An artificial intelligence-based video stream encryption and decryption method and system

Abstract

The application discloses an artificial intelligence-based video stream encryption and decryption method and system. The method comprises the following steps: preprocessing the input video stream, removing noise and adjusting the resolution; using an artificial intelligence algorithm to extract image and time sequence features of the video stream; dynamically generating an encryption strategy according to the extracted features, selecting appropriate encryption algorithms and key parameters; encrypting the video stream according to the encryption strategy and transmitting it through a network; and using a corresponding decryption algorithm to recover the original video content according to the encryption strategy at the receiving end. The application realizes dynamic adjustment of the encryption strategy through artificial intelligence technology, can effectively resist attacks and improve the security of the video stream.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a video stream encryption and decryption method and system based on artificial intelligence. Background Technology

[0002] With the rapid development of internet technology, video streaming media is being used more and more widely in people's lives, such as online video conferencing, live streaming, and video-on-demand. However, video streams face many security threats during transmission, such as data leakage, tampering, and theft. This not only infringes on user privacy but may also cause huge economic losses to businesses and organizations.

[0003] Traditional video stream encryption and decryption methods mainly rely on fixed encryption algorithms and key management mechanisms. While these methods can ensure video stream security to a certain extent, their security and flexibility are gradually becoming insufficient in the face of increasingly complex network attack methods. For example, fixed encryption algorithms are easily cracked, and once the key is leaked, the security of the entire video stream will be seriously threatened. Moreover, traditional methods often suffer from low encryption and decryption efficiency and difficulty in adapting to different network environments when processing large-scale video stream data. Summary of the Invention

[0004] Based on this, the embodiments of this application provide a video stream encryption and decryption method and system based on artificial intelligence, which solves the problems of low encryption and decryption efficiency and difficulty in adapting to different network environments in the prior art.

[0005] Firstly, an artificial intelligence-based video stream encryption / decryption method is provided, the method comprising:

[0006] The input video stream is preprocessed to remove noise and adjust the resolution;

[0007] Artificial intelligence algorithms are used to extract features from the preprocessed video stream. The extracted features include the texture, color, and shape features of the image, as well as the time series features of the video stream.

[0008] Based on the extracted video stream features, an artificial intelligence model is used to dynamically generate encryption strategies, including selecting encryption algorithms, determining key generation methods and lengths;

[0009] The video stream is encrypted according to the generated encryption strategy, and the encrypted video stream is transmitted over the network.

[0010] After receiving the encrypted video stream, the receiving end decrypts it using the corresponding decryption algorithm according to the encryption policy, restoring the original video content.

[0011] Optionally, in the preprocessing step, an adaptive filtering algorithm is used to remove noise from the video stream. The adaptive filtering algorithm includes dynamically adjusting the filtering parameters according to the noise type and intensity of the video stream.

[0012] The resolution is dynamically adjusted based on the resolution and bitrate of the video stream. Specifically, by analyzing the clarity requirements and transmission bandwidth limitations of the video stream, an appropriate resolution adjustment strategy is selected to optimize subsequent processing efficiency while ensuring smooth transmission of the video stream under different network environments.

[0013] Optionally, in the feature extraction step, a convolutional neural network is used to extract features from each frame of the video stream. The extracted feature vector includes the image's texture features, color distribution features, and inter-frame motion change features.

[0014] Specifically, the convolutional neural network model contains multiple convolutional layers, pooling layers, and fully connected layers. By training with a large amount of labeled video frame data, it can automatically learn high-level feature representations of images. Temporal series features are extracted through a long short-term memory network to analyze the dynamic changes of the video stream. The long short-term memory network model can capture the long-term dependencies between frames in the video stream and extract the temporal series feature vector of the video stream.

[0015] Optionally, in the encryption strategy generation step, a machine learning model is used to analyze the relationship between video stream features and security requirements. Specifically, a decision tree model is constructed to dynamically select a symmetric encryption algorithm or an asymmetric encryption algorithm based on the importance and real-time requirements of the video stream. Furthermore, a genetic algorithm is used to optimize the key length and encryption parameters. The genetic algorithm iteratively optimizes the key length and encryption parameters by simulating a natural selection process.

[0016] The encryption strategy also includes dynamically adjusting the encryption mode of the encryption algorithm based on the type of video stream and the application scenario, including electronic codebook mode or cryptographic blockchain mode.

[0017] Optionally, in the video stream encryption step, the encryption algorithm dynamically adjusts the encryption strength according to the network environment. Specifically, the encryption strength of the encryption algorithm is adjusted in real time by monitoring the network bandwidth, latency and packet loss rate parameters.

