System

Abstract

To provide a system which automatizes editing of an image and voice data, and which effectively detects and cuts a statement that has a risk of backlash.SOLUTION: A system includes a reception part, an analysis part, a detection part and an edition part. The reception part inputs an image and voice data. The analysis part analyzes the data inputted by the reception part. The detection part detects a statement that has a risk of backlash based on the data analyzed by the analysis part. The edition part cuts the portion detected by the detection part according to a reference, and inputs a telop.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was a problem that the task of manually detecting and cutting comments that pose a risk of causing an uproar when editing video and audio data was cumbersome and difficult to do efficiently.

[0005] The system according to the embodiment aims to automate the editing of video and audio data and efficiently detect and cut comments that pose a risk of causing an uproar. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a detection unit, and an editing unit. The reception unit inputs video and audio data. The analysis unit analyzes the data input by the reception unit. The detection unit detects comments that pose a risk of causing a flame war based on the data analyzed by the analysis unit. The editing unit cuts out the portion detected by the detection unit according to a standard and inserts a caption. Effect of the Invention

[0007] The system according to the embodiment automates the editing of video and audio data, and can efficiently detect and cut comments that pose a risk of causing an uproar. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The video and audio analysis system according to the embodiment of the present invention is a system that automatically analyzes and edits video and audio data. This system inputs video and audio data, and AI analyzes the data to detect remarks that pose a risk of flaming or inappropriate expressions. For the detected parts, appropriate cuts and captions (such as annotations) are inserted to make video production more efficient and reduce the use of inappropriate expressions and the possibility of flaming. For example, video and audio data are input. For example, a video file or an audio file is uploaded to the system. This data is analyzed by AI. Next, AI analyzes the video and audio data. AI analyzes the remarks and actions of people in the video and the contents of the audio data to detect remarks that pose a risk of flaming or inappropriate expressions. For example, if discriminatory remarks or violent expressions are included, the AI ​​detects them. For the detected parts, appropriate cuts and captions (such as annotations) are inserted. For example, a part containing discriminatory remarks is cut, and a caption such as "This was cut because it contained inappropriate expressions" is inserted in that part. This reduces the risk of flaming while providing appropriate information to viewers. This mechanism makes video production more efficient. Users can save time and effort in editing manually and can create high-quality videos in a short time. In addition, by reducing the use of inappropriate expressions and the possibility of flame wars, it provides value to many users. For example, content creators can use this system to streamline video editing work and provide appropriate content to viewers. In addition, corporate public relations personnel can use this system to create effective promotional videos without damaging the company's image. This allows the video and audio analysis system to automatically analyze and edit video and audio data.

[0029] The video and audio analysis system according to the embodiment includes a reception unit, an analysis unit, a detection unit, and an editing unit. The reception unit inputs video and audio data. The video and audio data includes, for example, MP4 format, WAV format, live streaming data, and the like, but is not limited to such examples. The reception unit uploads, for example, video files and audio files to the system. The analysis unit analyzes the data input by the reception unit using AI. The analysis is performed, for example, using voice recognition technology and video analysis algorithms, but is not limited to such examples. For example, the analysis unit analyzes the remarks and actions of people in the video and the content of the voice data. For example, the analysis unit converts remarks into text data using voice recognition technology, and analyzes actions using gesture recognition technology. The detection unit detects remarks that are at risk of causing a flaming incident or inappropriate expressions based on the data analyzed by the analysis unit. The detection is performed, for example, using a specific keyword list or emotion analysis, but is not limited to such examples. For example, the detection unit detects discriminatory remarks and violent expressions. The detection unit detects utterances using, for example, a specific keyword list and detects expressions using sentiment analysis. The editing unit cuts the portion detected by the detection unit according to a criterion and inserts a caption. Editing is performed, for example, according to a criterion for cut editing or caption insertion, but is not limited to such an example. For example, the editing unit cuts the detected portion and inserts a caption such as "This was cut because it contained an inappropriate expression." In this way, the video and audio analysis system according to the embodiment can automatically analyze video and audio data and perform editing. A part or all of the above-mentioned processing in the editing unit may be performed, for example, using AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that inputs the portion detected by the detection unit and outputs cut editing and caption insertion.

[0030] The reception unit inputs video and audio data. The video and audio data include, but are not limited to, MP4 format, WAV format, and live streaming data. The reception unit uploads, for example, video files and audio files to the system. Specifically, a user can select and upload a file from a local storage or cloud storage through the system interface. When the reception unit receives these data, it analyzes the format and metadata of the data and prepares for appropriate processing. For example, in the case of video data, it extracts information such as frame rate and resolution, and in the case of audio data, it extracts information such as sampling rate and bit rate. Furthermore, the reception unit also supports receiving live streaming data, and can receive data in real time and transmit it to the analysis unit. In the case of live streaming data, the reception unit buffers data and handles errors to ensure a stable data supply. As a result, the reception unit can efficiently receive video and audio data in various formats and smoothly proceed with the processing of the entire system.

[0031] The analysis unit uses AI to analyze the data input by the reception unit. The analysis is performed, for example, using voice recognition technology or a video analysis algorithm, but is not limited to such examples. Specifically, the voice data is converted into text data using voice recognition technology, and the movement of people and objects in the video is analyzed using a video analysis algorithm. For example, the voice recognition technology uses a voice model using deep learning to convert the content of a statement into text with high accuracy. This allows the content, tone, emotion, and the like of the statement to be analyzed in detail. The video analysis algorithm uses computer vision technology to analyze the gestures, facial expressions, and behavior of people in the video. For example, the gesture recognition technology can be used to analyze hand movements and facial expressions to infer the intention and emotion of the action. Furthermore, the analysis unit integrates these analysis results and grasps the overall context of the video and audio data. For example, the degree of agreement between the content of the statement and the gestures can be evaluated, and the credibility and intention of the statement can be analyzed. This allows the analysis unit to analyze the video and audio data from multiple angles and extract detailed information.

[0032] The detection unit detects statements that pose a risk of flaming or inappropriate expressions based on the data analyzed by the analysis unit. The detection is performed, for example, using a specific keyword list or emotion analysis, but is not limited to such examples. Specifically, a specific keyword list is used to detect discriminatory statements or violent expressions. For example, the keyword list includes discriminatory terms, violent expressions, insulting words, etc., and it is checked whether these keywords are included in the statement. The emotion analysis analyzes the tone and emotion of the statement to evaluate whether it contains negative emotions. For example, an emotion analysis algorithm is used to calculate an emotion score for the statement, and if the negative emotion is high, it is determined that there is a high risk of flaming. Furthermore, the detection unit evaluates the context of the statement or expression based on the analysis result and determines the degree of risk. For example, the detection unit considers the context before and after the statement and the situation in the video to evaluate whether the statement is intentional or may be misleading. This allows the detection unit to evaluate the overall risk of the statement or expression, not just the match of keywords, and perform more accurate detection.

[0033] The editing department cuts the part detected by the detection department according to a standard and inserts a caption. Editing is performed, for example, according to the standard of cut editing and caption insertion, but is not limited to such examples. Specifically, the detected part is automatically cut and a caption such as "It was cut because it contained inappropriate expressions" is inserted. The editing department can automate these editing tasks using AI. For example, an AI model that performs cut editing and caption insertion is used to perform editing based on input data from the detection department. The AI ​​model analyzes the timestamps of the video and audio data and accurately cuts the detected part. In addition, the insertion position and content of the caption are automatically determined and displayed at the appropriate timing. Furthermore, the editing department can also respond to customization requests from users. For example, if a user wants to edit according to specific standards or rules, the editing department can perform editing that reflects these requests. This allows the editing department to quickly and accurately edit the detected inappropriate parts and provide appropriate information to the viewers.

[0034] The analysis unit can analyze the remarks and actions of the person in the video and the content of the voice data. The analysis unit converts the remarks of the person in the video into text data, for example, using voice recognition technology. For example, the analysis unit converts the remarks of the person in the video into text data with high accuracy using voice recognition technology. The analysis unit can also analyze the actions of the person in the video using gesture recognition technology. For example, the analysis unit analyzes the hand movements and facial expressions of the person in the video using gesture recognition technology. The analysis unit can also analyze the content of the voice data. For example, the analysis unit converts the content of the voice data into text data using voice recognition technology and analyzes the content. This makes it possible to perform more accurate analysis by analyzing the remarks and actions of the person in the video and the content of the voice data. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the remarks and actions of the person in the video and the content of the voice data and outputs the analysis result.

