, by referring to similar past cases, the accuracy of problem identification is improved.

[0092] When the generation AI proposes a solution, the solution proposal unit can refer to past success stories and propose the most effective solution. For example, the generation AI searches a database of past success stories and proposes the optimal solution to the current problem. For example, it refers to past cases of building repairs or cases of crop disease control. The generation AI also predicts the effectiveness of solutions based on past success stories and proposes the most effective solution. For example, it learns from past data and predicts the effectiveness of repair methods or pesticides. The generation AI also refers to past success stories and extracts features that are useful for proposing solutions. For example, it proposes solutions based on specific repair methods or pesticide use conditions. In this way, effective solutions can be proposed by referring to past success stories.

[0093] The solution proposal unit uses the emotion estimation function to propose solutions according to the user's emotions, and can provide solutions that are easy for the user to accept. In the solution proposal unit, for example, the generation AI analyzes the user's emotion data and proposes solutions according to the emotions. For example, if the user is feeling anxious, it proposes a solution that gives the user a sense of security. The generation AI also uses the emotion estimation function to propose solutions based on the user's emotions. For example, if the user is feeling positive, it proposes a positive solution. The generation AI also provides solutions that are easy for the user to accept based on the emotion data. For example, if the user is feeling stressed, it proposes a simple and effective solution. In this way, by proposing solutions according to the user's emotions, it is possible to provide solutions that are easy for the user to accept.

[0094] When the generation AI proposes a solution, the solution proposal unit can simulate multiple solutions and select the optimal solution. For example, the generation AI simulates multiple solutions and compares their effectiveness. For example, it simulates different repair methods or pesticide application methods and selects the optimal solution. The generation AI also proposes the optimal solution based on the simulation results. For example, it compares the costs and effectiveness of repair methods and proposes the most effective method. The generation AI also performs simulations in real time and presents the optimal solution to the user. For example, it performs simulations under different conditions and selects the optimal solution. In this way, the optimal solution can be selected by simulating multiple solutions.

[0095] The solution proposal unit can use the emotion estimation function to monitor the user's emotional reactions in real time when proposing a solution and adjust the proposed content. In the solution proposal unit, for example, the generation AI monitors the user's emotional reactions in real time and adjusts the proposed content of the solution. For example, if the user is feeling anxious, a detailed explanation is added. The generation AI also uses the emotion estimation function to propose solutions according to the user's emotions. For example, if the user is feeling positive, a proactive solution is proposed. The generation AI also provides solutions according to the user's emotions based on the emotion data. For example, if the user is feeling stressed, a simple and effective solution is proposed. In this way, the proposed content can be adjusted by monitoring the user's emotional reactions in real time.

[0096] When displaying the proposed content, the generating AI can incorporate interactive elements to allow the user to try out the proposed content. For example, the display unit can incorporate interactive elements to allow the user to try out the proposed content. For example, the generating AI can simulate a repair method or try out a method of using pesticides. The display unit also provides an interface that allows the user to try out the proposed content. For example, the procedure for a repair method can be displayed step by step, allowing the user to actually try it out. The generating AI can also incorporate interactive elements to allow the user to try out the proposed content. For example, the method of using pesticides can be simulated to confirm the effects. This allows the user to try out the proposed content, thereby deepening their understanding.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The video capture unit captures videos taken by the user. For example, videos taken with a smartphone can be uploaded to the app. Videos taken by drones can also be captured. The video capture unit can also stream videos in real time. For example, videos can be captured in real time using a smartphone camera and sent to the analysis unit. Step 2: In the analysis unit, the generation AI analyzes the captured video. For example, the generation AI uses text generation AI (e.g., LLM) to extract important information from the video. The generation AI can also use multimodal generation AI to analyze the content of the video. The generation AI can also use image analysis technology to recognize objects and actions in the video. For example, text generation AI has learned from large amounts of video data and has advanced analytical capabilities. Multimodal generation AI can handle multiple modalities, including not only video but also audio and text. The generation AI uses image analysis technology to recognize objects and actions in the video and perform analysis based on that. Step 3: In the problem identification section, the generation AI identifies problems from the video analyzed by the analysis section. For example, the generation AI detects cracks and damaged areas in a building. The generation AI can also detect diseases in agricultural crops. The generation AI can also detect abnormal behavior or conditions within the video. For example, the generation AI detects cracks in a building and identifies their location and size. When detecting diseases in agricultural crops, the generation AI detects abnormalities in the color and shape of the leaves and identifies the type of disease. Step 4: In the solution proposal section, the generation AI proposes solutions based on the problems identified by the problem identification section. For example, the generation AI proposes methods for repairing buildings and the materials to be used. The generation AI can also propose appropriate pesticides and countermeasures for crop diseases. The generation AI can also propose multiple solutions to a problem. For example, as a method for repairing a building, the generation AI proposes how to repair the repair area and a list of materials to be used. For crop diseases, the generation AI proposes appropriate pesticides and countermeasures and explains how to use them. Step 5: The display unit displays the solutions proposed by the solution proposal unit to the user. For example, the display unit may display a list of repair methods and materials to be used within the app. It may also display methods for preventing crop diseases and a list of pesticides to be used. The display unit may also display detailed explanations and procedures for the solutions. For example, the display unit may display step-by-step procedures for repair methods so that the user can actually try them out.

[0099] 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.

[0100] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 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.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0105] 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.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 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.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0120] 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.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] 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.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0135] 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.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] 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.

[0139] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0140] 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.

[0141] 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.

[0142] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] 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.

[0149] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0150] 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.

[0151] 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).

[0152] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0153] 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."

[0154] 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.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0160] The hardware resource that executes the specific process 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 process may be a single processor.

[0161] 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.

[0162] 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.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] 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.

[0165] 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. [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a video capture unit that captures videos taken by a user; an analysis unit that analyzes the video captured by the video capture unit; a problem identification unit that identifies problems from the video analyzed by the analysis unit; a solution proposal unit that proposes a solution based on the problem identified by the problem identification unit; a display unit that displays the solution proposed by the solution proposal unit. A system characterized by:

2. The video capture unit When capturing a video, the AI ​​generator evaluates the quality of the video in real time and provides shooting advice to achieve optimal analysis results.

2. The system of claim 1.

3. The analysis unit Integrate the video from multiple perspectives to extract more detailed information 2. The system of claim 1.

4. The analysis unit Analyzing emotions of people in the video and prioritizing the issues based on the emotions.

2. The system of claim 1.

5. The analysis unit When capturing the video, the audio data is also analyzed at the same time, and the information obtained from the audio is used as a complement.

2. The system of claim 1.

6. The analysis unit The analysis results of the video are integrated with other sensor data to perform more accurate analysis.

2. The system of claim 1.

Images