[0018] During the encryption process, potential risk points are predicted through neural networks, and encryption parameters are adjusted in advance to ensure the stability of the encryption process. Specifically, deep neural networks are used to monitor the data in real time during the encryption process, predict possible encryption errors or security vulnerabilities, and adjust encryption parameters in a timely manner. The encryption parameters include key update frequency and encryption block size.

[0019] Optionally, in the video streaming step, artificial intelligence algorithms are used to monitor the network environment in real time, including parameters such as bandwidth, latency, and packet loss rate.

[0020] Specifically, a sensor network deployed on network nodes collects network status data in real time, and machine learning algorithms are used for data analysis and prediction. Based on the monitoring results, the encoding format and resolution of the video stream are dynamically adjusted. Specifically, adaptive encoding technology is used to dynamically select the appropriate encoding format based on the network status and adjust the resolution of the video stream to ensure stable transmission of the video stream in different network environments.

[0021] Meanwhile, a data integrity verification mechanism is used to retransmit or repair lost or damaged data. Specifically, cyclic redundancy check and forward error correction coding technology are used to verify the integrity of data during transmission. Once data loss or damage is detected, the retransmission or repair mechanism is immediately activated to ensure the integrity and availability of the video stream.

[0022] Optionally, in the video stream decryption step, the decryption algorithm dynamically adjusts the decryption parameters according to the encryption strategy. Specifically, the parameter adaptive module in the decryption algorithm dynamically adjusts the decryption parameters according to the encryption parameters in the encryption strategy.

[0023] Machine learning models are used to predict potential errors during the decryption process and correct them in advance. Specifically, deep learning models are used to monitor the data in real time during the decryption process, predict possible decryption errors, including key errors and data format errors, and correct errors in a timely manner through an adaptive error correction mechanism.

[0024] In a second aspect, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the video stream encryption and decryption method described in any of the first aspects above.

[0025] Thirdly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the video stream encryption / decryption method described in any of the first aspects above.

[0026] Fourthly, a computer program product is provided, on which a computer program is stored, and when the computer program is executed by a processor, it implements the video stream encryption and decryption method described in any of the first aspects above.

[0027] The beneficial effects of the technical solutions provided in this application include at least the following:

[0028] (1) By dynamically generating encryption strategies through artificial intelligence algorithms, encryption algorithms and key parameters can be flexibly selected according to the characteristics and security requirements of the video stream. Compared with traditional fixed encryption methods, this method can effectively resist attacks targeting specific encryption algorithms, significantly improve the security of video streams during transmission, and protect user privacy and data security.

[0029] (2) During the encryption and decryption process, this application utilizes artificial intelligence technology to monitor and analyze the network environment and video stream characteristics in real time, and dynamically adjusts the encryption strength and decryption parameters. This adaptive mechanism can optimize the encryption and decryption process, reduce the consumption of computing resources, improve the transmission efficiency and decryption speed of the video stream, and ensure smooth playback of the video stream while ensuring security. Attached Figure Description

[0030] To more clearly illustrate the embodiments of this application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0031] Figure 1 A flowchart illustrating the steps of an artificial intelligence-based video stream encryption / decryption method provided in this application embodiment;

[0032] Figure 2 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0034] In the description of this application, the terms "comprising," "having," and any variations thereof are intended to cover non-exclusive inclusion, such as a process, method, system, product, or apparatus that includes a series of steps or units, not necessarily limited to those steps or units that are expressly listed, but may also include other steps or units that are not expressly listed but are inherent to these processes, methods, products, or apparatuses, or steps or units added based on further optimizations conceived in this application.

[0035] With the rapid development of internet technology, video streaming media is being used more and more widely in people's lives, such as online video conferencing, live streaming, and video-on-demand. However, video streams face many security threats during transmission, such as data leakage, tampering, and theft. This not only infringes on user privacy but may also cause huge economic losses to businesses and organizations.

[0036] Traditional video stream encryption and decryption methods mainly rely on fixed encryption algorithms and key management mechanisms. While these methods can ensure video stream security to a certain extent, their security and flexibility are gradually becoming insufficient in the face of increasingly complex network attack methods. For example, fixed encryption algorithms are easily cracked, and once the key is leaked, the security of the entire video stream will be seriously threatened. Moreover, traditional methods often suffer from low encryption and decryption efficiency and difficulty in adapting to different network environments when processing large-scale video stream data.