[0035] The detection unit can detect remarks and expressions based on a specific criterion. The detection unit detects remarks and expressions using, for example, a specific keyword list. For example, the detection unit detects discriminatory remarks and violent expressions using a specific keyword list. The detection unit can also detect remarks and expressions using sentiment analysis. For example, the detection unit uses sentiment analysis to analyze the tone and emotion of a remark and detect remarks that pose a risk of flaming and inappropriate expressions. In this way, the risk of flaming can be reduced by detecting discriminatory remarks and violent expressions. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that receives a specific keyword list and sentiment analysis as input and outputs a detection result of a remark or expression.

[0036] The editing department can cut the detected part and insert a caption. For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate expressions." For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate expressions." The editing department can also edit the detected part according to the criteria for cut editing and caption insertion. For example, the editing department cuts a part containing a specific keyword and inserts a caption in that part. In this way, by cutting the detected part and inserting a caption, it is possible to reduce the risk of a flaming incident while providing appropriate information to viewers. Part or all of the above-mentioned processing in the editing department may be performed, for example, using AI or may be performed without using AI. For example, the editing department can perform editing using an AI model that inputs the part detected by the detection unit and outputs cut editing and caption insertion.

[0037] The reception unit can input a video file or an audio file. The reception unit, for example, uploads a video file or an audio file to the system. The video file or audio file includes, for example, an MP4 format, a WAV format, an AVI format, and the like, but is not limited to such examples. For example, the reception unit uploads a video file in MP4 format to the system and passes it to the analysis unit. The reception unit can also upload an audio file in WAV format to the system and pass it to the analysis unit. Furthermore, the reception unit can also upload a video file in AVI format to the system and pass it to the analysis unit. Thereby, data can be provided to the system by inputting a video file or an audio file. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs a video file or an audio file and passes data to the analysis unit.

[0038] The editing department can insert a caption such as "It was cut because it contained an expression based on a specific criterion." The editing department inserts a caption such as "It was cut because it contained an expression based on a specific criterion." For example, the editing department cuts the detected part and inserts a caption such as "It was cut because it contained an expression based on a specific criterion" in that part. The editing department can also edit the detected part according to the criteria for cutting and inserting a caption. For example, the editing department cuts a part that contains a specific keyword and inserts a caption in that part. By inserting a caption in the part that contains an inappropriate expression, it is possible to reduce the risk of a flame war while providing appropriate information to viewers. A part or all of the above-mentioned processing in the editing department may be performed, for example, using AI or may be performed without using AI. For example, the editing department can perform editing using an AI model that inputs the part detected by the detection unit and outputs cutting and inserting a caption.

[0039] The reception unit can analyze the user's past data input history and select the optimal input method. The reception unit, for example, preferentially suggests an input method (such as voice or text) that the user has frequently used in the past. For example, the reception unit analyzes an input method that the user has frequently used in the past and preferentially suggests voice input or text input. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past input history. For example, the reception unit analyzes the user's past input history and predicts and suggests an input method to be used in a specific time period. The reception unit can also select the optimal input method based on the format of data that the user has input in the past. For example, the reception unit analyzes the format of data that the user has input in the past and selects the optimal input method. As a result, the optimal input method is suggested by analyzing the user's past data input history, and efficient data input is possible. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that uses the user's past data input history as input and selects the optimal input method.

[0040] The reception unit can perform filtering based on the user's current project or field of interest when inputting video or audio data. The reception unit, for example, preferentially inputs only data related to a project currently in progress by the user. For example, the reception unit efficiently inputs highly relevant data by preferentially inputting data related to a project currently in progress by the user. The reception unit can also automatically filter highly relevant data based on the user's field of interest. For example, the reception unit automatically filters highly relevant data based on the user's field of interest. The reception unit can also filter input data based on project tags set by the user. For example, the reception unit filters input data based on project tags set by the user. As a result, highly relevant data can be efficiently input by filtering data based on the user's current project or field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's current project or field of interest and outputs a filtering result.

[0041] The reception unit can preferentially input highly relevant data in consideration of the geographical location information of the user when inputting video and audio data. The reception unit, for example, preferentially inputs data related to the location where the user is currently located. For example, the reception unit efficiently inputs highly relevant data by preferentially inputting data related to the location where the user is currently located. The reception unit can also automatically filter highly relevant data based on the geographical location information of the user. For example, the reception unit automatically filters highly relevant data based on the geographical location information of the user. The reception unit can also filter input data based on geographical tags set by the user. For example, the reception unit filters input data based on geographical tags set by the user. This enables efficient data input by preferentially inputting highly relevant data based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs the geographical location information of the user and preferentially inputs highly relevant data.

[0042] The reception unit can analyze the social media activity of the user and input related data when video or audio data is input. The reception unit, for example, preferentially inputs related data based on content shared by the user on social media. For example, the reception unit preferentially inputs related data based on content shared by the user on social media, thereby efficiently inputting highly relevant data. The reception unit can also analyze the social media activity of the user and automatically filter highly relevant data. For example, the reception unit analyzes the social media activity of the user and automatically filters highly relevant data. The reception unit can also filter the input data based on accounts followed by the user on social media. For example, the reception unit filters the input data based on accounts followed by the user on social media. In this way, highly relevant data can be efficiently input by analyzing the social media activity of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs the social media activity of the user and inputs related data.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the video and audio data during the analysis. The analysis unit performs a detailed analysis of important data, for example. For example, the analysis unit performs a detailed analysis of important data to analyze important parts of the data in detail. The analysis unit can also perform a concise analysis of data with low importance. For example, the analysis unit performs a concise analysis of data with low importance to perform efficient analysis. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit performs efficient analysis by dynamically adjusting the level of detail of the analysis according to the importance of the data. As a result, efficient analysis is possible by adjusting the level of detail of the analysis based on the importance of the video and audio data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that uses the importance of data as an input and adjusts the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. The analysis unit applies a video analysis algorithm to video data, for example. For example, the analysis unit improves the analysis accuracy of the video data by applying a video analysis algorithm to the video data. The analysis unit can also apply a voice analysis algorithm to voice data. For example, the analysis unit improves the analysis accuracy of the voice data by applying a voice analysis algorithm to the voice data. The analysis unit can also select an optimal analysis algorithm depending on the category of data. For example, the analysis unit improves the analysis accuracy by selecting an optimal analysis algorithm depending on the category of data. As a result, the analysis accuracy is improved by applying the optimal analysis algorithm depending on the category of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the category of data and applies the optimal analysis algorithm.

[0045] The analysis unit can determine the priority of the analysis based on the time of data submission during the analysis. The analysis unit, for example, prioritizes the analysis of the latest data. For example, the analysis unit prioritizes the analysis of the latest data, thereby quickly providing the latest information. The analysis unit can also postpone data submitted a long time ago. For example, the analysis unit performs efficient analysis by postponing data submitted a long time ago. The analysis unit can also dynamically adjust the priority of the analysis according to the time of data submission. For example, the analysis unit performs efficient analysis by dynamically adjusting the priority of the analysis according to the time of data submission. As a result, efficient analysis is possible by determining the priority of the analysis based on the time of data submission. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the time of data submission and determines the priority of the analysis.

[0046] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. The analysis unit, for example, prioritizes analysis of highly relevant data. For example, the analysis unit quickly provides highly relevant information by prioritizing analysis of highly relevant data. The analysis unit can also postpone data with low relevance. For example, the analysis unit performs efficient analysis by postponing data with low relevance. The analysis unit can also dynamically adjust the order of analysis according to the relevance of data. For example, the analysis unit performs efficient analysis by dynamically adjusting the order of analysis according to the relevance of data. As a result, efficient analysis is possible by adjusting the order of analysis based on the relevance of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the relevance of data and adjusts the order of analysis.

[0047] The detection unit can improve the accuracy of detection by considering the correlation between video and audio data at the time of detection. The detection unit performs detection by considering, for example, synchronization between video and audio. For example, the detection unit improves the accuracy of detection by performing detection by considering synchronization between video and audio. The detection unit can also perform detection by associating the speech and behavior of a person in the video. For example, the detection unit performs detection more accurately by associating the speech and behavior of a person in the video. The detection unit can also perform detection by associating the content of audio data with a scene in the video. For example, the detection unit improves the accuracy of detection by associating the content of audio data with a scene in the video. As a result, the accuracy of detection is improved by considering the correlation between video and audio. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that receives video and audio data as input and performs detection by considering the correlation.

[0048] The detection unit can perform detection by taking into consideration attribute information of the data submitter at the time of detection. The detection unit performs detection based on, for example, the age and sex of the submitter. For example, the detection unit performs more appropriate detection by performing detection based on the age and sex of the submitter. The detection unit can also perform detection based on the submitter's occupation and position. For example, the detection unit performs more appropriate detection by performing detection based on the submitter's occupation and position. The detection unit can also perform detection based on the submitter's past speech history. For example, the detection unit performs more appropriate detection by performing detection based on the submitter's past speech history. This makes it possible to perform more appropriate detection by taking into consideration the attribute information of the submitter. Part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that uses the attribute information of the submitter as input and performs detection.

[0049] The detection unit can perform detection in consideration of the geographical distribution of data at the time of detection. The detection unit performs detection based on, for example, the geographical distribution of data. For example, the detection unit performs more appropriate detection by performing detection based on the geographical distribution of data. The detection unit can also preferentially detect data with high geographical relevance. For example, the detection unit performs more appropriate detection by preferentially detecting data with high geographical relevance. The detection unit can also dynamically adjust the accuracy of detection according to the geographical distribution. For example, the detection unit performs more appropriate detection by dynamically adjusting the accuracy of detection according to the geographical distribution. This enables more appropriate detection by considering the geographical distribution of data. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that uses the geographical distribution of data as an input and performs detection.

[0050] The detection unit can improve the accuracy of detection by referring to related literature of the data at the time of detection. The detection unit, for example, sets a detection standard by referring to related literature. For example, the detection unit improves the accuracy of detection by setting a detection standard by referring to related literature. The detection unit can also improve the accuracy of detection based on the contents of the related literature. For example, the detection unit improves the accuracy of detection based on the contents of the related literature. The detection unit can also dynamically refer to related literature to complement the detection result. For example, the detection unit dynamically refers to related literature to complement the detection result to improve the accuracy of detection. As a result, the accuracy of detection is improved by referring to related literature. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that performs detection using related literature as input.

[0051] The editing unit can adjust the level of detail of the editing based on the importance of the detected part during editing. The editing unit, for example, performs detailed editing on important parts. For example, the editing unit performs detailed editing on important parts to provide important information in detail. The editing unit can also perform concise editing on parts with low importance. For example, the editing unit performs concise editing on parts with low importance to perform efficient editing. The editing unit can also dynamically adjust the level of detail of the editing according to the importance of the detected part. For example, the editing unit performs efficient editing by dynamically adjusting the level of detail of the editing according to the importance of the detected part. As a result, efficient editing is possible by adjusting the level of detail of the editing based on the importance of the detected part. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that uses the importance of the detected part as an input and adjusts the level of detail of the editing.

[0052] The editing unit can apply different editing algorithms depending on the category of data during editing. The editing unit applies a video editing algorithm to video data, for example. For example, the editing unit applies a video editing algorithm to video data to improve the editing accuracy of the video data. The editing unit can also apply an audio editing algorithm to audio data. For example, the editing unit applies an audio editing algorithm to audio data to improve the editing accuracy of the audio data. The editing unit can also select an optimal editing algorithm depending on the category of data. For example, the editing unit improves the editing accuracy by selecting an optimal editing algorithm depending on the category of data. As a result, the accuracy of editing is improved by applying the optimal editing algorithm depending on the category of data. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that inputs the category of data and applies the optimal editing algorithm.

[0053] The editing department can adjust the order of editing based on the submission time of data during editing. The editing department, for example, gives priority to editing the latest data. For example, the editing department gives priority to editing the latest data, thereby quickly providing the latest information. The editing department can also postpone data submitted earlier. For example, the editing department performs efficient editing by postponing data submitted earlier. The editing department can also dynamically adjust the order of editing according to the submission time of data. For example, the editing department performs efficient editing by dynamically adjusting the order of editing according to the submission time of data. As a result, efficient editing is possible by adjusting the order of editing based on the submission time of data. A part or all of the above-mentioned processing in the editing department may be performed using, for example, AI, or may be performed without using AI. For example, the editing department can perform editing using an AI model that uses the submission time of data as an input and adjusts the order of editing.

[0054] The editing unit can adjust the order of editing based on the relevance of data during editing. The editing unit, for example, gives priority to editing highly relevant data. For example, the editing unit gives priority to editing highly relevant data, thereby quickly providing highly relevant information. The editing unit can also postpone data with low relevance. For example, the editing unit performs efficient editing by postponing data with low relevance. The editing unit can also dynamically adjust the order of editing according to the relevance of data. For example, the editing unit performs efficient editing by dynamically adjusting the order of editing according to the relevance of data. As a result, efficient editing is possible by adjusting the order of editing based on the relevance of data. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that uses the relevance of data as an input and adjusts the order of editing.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The analysis unit can propose a recommended editing style based on the analysis results of the video and audio data, taking into consideration the user's preferences and viewing history. For example, the analysis unit analyzes the style of videos that the user has liked to watch in the past, and proposes a similar editing style. The analysis unit can also propose an editing style related to a specific genre or theme from the user's viewing history. Furthermore, the analysis unit can recommend specific effects and transitions based on the user's preferences. This makes it possible to produce videos with higher satisfaction by proposing an editing style that matches the user's preferences. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can make a proposal using an AI model that inputs the user's viewing history and preferences and outputs a recommended editing style.

[0057] The detection unit can detect inappropriate expressions in a particular culture or region based on the analysis results of the video and audio data. For example, the detection unit detects remarks and actions that are discriminatory in a particular culture or region. The detection unit can also detect inappropriate expressions related to a particular religion or faith. Furthermore, the detection unit can detect inappropriate expressions based on a particular social background or historical context. In this way, by detecting inappropriate expressions in a particular culture or region, appropriate content can be provided to a global audience. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can perform detection using an AI model that inputs data related to a particular culture or region and detects inappropriate expressions.

[0058] The editorial department can perform customized editing for a specific audience based on the analysis results of the video and audio data. For example, the editorial department can add educational subtitles and animations to content for children. The editorial department can also increase the font size and use easy-to-read fonts for content for the elderly. Furthermore, the editorial department can insert related information and links for viewers with specific hobbies and interests. This makes it possible to improve viewer satisfaction by performing customized editing for a specific audience. Some or all of the above-mentioned processing in the editorial department may be performed using, for example, AI, or may be performed without using AI. For example, the editorial department can perform editing using an AI model that inputs data on the audience and outputs customized editing.

[0059] The reception unit can compress and convert the data when inputting video and audio data, taking into account the performance of the user's device. For example, if the user's device has low specifications, the reception unit compresses and inputs the data. In addition, if the user is using a high-spec device, the reception unit can input high-resolution data as is. Furthermore, the reception unit can adjust the data compression rate according to the storage capacity of the device. This enables efficient data input by compressing and converting data according to the performance of the user's device. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input device performance data using an AI model that compresses and converts data.

[0060] The analysis unit can recommend content related to a particular trend or topic based on the analysis results of the video and audio data. For example, the analysis unit recommends related content based on a current trend. The analysis unit can also recommend past content related to a particular topic. Furthermore, the analysis unit can suggest new content related to a trend or topic based on the user's interest. In this way, by recommending content related to a particular trend or topic, it is possible to attract the user's interest and extend the viewing time. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can make suggestions using an AI model that inputs data related to trends and topics and recommends related content.