[0037] Please refer to Figure 1 The diagram illustrates a flowchart of an artificial intelligence-based video stream encryption / decryption method provided in an embodiment of this application. The method may include the following steps:

[0038] S1 preprocesses the input video stream, removing noise and adjusting the resolution.

[0039] In this step, the input video stream is first received. The main task is to remove noise from the video stream and adjust its resolution to ensure the accuracy and efficiency of subsequent processing. The specific implementation is as follows:

[0040] An adaptive filtering algorithm is used to denoise the video stream. This algorithm dynamically adjusts the filtering parameters based on the type and intensity of noise in the video stream. For example, for Gaussian noise, the algorithm adjusts the kernel size and standard deviation of the filter; for impulse noise, the algorithm switches to median filtering mode. This adaptability allows the denoising process to achieve optimal results for different types of noise.

[0041] Based on the video stream's resolution and bitrate, the preprocessing module analyzes the video stream's clarity requirements and transmission bandwidth limitations, dynamically selecting an appropriate resolution adjustment strategy. For example, for a high-resolution video stream with limited bandwidth, the module will adjust its resolution from 4K to 1080p to optimize subsequent processing efficiency while ensuring smooth transmission of the video stream under different network environments.

[0042] S2 uses artificial intelligence algorithms to extract features from the preprocessed video stream.

[0043] The extracted features include image texture, color, and shape features, as well as temporal series features of the video stream. The main task in this step is to extract image texture, color, and shape features, as well as temporal series features from the video stream. The specific implementation is as follows:

[0044] Image Feature Extraction: Convolutional Neural Networks (CNNs) are used to extract features from each frame of the video stream. A CNN model contains multiple convolutional layers, pooling layers, and fully connected layers. By training on a large amount of labeled video frame data, CNNs can automatically learn high-level feature representations of images. The extracted feature vectors include texture features, color distribution features, and inter-frame motion variation features.

[0045] Time-series feature extraction: Time-series features are extracted using a Long Short-Term Memory (LSTM) network. The LSTM model can capture the long-term dependencies between frames in a video stream, extracting time-series feature vectors from the video stream. These feature vectors provide comprehensive feature information for subsequent encryption strategy generation, helping to generate more accurate encryption strategies.

[0046] S3, based on the extracted video stream features, dynamically generates encryption strategies through an artificial intelligence model, including selecting encryption algorithms, determining key generation methods and lengths.

[0047] This step involves selecting a suitable encryption algorithm and determining the key generation method and length. The specific implementation is as follows:

[0048] Machine learning models (such as decision tree models) are used to analyze the relationship between video stream characteristics and security requirements. Based on the importance and real-time requirements of the video stream, either a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA) is dynamically selected. For example, for video streams with high real-time requirements, the AES algorithm is chosen to ensure encryption efficiency; for video streams with extremely high security requirements, the RSA algorithm is chosen to ensure encryption strength.

[0049] The key length and encryption parameters are optimized using a genetic algorithm. The genetic algorithm iteratively optimizes the key length and encryption parameters by simulating the natural selection process. For example, the initial population consists of randomly generated key parameters. The security and efficiency of each set of parameters are evaluated using a fitness function. The optimal parameters are selected and subjected to crossover and mutation operations to ultimately obtain the optimal key length and encryption parameters.

[0050] The encryption mode of the encryption algorithm is dynamically adjusted based on the type of video stream and the application scenario. For example, the Cipher Block Chain (CBC) mode is selected for video streams requiring high security, while the Electronic Codebook (ECB) mode is selected for video streams requiring high efficiency.

[0051] S4. Encrypt the video stream according to the generated encryption strategy, and transmit the encrypted video stream over the network.

[0052] The encryption module encrypts the video stream according to the generated encryption policy and then transmits the encrypted video stream over the network. The main task of this module is to ensure the stability and security of the encryption process. The specific implementation is as follows:

[0053] The encryption algorithm dynamically adjusts its encryption strength based on the network environment. By monitoring network bandwidth, latency, and packet loss rate parameters, the encryption strength is adjusted in real time. For example, in a high-bandwidth, low-latency network environment, the encryption strength can be appropriately increased; in a low-bandwidth, high-latency network environment, the encryption strength can be appropriately decreased to ensure encryption efficiency.

[0054] By using neural networks to predict potential risks during the encryption process, encryption parameters can be adjusted in advance. Specifically, deep neural networks are used to monitor data in real time during the encryption process, predict possible encryption errors or security vulnerabilities, and adjust encryption parameters such as key update frequency and encryption block size in a timely manner to ensure the stability of the encryption process.