[0061] The analysis unit can automatically generate content related to a specific event or occurrence based on the analysis results of the video and audio data. For example, the analysis unit can automatically extract video clips related to a specific event and generate a highlight video. The analysis unit can also automatically extract audio clips related to a specific event and generate a podcast. Furthermore, the analysis unit can generate a documentary by combining video and audio data based on a specific theme. This enables efficient content production by automatically generating content related to a specific event or occurrence. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can generate content using an AI model that inputs data related to an event or occurrence and automatically generates related content.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The reception unit inputs video and audio data. The video and audio data includes, for example, MP4 format, WAV format, live streaming data, etc. The reception unit uploads the video file and audio file to the system. Step 2: The analysis unit uses AI to analyze the data entered by the reception unit. The analysis is performed using voice recognition technology and video analysis algorithms. For example, the analysis unit analyzes the remarks and actions of people in the video, as well as the content of the voice data. It converts remarks into text data using voice recognition technology, and analyzes actions using gesture recognition technology. Step 3: The detection unit detects comments that pose a risk of flaming or inappropriate expressions based on the data analyzed by the analysis unit. Detection is performed using a specific keyword list and sentiment analysis. For example, the detection unit detects discriminatory comments or violent expressions. It detects comments using a specific keyword list and expressions using sentiment analysis. Step 4: The editing department cuts the part detected by the detection department according to a standard and inserts a caption. Editing is performed according to the standards for cut editing and caption insertion. For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate content." The processing in the editing department may be performed using AI or without AI.

[0064] (Example 2) The video and audio analysis system according to the embodiment of the present invention is a system that automatically analyzes and edits video and audio data. This system inputs video and audio data, and AI analyzes the data to detect remarks that pose a risk of flaming or inappropriate expressions. For the detected parts, appropriate cuts and captions (such as annotations) are inserted to make video production more efficient and reduce the use of inappropriate expressions and the possibility of flaming. For example, video and audio data are input. For example, a video file or an audio file is uploaded to the system. This data is analyzed by AI. Next, AI analyzes the video and audio data. AI analyzes the remarks and actions of people in the video and the contents of the audio data to detect remarks that pose a risk of flaming or inappropriate expressions. For example, if discriminatory remarks or violent expressions are included, the AI ​​detects them. For the detected parts, appropriate cuts and captions (such as annotations) are inserted. For example, a part containing discriminatory remarks is cut, and a caption such as "This was cut because it contained inappropriate expressions" is inserted in that part. This reduces the risk of flaming while providing appropriate information to viewers. This mechanism makes video production more efficient. Users can save time and effort in editing manually and can create high-quality videos in a short time. In addition, by reducing the use of inappropriate expressions and the possibility of flame wars, it provides value to many users. For example, content creators can use this system to streamline video editing work and provide appropriate content to viewers. In addition, corporate public relations personnel can use this system to create effective promotional videos without damaging the company's image. This allows the video and audio analysis system to automatically analyze and edit video and audio data.

[0065] The video and audio analysis system according to the embodiment includes a reception unit, an analysis unit, a detection unit, and an editing unit. The reception unit inputs video and audio data. The video and audio data includes, for example, MP4 format, WAV format, live streaming data, and the like, but is not limited to such examples. The reception unit uploads, for example, video files and audio files to the system. The analysis unit analyzes the data input by the reception unit using AI. The analysis is performed, for example, using voice recognition technology and video analysis algorithms, but is not limited to such examples. For example, the analysis unit analyzes the remarks and actions of people in the video and the content of the voice data. For example, the analysis unit converts remarks into text data using voice recognition technology, and analyzes actions using gesture recognition technology. The detection unit detects remarks that are at risk of causing a flaming incident or inappropriate expressions based on the data analyzed by the analysis unit. The detection is performed, for example, using a specific keyword list or emotion analysis, but is not limited to such examples. For example, the detection unit detects discriminatory remarks and violent expressions. The detection unit detects utterances using, for example, a specific keyword list and detects expressions using sentiment analysis. The editing unit cuts the portion detected by the detection unit according to a criterion and inserts a caption. Editing is performed, for example, according to a criterion for cut editing or caption insertion, but is not limited to such an example. For example, the editing unit cuts the detected portion and inserts a caption such as "This was cut because it contained an inappropriate expression." In this way, the video and audio analysis system according to the embodiment can automatically analyze video and audio data and perform editing. A part or all of the above-mentioned processing in the editing unit may be performed, for example, using AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that inputs the portion detected by the detection unit and outputs cut editing and caption insertion.

[0066] The reception unit inputs video and audio data. The video and audio data include, but are not limited to, MP4 format, WAV format, and live streaming data. The reception unit uploads, for example, video files and audio files to the system. Specifically, a user can select and upload a file from a local storage or cloud storage through the system interface. When the reception unit receives these data, it analyzes the format and metadata of the data and prepares for appropriate processing. For example, in the case of video data, it extracts information such as frame rate and resolution, and in the case of audio data, it extracts information such as sampling rate and bit rate. Furthermore, the reception unit also supports receiving live streaming data, and can receive data in real time and transmit it to the analysis unit. In the case of live streaming data, the reception unit buffers data and handles errors to ensure a stable data supply. As a result, the reception unit can efficiently receive video and audio data in various formats and smoothly proceed with the processing of the entire system.

[0067] The analysis unit uses AI to analyze the data input by the reception unit. The analysis is performed, for example, using voice recognition technology or a video analysis algorithm, but is not limited to such examples. Specifically, the voice data is converted into text data using voice recognition technology, and the movement of people and objects in the video is analyzed using a video analysis algorithm. For example, the voice recognition technology uses a voice model using deep learning to convert the content of a statement into text with high accuracy. This allows the content, tone, emotion, and the like of the statement to be analyzed in detail. The video analysis algorithm uses computer vision technology to analyze the gestures, facial expressions, and behavior of people in the video. For example, the gesture recognition technology can be used to analyze hand movements and facial expressions to infer the intention and emotion of the action. Furthermore, the analysis unit integrates these analysis results and grasps the overall context of the video and audio data. For example, the degree of agreement between the content of the statement and the gestures can be evaluated, and the credibility and intention of the statement can be analyzed. This allows the analysis unit to analyze the video and audio data from multiple angles and extract detailed information.

[0068] The detection unit detects statements that pose a risk of flaming or inappropriate expressions based on the data analyzed by the analysis unit. The detection is performed, for example, using a specific keyword list or emotion analysis, but is not limited to such examples. Specifically, a specific keyword list is used to detect discriminatory statements or violent expressions. For example, the keyword list includes discriminatory terms, violent expressions, insulting words, etc., and it is checked whether these keywords are included in the statement. The emotion analysis analyzes the tone and emotion of the statement to evaluate whether it contains negative emotions. For example, an emotion analysis algorithm is used to calculate an emotion score for the statement, and if the negative emotion is high, it is determined that there is a high risk of flaming. Furthermore, the detection unit evaluates the context of the statement or expression based on the analysis result and determines the degree of risk. For example, the detection unit considers the context before and after the statement and the situation in the video to evaluate whether the statement is intentional or may be misleading. This allows the detection unit to evaluate the overall risk of the statement or expression, not just the match of keywords, and perform more accurate detection.

[0069] The editing department cuts the part detected by the detection department according to a standard and inserts a caption. Editing is performed, for example, according to the standard of cut editing and caption insertion, but is not limited to such examples. Specifically, the detected part is automatically cut and a caption such as "It was cut because it contained inappropriate expressions" is inserted. The editing department can automate these editing tasks using AI. For example, an AI model that performs cut editing and caption insertion is used to perform editing based on input data from the detection department. The AI ​​model analyzes the timestamps of the video and audio data and accurately cuts the detected part. In addition, the insertion position and content of the caption are automatically determined and displayed at the appropriate timing. Furthermore, the editing department can also respond to customization requests from users. For example, if a user wants to edit according to specific standards or rules, the editing department can perform editing that reflects these requests. This allows the editing department to quickly and accurately edit the detected inappropriate parts and provide appropriate information to the viewers.

[0070] The analysis unit can analyze the remarks and actions of the person in the video and the content of the voice data. The analysis unit converts the remarks of the person in the video into text data, for example, using voice recognition technology. For example, the analysis unit converts the remarks of the person in the video into text data with high accuracy using voice recognition technology. The analysis unit can also analyze the actions of the person in the video using gesture recognition technology. For example, the analysis unit analyzes the hand movements and facial expressions of the person in the video using gesture recognition technology. The analysis unit can also analyze the content of the voice data. For example, the analysis unit converts the content of the voice data into text data using voice recognition technology and analyzes the content. This makes it possible to perform more accurate analysis by analyzing the remarks and actions of the person in the video and the content of the voice data. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the remarks and actions of the person in the video and the content of the voice data and outputs the analysis result.

[0071] The detection unit can detect remarks and expressions based on a specific criterion. The detection unit detects remarks and expressions using, for example, a specific keyword list. For example, the detection unit detects discriminatory remarks and violent expressions using a specific keyword list. The detection unit can also detect remarks and expressions using sentiment analysis. For example, the detection unit uses sentiment analysis to analyze the tone and emotion of a remark and detect remarks that pose a risk of flaming and inappropriate expressions. In this way, the risk of flaming can be reduced by detecting discriminatory remarks and violent expressions. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that receives a specific keyword list and sentiment analysis as input and outputs a detection result of a remark or expression.

[0072] The editing department can cut the detected part and insert a caption. For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate expressions." For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate expressions." The editing department can also edit the detected part according to the criteria for cut editing and caption insertion. For example, the editing department cuts a part containing a specific keyword and inserts a caption in that part. In this way, by cutting the detected part and inserting a caption, it is possible to reduce the risk of a flaming incident while providing appropriate information to viewers. Part or all of the above-mentioned processing in the editing department may be performed, for example, using AI or may be performed without using AI. For example, the editing department can perform editing using an AI model that inputs the part detected by the detection unit and outputs cut editing and caption insertion.

[0073] The reception unit can input a video file or an audio file. The reception unit, for example, uploads a video file or an audio file to the system. The video file or audio file includes, for example, an MP4 format, a WAV format, an AVI format, and the like, but is not limited to such examples. For example, the reception unit uploads a video file in MP4 format to the system and passes it to the analysis unit. The reception unit can also upload an audio file in WAV format to the system and pass it to the analysis unit. Furthermore, the reception unit can also upload a video file in AVI format to the system and pass it to the analysis unit. Thereby, data can be provided to the system by inputting a video file or an audio file. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs a video file or an audio file and passes data to the analysis unit.

[0074] The editing department can insert a caption such as "It was cut because it contained an expression based on a specific criterion." The editing department inserts a caption such as "It was cut because it contained an expression based on a specific criterion." For example, the editing department cuts the detected part and inserts a caption such as "It was cut because it contained an expression based on a specific criterion" in that part. The editing department can also edit the detected part according to the criteria for cutting and inserting a caption. For example, the editing department cuts a part that contains a specific keyword and inserts a caption in that part. By inserting a caption in the part that contains an inappropriate expression, it is possible to reduce the risk of a flame war while providing appropriate information to viewers. A part or all of the above-mentioned processing in the editing department may be performed, for example, using AI or may be performed without using AI. For example, the editing department can perform editing using an AI model that inputs the part detected by the detection unit and outputs cutting and inserting a caption.

[0075] The reception unit can estimate the user's emotion and adjust the input timing of the video and audio data based on the estimated user's emotion. For example, when the user is stressed, the reception unit provides a simple interface and minimizes the input procedure. For example, when the user is stressed, the reception unit provides a simple interface and minimizes the input procedure, thereby reducing the user's stress. In addition, the reception unit can provide detailed input options and suggest a customizable input method when the user is relaxed. For example, when the user is relaxed, the reception unit provides detailed input options and suggests a customizable input method, thereby providing an input method according to the user's needs. In addition, the reception unit can prioritize voice input when the user is in a hurry, allowing the user to input video and audio data quickly. For example, when the user is in a hurry, the reception unit prioritizes voice input and allows the user to input video and audio data quickly, thereby saving the user's time. As a result, by adjusting the input timing based on the user's emotion, the user's stress is reduced and efficient data input is possible. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit may perform input using an AI model that receives emotion data of a user and adjusts the input timing.

[0076] The reception unit can analyze the user's past data input history and select the optimal input method. The reception unit, for example, preferentially suggests an input method (such as voice or text) that the user has frequently used in the past. For example, the reception unit analyzes an input method that the user has frequently used in the past and preferentially suggests voice input or text input. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past input history. For example, the reception unit analyzes the user's past input history and predicts and suggests an input method to be used in a specific time period. The reception unit can also select the optimal input method based on the format of data that the user has input in the past. For example, the reception unit analyzes the format of data that the user has input in the past and selects the optimal input method. As a result, the optimal input method is suggested by analyzing the user's past data input history, and efficient data input is possible. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that uses the user's past data input history as input and selects the optimal input method.

[0077] The reception unit can perform filtering based on the user's current project or field of interest when inputting video or audio data. The reception unit, for example, preferentially inputs only data related to a project currently in progress by the user. For example, the reception unit efficiently inputs highly relevant data by preferentially inputting data related to a project currently in progress by the user. The reception unit can also automatically filter highly relevant data based on the user's field of interest. For example, the reception unit automatically filters highly relevant data based on the user's field of interest. The reception unit can also filter input data based on project tags set by the user. For example, the reception unit filters input data based on project tags set by the user. As a result, highly relevant data can be efficiently input by filtering data based on the user's current project or field of interest. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's current project or field of interest and outputs a filtering result.

[0078] The reception unit can estimate the user's emotion and determine the priority of data to be input based on the estimated user's emotion. For example, when the user is nervous, the reception unit preferentially inputs important data. For example, when the user is nervous, the reception unit preferentially inputs important data, thereby reducing the burden on the user. The reception unit can also preferentially input detailed data when the user is relaxed. For example, when the user is relaxed, the reception unit preferentially inputs detailed data, thereby providing data input according to the user's needs. The reception unit can also preferentially input the most important data when the user is in a hurry. For example, when the user is in a hurry, the reception unit preferentially inputs the most important data, thereby saving the user's time. As a result, important data can be preferentially input by determining the priority of data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input a user's emotional data using an AI model that determines the priority order of the data.

[0079] The reception unit can preferentially input highly relevant data in consideration of the geographical location information of the user when inputting video and audio data. The reception unit, for example, preferentially inputs data related to the location where the user is currently located. For example, the reception unit efficiently inputs highly relevant data by preferentially inputting data related to the location where the user is currently located. The reception unit can also automatically filter highly relevant data based on the geographical location information of the user. For example, the reception unit automatically filters highly relevant data based on the geographical location information of the user. The reception unit can also filter input data based on geographical tags set by the user. For example, the reception unit filters input data based on geographical tags set by the user. This enables efficient data input by preferentially inputting highly relevant data based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs the geographical location information of the user and preferentially inputs highly relevant data.

[0080] The reception unit can analyze the social media activity of the user and input related data when video or audio data is input. The reception unit, for example, preferentially inputs related data based on content shared by the user on social media. For example, the reception unit preferentially inputs related data based on content shared by the user on social media, thereby efficiently inputting highly relevant data. The reception unit can also analyze the social media activity of the user and automatically filter highly relevant data. For example, the reception unit analyzes the social media activity of the user and automatically filters highly relevant data. The reception unit can also filter the input data based on accounts followed by the user on social media. For example, the reception unit filters the input data based on accounts followed by the user on social media. In this way, highly relevant data can be efficiently input by analyzing the social media activity of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can perform input using an AI model that inputs the social media activity of the user and inputs related data.

[0081] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. The analysis unit provides a detailed analysis result when the user is relaxed, for example. For example, the analysis unit provides a detailed analysis result when the user is relaxed, thereby providing an analysis result that is easy for the user to understand. The analysis unit can also provide a concise and to the point analysis result when the user is nervous. For example, the analysis unit can reduce the burden on the user by providing a concise and to the point analysis result when the user is nervous. The analysis unit can also provide a quick analysis result when the user is in a hurry. For example, the analysis unit can save the user's time by providing a quick analysis result when the user is in a hurry. This allows the analysis result to be easily understood by adjusting the expression method of the analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may perform analysis using an AI model that inputs the user's emotion data and adjusts the way the analysis is expressed.