[0055] The transmission module utilizes artificial intelligence algorithms to monitor the network environment in real time, including parameters such as bandwidth, latency, and packet loss rate. The main task of this module is to ensure stable transmission of video streams under different network conditions. The specific implementation is as follows:

[0056] By deploying a sensor network on network nodes, network status data is collected in real time, and machine learning algorithms are used for data analysis and prediction. For example, linear regression models are used to predict trends in network bandwidth, and decision tree models are used to predict network latency and packet loss rate.

[0057] Based on monitoring results, the encoding format and resolution of the video stream are dynamically adjusted. Specifically, adaptive encoding technology is used to dynamically select an appropriate encoding format (such as H.264 or H.265) according to network conditions and adjust the resolution of the video stream to ensure stable transmission of the video stream under different network environments.

[0058] A data integrity verification mechanism is used to retransmit or repair lost or corrupted data. Specifically, Cyclic Redundancy Check (CRC) and Forward Error Correction (FEC) technologies are employed to verify the integrity of data during transmission. Once data loss or corruption is detected, the retransmission or repair mechanism is immediately activated to ensure the integrity and availability of the video stream.

[0059] S5: After receiving the encrypted video stream, the receiving end decrypts it using the corresponding decryption algorithm according to the encryption strategy, restoring the original video content.

[0060] In this step, the video stream is decrypted using the corresponding decryption algorithm according to the encryption strategy, restoring the original video content. The main task of this module is to ensure the accuracy and efficiency of the decryption process. The specific implementation is as follows:

[0061] The decryption algorithm dynamically adjusts its decryption parameters based on the encryption strategy. Specifically, this is achieved through a parameter adaptation module within the decryption algorithm, which dynamically adjusts the decryption parameters according to the encryption parameters specified in the encryption strategy. For example, the parameters of the decryption algorithm are dynamically adjusted based on the key length and encryption mode used during encryption.

[0062] Machine learning models are used to predict potential errors during the decryption process, allowing for proactive corrective measures. Specifically, deep learning models are used to monitor data in real time during decryption, predicting possible errors such as key errors and data format errors. An adaptive error correction mechanism is then employed to promptly correct these errors, improving the accuracy and efficiency of decryption.

[0063] Through the above specific implementation methods, this application can achieve efficient and secure encryption and decryption processing of video streams, ensuring stable transmission and accurate decryption of video streams under different network environments.

[0064] This application also provides an artificial intelligence-based video stream encryption and decryption system. The system may include:

[0065] The preprocessing module is used to preprocess the input video stream, remove noise, and adjust the resolution;

[0066] The feature extraction module is used to extract features from the preprocessed video stream using artificial intelligence algorithms. The extracted features include the texture, color, and shape features of the image, as well as the time series features of the video stream.

[0067] The encryption module is used to dynamically generate encryption strategies based on the extracted video stream features using an artificial intelligence model, including selecting the encryption algorithm, determining the key generation method and length;

[0068] The transmission module is used to encrypt the video stream according to the generated encryption strategy and transmit the encrypted video stream over the network.

[0069] After receiving the encrypted video stream, the receiving end decrypts it using the corresponding decryption algorithm according to the encryption policy, restoring the original video content.

[0070] For specific limitations regarding AI-based video stream encryption and decryption systems, please refer to the limitations of AI-based video stream encryption and decryption methods mentioned above, which will not be repeated here. Each module in the aforementioned AI-based video stream encryption and decryption system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0071] In one embodiment, an electronic device is provided, which may be a computer, and its internal structure diagram may be as follows: Figure 2 As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for encrypting and decrypting video stream data based on artificial intelligence. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an artificial intelligence-based video stream encryption and decryption method.

[0072] Those skilled in the art will understand that, Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0073] In one embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described artificial intelligence-based video stream encryption and decryption method.

[0074] In one embodiment of this application, a computer program product is provided, including a computer program / instructions, which, when executed by a processor, implements the steps of the above-described AI-based video stream encryption and decryption method.

[0075] The computer-readable storage medium and computer program product provided in this embodiment are similar in implementation principle and technical effect to the above method embodiments, and will not be repeated here.

[0076] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in M ​​forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Memory Bus Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM), etc.