[0082] The analysis unit can adjust the level of detail of the analysis based on the importance of the video and audio data during the analysis. The analysis unit performs a detailed analysis of important data, for example. For example, the analysis unit performs a detailed analysis of important data to analyze important parts of the data in detail. The analysis unit can also perform a concise analysis of data with low importance. For example, the analysis unit performs a concise analysis of data with low importance to perform efficient analysis. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit performs efficient analysis by dynamically adjusting the level of detail of the analysis according to the importance of the data. As a result, efficient analysis is possible by adjusting the level of detail of the analysis based on the importance of the video and audio data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that uses the importance of data as an input and adjusts the level of detail of the analysis.

[0083] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. The analysis unit applies a video analysis algorithm to video data, for example. For example, the analysis unit improves the analysis accuracy of the video data by applying a video analysis algorithm to the video data. The analysis unit can also apply a voice analysis algorithm to voice data. For example, the analysis unit improves the analysis accuracy of the voice data by applying a voice analysis algorithm to the voice data. The analysis unit can also select an optimal analysis algorithm depending on the category of data. For example, the analysis unit improves the analysis accuracy by selecting an optimal analysis algorithm depending on the category of data. As a result, the analysis accuracy is improved by applying the optimal analysis algorithm depending on the category of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the category of data and applies the optimal analysis algorithm.

[0084] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The analysis unit performs a detailed analysis, for example, when the user is relaxed. For example, when the user is relaxed, the analysis unit performs a detailed analysis to provide an analysis result that is easy for the user to understand. The analysis unit can also perform a concise analysis when the user is in a hurry. For example, when the user is in a hurry, the analysis unit performs a concise analysis to save the user's time. The analysis unit can also provide a visually stimulating analysis result when the user is excited. For example, when the user is excited, the analysis unit provides a visually stimulating analysis result to attract the user's interest. This allows the analysis result of an appropriate length for the user to be provided by adjusting the length of the analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the analysis unit can perform the analysis using an AI model that takes the user's emotional data as input and adjusts the length of the analysis.

[0085] The analysis unit can determine the priority of the analysis based on the time of data submission during the analysis. The analysis unit, for example, prioritizes the analysis of the latest data. For example, the analysis unit prioritizes the analysis of the latest data, thereby quickly providing the latest information. The analysis unit can also postpone data submitted a long time ago. For example, the analysis unit performs efficient analysis by postponing data submitted a long time ago. The analysis unit can also dynamically adjust the priority of the analysis according to the time of data submission. For example, the analysis unit performs efficient analysis by dynamically adjusting the priority of the analysis according to the time of data submission. As a result, efficient analysis is possible by determining the priority of the analysis based on the time of data submission. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the time of data submission and determines the priority of the analysis.

[0086] The analysis unit can adjust the order of analysis based on the relevance of data during analysis. The analysis unit, for example, prioritizes analysis of highly relevant data. For example, the analysis unit quickly provides highly relevant information by prioritizing analysis of highly relevant data. The analysis unit can also postpone data with low relevance. For example, the analysis unit performs efficient analysis by postponing data with low relevance. The analysis unit can also dynamically adjust the order of analysis according to the relevance of data. For example, the analysis unit performs efficient analysis by dynamically adjusting the order of analysis according to the relevance of data. As a result, efficient analysis is possible by adjusting the order of analysis based on the relevance of data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that inputs the relevance of data and adjusts the order of analysis.

[0087] The detection unit can estimate the user's emotion and adjust the detection criteria based on the estimated user's emotion. For example, when the user is relaxed, the detection unit performs detection with strict criteria. For example, when the user is relaxed, the detection unit performs detection with strict criteria to perform more accurate detection. In addition, the detection unit can also perform detection with loose criteria when the user is tense. For example, when the user is tense, the detection unit performs detection with loose criteria to reduce the burden on the user. In addition, the detection unit can also perform detection quickly when the user is in a hurry. For example, when the user is in a hurry, the detection unit performs detection quickly to save the user's time. As a result, by adjusting the detection criteria based on the user's emotion, more appropriate detection is possible. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can perform detection using an AI model that takes a user's emotional data as input and adjusts the detection criteria.

[0088] The detection unit can improve the accuracy of detection by considering the correlation between video and audio data at the time of detection. The detection unit performs detection by considering, for example, synchronization between video and audio. For example, the detection unit improves the accuracy of detection by performing detection by considering synchronization between video and audio. The detection unit can also perform detection by associating the speech and behavior of a person in the video. For example, the detection unit performs detection more accurately by associating the speech and behavior of a person in the video. The detection unit can also perform detection by associating the content of audio data with a scene in the video. For example, the detection unit improves the accuracy of detection by associating the content of audio data with a scene in the video. As a result, the accuracy of detection is improved by considering the correlation between video and audio. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that receives video and audio data as input and performs detection by considering the correlation.

[0089] The detection unit can perform detection by taking into consideration attribute information of the data submitter at the time of detection. The detection unit performs detection based on, for example, the age and sex of the submitter. For example, the detection unit performs more appropriate detection by performing detection based on the age and sex of the submitter. The detection unit can also perform detection based on the submitter's occupation and position. For example, the detection unit performs more appropriate detection by performing detection based on the submitter's occupation and position. The detection unit can also perform detection based on the submitter's past speech history. For example, the detection unit performs more appropriate detection by performing detection based on the submitter's past speech history. This makes it possible to perform more appropriate detection by taking into consideration the attribute information of the submitter. Part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that uses the attribute information of the submitter as input and performs detection.

[0090] The detection unit can estimate the user's emotion and adjust the order of displaying the detection results based on the estimated user's emotion. For example, when the user is relaxed, the detection unit preferentially displays detailed results. For example, when the user is relaxed, the detection unit preferentially displays detailed results, thereby providing results that are easy for the user to understand. In addition, the detection unit can also preferentially display concise results when the user is nervous. For example, when the user is nervous, the detection unit preferentially displays concise results to reduce the burden on the user. In addition, the detection unit can also quickly display results when the user is in a hurry. For example, when the user is in a hurry, the detection unit quickly displays results to save the user's time. In this way, by adjusting the display order of the results based on the user's emotion, it is possible to provide results that are easy for the user to understand. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can perform detection using an AI model that takes a user's emotion data as input and adjusts the display order of the results.

[0091] The detection unit can perform detection in consideration of the geographical distribution of data at the time of detection. The detection unit performs detection based on, for example, the geographical distribution of data. For example, the detection unit performs more appropriate detection by performing detection based on the geographical distribution of data. The detection unit can also preferentially detect data with high geographical relevance. For example, the detection unit performs more appropriate detection by preferentially detecting data with high geographical relevance. The detection unit can also dynamically adjust the accuracy of detection according to the geographical distribution. For example, the detection unit performs more appropriate detection by dynamically adjusting the accuracy of detection according to the geographical distribution. This enables more appropriate detection by considering the geographical distribution of data. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that uses the geographical distribution of data as an input and performs detection.

[0092] The detection unit can improve the accuracy of detection by referring to related literature of the data at the time of detection. The detection unit, for example, sets a detection standard by referring to related literature. For example, the detection unit improves the accuracy of detection by setting a detection standard by referring to related literature. The detection unit can also improve the accuracy of detection based on the contents of the related literature. For example, the detection unit improves the accuracy of detection based on the contents of the related literature. The detection unit can also dynamically refer to related literature to complement the detection result. For example, the detection unit dynamically refers to related literature to complement the detection result to improve the accuracy of detection. As a result, the accuracy of detection is improved by referring to related literature. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that performs detection using related literature as input.

[0093] The editing unit can estimate the user's emotion and adjust the editing method based on the estimated user's emotion. For example, when the user is relaxed, the editing unit performs detailed editing. For example, when the user is relaxed, the editing unit performs detailed editing to provide an editing result that is easy for the user to understand. In addition, the editing unit can perform concise editing when the user is nervous. For example, when the user is nervous, the editing unit performs concise editing to reduce the burden on the user. In addition, the editing unit can perform quick editing when the user is in a hurry. For example, when the user is in a hurry, the editing unit performs quick editing to save the user's time. As a result, by adjusting the editing method based on the user's emotion, appropriate editing for the user is possible. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editorial team could use an AI model that takes a user's emotional data as input and adjusts the editing method.

[0094] The editing unit can adjust the level of detail of the editing based on the importance of the detected part during editing. The editing unit, for example, performs detailed editing on important parts. For example, the editing unit performs detailed editing on important parts to provide important information in detail. The editing unit can also perform concise editing on parts with low importance. For example, the editing unit performs concise editing on parts with low importance to perform efficient editing. The editing unit can also dynamically adjust the level of detail of the editing according to the importance of the detected part. For example, the editing unit performs efficient editing by dynamically adjusting the level of detail of the editing according to the importance of the detected part. As a result, efficient editing is possible by adjusting the level of detail of the editing based on the importance of the detected part. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that uses the importance of the detected part as an input and adjusts the level of detail of the editing.

[0095] The editing unit can apply different editing algorithms depending on the category of data during editing. The editing unit applies a video editing algorithm to video data, for example. For example, the editing unit applies a video editing algorithm to video data to improve the editing accuracy of the video data. The editing unit can also apply an audio editing algorithm to audio data. For example, the editing unit applies an audio editing algorithm to audio data to improve the editing accuracy of the audio data. The editing unit can also select an optimal editing algorithm depending on the category of data. For example, the editing unit improves the editing accuracy by selecting an optimal editing algorithm depending on the category of data. As a result, the accuracy of editing is improved by applying the optimal editing algorithm depending on the category of data. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that inputs the category of data and applies the optimal editing algorithm.

[0096] The editing unit can estimate the user's emotion and determine the priority of editing based on the estimated user's emotion. For example, when the user is relaxed, the editing unit prioritizes detailed editing. For example, when the user is relaxed, the editing unit prioritizes detailed editing to provide an editing result that is easy for the user to understand. In addition, the editing unit can also prioritize concise editing when the user is nervous. For example, when the user is nervous, the editing unit prioritizes concise editing to reduce the burden on the user. In addition, the editing unit can also quickly edit when the user is in a hurry. For example, when the user is in a hurry, the editing unit quickly edits to save the user's time. In this way, important parts can be edited with priority by determining the priority of editing based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editorial department can use an AI model that takes a user's emotional data as input and determines the priority of edits.

[0097] The editing department can adjust the order of editing based on the submission time of data during editing. The editing department, for example, gives priority to editing the latest data. For example, the editing department gives priority to editing the latest data, thereby quickly providing the latest information. The editing department can also postpone data submitted earlier. For example, the editing department performs efficient editing by postponing data submitted earlier. The editing department can also dynamically adjust the order of editing according to the submission time of data. For example, the editing department performs efficient editing by dynamically adjusting the order of editing according to the submission time of data. As a result, efficient editing is possible by adjusting the order of editing based on the submission time of data. A part or all of the above-mentioned processing in the editing department may be performed using, for example, AI, or may be performed without using AI. For example, the editing department can perform editing using an AI model that uses the submission time of data as an input and adjusts the order of editing.

[0098] The editing unit can adjust the order of editing based on the relevance of data during editing. The editing unit, for example, gives priority to editing highly relevant data. For example, the editing unit gives priority to editing highly relevant data, thereby quickly providing highly relevant information. The editing unit can also postpone data with low relevance. For example, the editing unit performs efficient editing by postponing data with low relevance. The editing unit can also dynamically adjust the order of editing according to the relevance of data. For example, the editing unit performs efficient editing by dynamically adjusting the order of editing according to the relevance of data. As a result, efficient editing is possible by adjusting the order of editing based on the relevance of data. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can perform editing using an AI model that uses the relevance of data as an input and adjusts the order of editing.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The analysis unit can propose a recommended editing style based on the analysis results of the video and audio data, taking into consideration the user's preferences and viewing history. For example, the analysis unit analyzes the style of videos that the user has liked to watch in the past, and proposes a similar editing style. The analysis unit can also propose an editing style related to a specific genre or theme from the user's viewing history. Furthermore, the analysis unit can recommend specific effects and transitions based on the user's preferences. This makes it possible to produce videos with higher satisfaction by proposing an editing style that matches the user's preferences. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can make a proposal using an AI model that inputs the user's viewing history and preferences and outputs a recommended editing style.

[0101] The detection unit can detect inappropriate expressions in a particular culture or region based on the analysis results of the video and audio data. For example, the detection unit detects remarks and actions that are discriminatory in a particular culture or region. The detection unit can also detect inappropriate expressions related to a particular religion or faith. Furthermore, the detection unit can detect inappropriate expressions based on a particular social background or historical context. In this way, by detecting inappropriate expressions in a particular culture or region, appropriate content can be provided to a global audience. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can perform detection using an AI model that inputs data related to a particular culture or region and detects inappropriate expressions.

[0102] The editorial department can perform customized editing for a specific audience based on the analysis results of the video and audio data. For example, the editorial department can add educational subtitles and animations to content for children. The editorial department can also increase the font size and use easy-to-read fonts for content for the elderly. Furthermore, the editorial department can insert related information and links for viewers with specific hobbies and interests. This makes it possible to improve viewer satisfaction by performing customized editing for a specific audience. Some or all of the above-mentioned processing in the editorial department may be performed using, for example, AI, or may be performed without using AI. For example, the editorial department can perform editing using an AI model that inputs data on the audience and outputs customized editing.

[0103] The reception unit can compress and convert the data when inputting video and audio data, taking into account the performance of the user's device. For example, if the user's device has low specifications, the reception unit compresses and inputs the data. In addition, if the user is using a high-spec device, the reception unit can input high-resolution data as is. Furthermore, the reception unit can adjust the data compression rate according to the storage capacity of the device. This enables efficient data input by compressing and converting data according to the performance of the user's device. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input device performance data using an AI model that compresses and converts data.

[0104] The analysis unit can recommend content related to a particular trend or topic based on the analysis results of the video and audio data. For example, the analysis unit recommends related content based on a current trend. The analysis unit can also recommend past content related to a particular topic. Furthermore, the analysis unit can suggest new content related to a trend or topic based on the user's interest. In this way, by recommending content related to a particular trend or topic, it is possible to attract the user's interest and extend the viewing time. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can make suggestions using an AI model that inputs data related to trends and topics and recommends related content.

[0105] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, the analysis unit displays a detailed analysis result when the user is relaxed. In addition, the analysis unit can also display a concise analysis result when the user is nervous. Furthermore, the analysis unit can display a visually stimulating analysis result when the user is excited. In this way, by adjusting the display method of the analysis result based on the user's emotion, it is possible to provide an analysis result that is easy for the user to understand. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can perform analysis using an AI model that inputs the user's emotion data and adjusts the display method of the analysis result.

[0106] The detection unit can estimate the user's emotion and adjust the accuracy of detection based on the estimated user's emotion. For example, the detection unit performs detection with strict criteria when the user is relaxed. Also, the detection unit can perform detection with loose criteria when the user is tense. Furthermore, the detection unit can perform detection quickly when the user is in a hurry. This allows more appropriate detection by adjusting the accuracy of detection based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can perform detection using an AI model that inputs the user's emotion data and adjusts the accuracy of detection.

[0107] The editing unit can estimate the user's emotion and adjust the tempo of editing based on the estimated user's emotion. For example, when the user is relaxed, the editing unit performs editing at a relaxed tempo. Also, when the user is nervous, the editing unit can perform editing at a fast tempo. Furthermore, when the user is excited, the editing unit can perform visually stimulating editing. In this way, by adjusting the tempo of editing based on the user's emotion, it is possible to provide content that is attractive to viewers. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editing unit can perform editing using an AI model that inputs the user's emotion data and adjusts the tempo of editing.