[0077] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0078] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A video stream encryption and decryption method based on artificial intelligence, characterized in that, The method includes: The input video stream is preprocessed to remove noise and adjust the resolution; Artificial intelligence algorithms are used to extract features from the preprocessed video stream. The extracted features include the texture, color, and shape features of the image, as well as the time series features of the video stream. Based on the extracted video stream features, an artificial intelligence model is used to dynamically generate encryption strategies, including selecting encryption algorithms, determining key generation methods and lengths; The video stream is encrypted according to the generated encryption strategy, and the encrypted video stream is transmitted over the network. After receiving the encrypted video stream, the receiving end decrypts it using the corresponding decryption algorithm according to the encryption strategy, restoring the original video content. In the encryption strategy generation step, a machine learning model is used to analyze the relationship between video stream characteristics and security requirements. Specifically, a decision tree model is constructed to dynamically select either a symmetric or asymmetric encryption algorithm based on the importance and real-time requirements of the video stream. Furthermore, a genetic algorithm is used to optimize the key length and encryption parameters. The genetic algorithm iteratively optimizes the key length and encryption parameters by simulating a natural selection process. The encryption strategy also includes dynamically adjusting the encryption mode of the encryption algorithm based on the type of video stream and the application scenario, including electronic codebook mode or cryptographic blockchain mode. In the video stream encryption process, the encryption algorithm dynamically adjusts the encryption strength according to the network environment. Specifically, it adjusts the encryption strength of the encryption algorithm in real time by monitoring network bandwidth, latency, and packet loss rate parameters. During the encryption process, potential risk points are predicted through neural networks, and encryption parameters are adjusted in advance to ensure the stability of the encryption process. Specifically, deep neural networks are used to monitor the data in real time during the encryption process, predict possible encryption errors or security vulnerabilities, and adjust encryption parameters in a timely manner. The encryption parameters include key update frequency and encryption block size.

2. The video stream encryption / decryption method according to claim 1, characterized in that, In the preprocessing step, an adaptive filtering algorithm is used to remove noise from the video stream. The adaptive filtering algorithm includes dynamically adjusting the filtering parameters according to the noise type and intensity of the video stream. The resolution is dynamically adjusted based on the resolution and bitrate of the video stream. Specifically, by analyzing the clarity requirements and transmission bandwidth limitations of the video stream, an appropriate resolution adjustment strategy is selected to optimize subsequent processing efficiency while ensuring smooth transmission of the video stream under different network environments.

3. The video stream encryption / decryption method according to claim 1, characterized in that, In the feature extraction step, a convolutional neural network is used to extract features from each frame of the video stream. The extracted feature vectors include the image's texture features, color distribution features, and inter-frame motion change features. Specifically, the convolutional neural network model contains multiple convolutional layers, pooling layers, and fully connected layers. By training with a large amount of labeled video frame data, it can automatically learn high-level feature representations of images. Temporal series features are extracted through a long short-term memory network to analyze the dynamic changes of the video stream. The long short-term memory network model can capture the long-term dependencies between frames in the video stream and extract the temporal series feature vector of the video stream.

4. The video stream encryption / decryption method according to claim 1, characterized in that, In the video stream transmission step, artificial intelligence algorithms are used to monitor the network environment in real time, including parameters such as bandwidth, latency, and packet loss rate. Specifically, a sensor network deployed on network nodes collects network status data in real time, and machine learning algorithms are used for data analysis and prediction. Based on the monitoring results, the encoding format and resolution of the video stream are dynamically adjusted. Specifically, adaptive encoding technology is used to dynamically select the appropriate encoding format based on the network status and adjust the resolution of the video stream to ensure stable transmission of the video stream in different network environments. Meanwhile, a data integrity verification mechanism is used to retransmit or repair lost or damaged data. Specifically, cyclic redundancy check and forward error correction coding technology are used to verify the integrity of data during transmission. Once data loss or damage is detected, the retransmission or repair mechanism is immediately activated to ensure the integrity and availability of the video stream.

5. The video stream encryption / decryption method according to claim 1, characterized in that, In the video stream decryption step, the decryption algorithm dynamically adjusts the decryption parameters according to the encryption strategy. Specifically, the parameter adaptive module in the decryption algorithm dynamically adjusts the decryption parameters according to the encryption parameters in the encryption strategy. Machine learning models are used to predict potential errors during the decryption process and correct them in advance. Specifically, deep learning models are used to monitor the data in real time during the decryption process, predict possible decryption errors, including key errors and data format errors, and correct errors in a timely manner through an adaptive error correction mechanism.

6. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the video stream encryption / decryption method as described in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the video stream encryption / decryption method as described in any one of claims 1 to 5.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the video stream encryption / decryption method according to any one of claims 1 to 5.

Images