[0108] The reception unit can estimate the user's emotion and customize the input interface based on the estimated user's emotion. For example, the reception unit provides detailed input options when the user is relaxed. The reception unit can also provide a simple input interface when the user is nervous. Furthermore, the reception unit can provide an interface that prioritizes voice input when the user is in a hurry. This reduces the user's stress by customizing the input interface based on the user's emotion, and enables efficient data input. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data using an AI model that customizes the input interface.

[0109] The analysis unit can automatically generate content related to a specific event or occurrence based on the analysis results of the video and audio data. For example, the analysis unit can automatically extract video clips related to a specific event and generate a highlight video. The analysis unit can also automatically extract audio clips related to a specific event and generate a podcast. Furthermore, the analysis unit can generate a documentary by combining video and audio data based on a specific theme. This enables efficient content production by automatically generating content related to a specific event or occurrence. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can generate content using an AI model that inputs data related to an event or occurrence and automatically generates related content.

[0110] The process flow of the second embodiment will be briefly described below.

[0111] Step 1: The reception unit inputs video and audio data. The video and audio data includes, for example, MP4 format, WAV format, live streaming data, etc. The reception unit uploads the video file and audio file to the system. Step 2: The analysis unit uses AI to analyze the data entered by the reception unit. The analysis is performed using voice recognition technology and video analysis algorithms. For example, the analysis unit analyzes the remarks and actions of people in the video, as well as the content of the voice data. It converts remarks into text data using voice recognition technology, and analyzes actions using gesture recognition technology. Step 3: The detection unit detects comments that pose a risk of flaming or inappropriate expressions based on the data analyzed by the analysis unit. Detection is performed using a specific keyword list and sentiment analysis. For example, the detection unit detects discriminatory comments or violent expressions. It detects comments using a specific keyword list and expressions using sentiment analysis. Step 4: The editing department cuts the part detected by the detection department according to a standard and inserts a caption. Editing is performed according to the standards for cut editing and caption insertion. For example, the editing department cuts the detected part and inserts a caption such as "This part was cut because it contained inappropriate content." The processing in the editing department may be performed using AI or without AI.

[0112] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0114] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and editing unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14, and inputs video and audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects remarks that may cause a flaming incident or inappropriate expressions based on the analyzed data. The editing unit is realized, for example, by the control unit 46A of the smart device 14, and cuts out the detected part and inserts a subtitle. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] 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.

[0120] 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 the voice according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0122] 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 performed in a secure state.

[0123] Fig. 4 shows an example of 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.

[0124] 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.

[0125] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0127] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0128] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0129] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0130] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and editing unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and inputs video and audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects statements that may cause a flaming incident or inappropriate expressions based on the analyzed data. The editing unit is realized, for example, by the control unit 46A of the smart glasses 214, and cuts out the detected part and inserts a subtitle. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] 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.

[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 the voice according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed in a secure state.

[0139] 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.

[0140] 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.

[0141] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0142] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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 identification processing unit 290 using these models.

[0143] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0144] 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 voice indicating a user input for 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.

[0145] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0146] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and editing unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314, and inputs video and audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects remarks that may cause a flaming incident or inappropriate expressions based on the analyzed data. The editing unit is realized, for example, by the control unit 46A of the headset type terminal 314, and cuts out the detected part and inserts a subtitle. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] 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.

[0152] 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 the voice according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0154] 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 performed in a secure state.

[0155] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0156] 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.

[0157] 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.

[0158] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0159] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 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.

[0160] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0161] 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 a voice indicating a user input for 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.

[0162] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0163] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0164] Each of the multiple elements including the above-mentioned reception unit, analysis unit, detection unit, and editing unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and inputs video and audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects remarks that may cause a flaming incident or inappropriate expressions based on the analyzed data. The editing unit is realized, for example, by the control unit 46A of the robot 414, and cuts out the detected part and inserts a subtitle. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0165] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0166] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0167] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0168] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0169] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0170] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0172] 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.

[0173] 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 Universal Serial Bus (USB) 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.

[0174] In addition, 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 upon request from the data processing device 12.

[0175] 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.

[0176] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0177] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0178] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0179] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0180] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0181] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0182] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0183] (Appendix 1) a reception section for inputting video and audio data; an analysis unit that analyzes the data input by the reception unit; A detection unit that detects comments that pose a risk of causing an uproar based on the data analyzed by the analysis unit; an editing unit that cuts the part detected by the detection unit according to a standard and inserts a telop. A system characterized by: (Appendix 2) The analysis unit is Analyze the statements and actions of people in the video and the content of audio data 2. The system of claim 1, (Appendix 3) The detection unit is Detecting statements or expressions based on specific criteria 2. The system of claim 1, (Appendix 4) The editorial department: Cut out the detected part and insert a subtitle 2. The system of claim 1, (Appendix 5) The reception unit is Input video and audio files 2. The system of claim 1, (Appendix 6) The editorial department: Insert a caption such as, "This was cut because it contained expressions based on certain standards." 2. The system of claim 1, (Appendix 7) The reception unit is A system that estimates a user's emotions and adjusts the timing of inputting video and audio data based on the estimated user's emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past data entry history and select the optimal entry method 2. The system of claim 1, (Appendix 9) The reception unit is Filtering video and audio data as it enters based on the user's current project or area of ​​interest 2. The system of claim 1, (Appendix 10) The reception unit is Infer user emotions and prioritize input data based on the inferred user emotions 2. The system of claim 1, (Appendix 11) The reception unit is When inputting video and audio data, the system takes into account the user's geographic location information and inputs data that is highly relevant to the user. 2. The system of claim 1, (Appendix 12) The reception unit is When video and audio data is input, the user's social media activity is analyzed and relevant data is input. 2. The system of claim 1, (Appendix 13) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, the level of analysis detail is adjusted based on the importance of video and audio data. 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, apply different analysis algorithms depending on the category of data 2. The system of claim 1, (Appendix 16) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, prioritize analysis based on when data were submitted 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, adjust the order of analysis based on data relevance 2. The system of claim 1, (Appendix 19) The detection unit is Estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. 2. The system of claim 1, (Appendix 20) The detection unit is Improve detection accuracy by considering correlations between video and audio data during detection 2. The system of claim 1, (Appendix 21) The detection unit is When detecting, the attribute information of the data submitter is taken into consideration. 2. The system of claim 1, (Appendix 22) The detection unit is Estimate the user's emotions and adjust the order in which the detection results are displayed based on the estimated user emotions. 2. The system of claim 1, (Appendix 23) The detection unit is When detecting, the geographical distribution of data is taken into account 2. The system of claim 1, (Appendix 24) The detection unit is When detecting, the accuracy of detection is improved by referencing related literature of the data. 2. The system of claim 1, (Appendix 25) The editorial department: Infer user emotions and adjust editing methods based on the estimated user emotions 2. The system of claim 1, (Appendix 26) The editorial department: When editing, adjust the level of detail in your edits based on the importance of the detected areas 2. The system of claim 1, (Appendix 27) The editorial department: Apply different editing algorithms to different categories of data when editing 2. The system of claim 1, (Appendix 28) The editorial department: Estimate user sentiment and prioritize edits based on the estimated user sentiment 2. The system of claim 1, (Appendix 29) The editorial department: When editing, adjust the order of edits based on when the data was submitted 2. The system of claim 1, (Appendix 30) The editorial department: As you edit, adjust the order of edits based on data relevance 2. The system of claim 1, [Explanation of symbols]

[0184] 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 reception section for inputting video and audio data; an analysis unit that analyzes the data input by the reception unit; A detection unit that detects comments that pose a risk of causing an uproar based on the data analyzed by the analysis unit; an editing unit that cuts the part detected by the detection unit according to a standard and inserts a telop. A system characterized by:

2. The analysis unit is Analyze the statements and actions of people in the video and the content of audio data 2. The system of claim 1 .

3. The detection unit is Detecting statements or expressions based on specific criteria 2. The system of claim 1 .

4. The reception unit is Input video and audio files 2. The system of claim 1 .

5. The reception unit is A system that estimates a user's emotions and adjusts the timing of inputting video and audio data based on the estimated user's emotions 2. The system of claim 1 .

6. The reception unit is Analyze the user's past data entry history and select the optimal entry method 2. The system of claim 1 .

Images