A video data collaborative management method and system integrating card storage and cloud storage

Abstract

The present invention discloses a video data collaborative management method and system integrating card storage and cloud storage, belonging to the technical field of data management, and specifically comprising: detecting whether card storage and cloud storage are turned on for any monitoring device through a device control platform; encoding the audio and video collected by the monitoring device and synthesizing them into a video file, and when the storage capacity of the storage card reaches a preset capacity, dividing the current video file into a plurality of video frames, extracting key frames, uploading the current video file to the cloud storage and deleting it locally; selecting key video segments in the current video file, saving the entire video file in a low-speed partition, and storing the key video segments in a high-speed partition; sending a play instruction or a download instruction to a storage card device and a cloud storage server according to a user query; the present invention enables users to seamlessly switch and access video data between different devices and platforms.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a method and system for collaboratively managing video data integrating card storage and cloud storage. Background Art

[0002] With the widespread deployment of surveillance cameras and the continuous advancement of HD and UHD video technology, the amount of video data is growing at an alarming rate. Traditional storage methods, such as relying solely on device cards for storage, face significant limitations such as limited capacity, vulnerability to damage, and easy data loss, making them unable to meet the needs of large-capacity, long-term storage.

[0003] To effectively address this challenge while meeting the needs of diverse users for small-capacity, short-term storage, we have designed a collaborative video data management method and system that integrates card-based storage with cloud storage. This system aims to achieve efficient, secure, and flexible management of video data by combining the immediacy and flexibility of local device cards with the unlimited scalability and high reliability of cloud storage.

[0004] In this method, video data can be uploaded to the cloud in real time for long-term storage and backup, while the local device card is used to temporarily store recent video data, thus taking into account the storage needs in different scenarios.

[0005] Currently, a relatively close approach to achieving collaborative management of video data between device card storage and cloud storage is to separate the card storage function and cloud storage function on the device side. In this approach, video data storage is clearly divided into two independent parts: one is local device card storage, and the other is cloud storage. However, video data is typically stored by time period. When querying surveillance video for a specific feature, it is still necessary to traverse the data of both the memory card and cloud storage simultaneously. However, due to the different reading speeds and capacities of memory cards and cloud storage, users cannot smoothly switch between different storage devices to view data, which affects the efficiency of users in obtaining effective information. Summary of the Invention

[0006] The purpose of the present invention is to provide a video data collaborative management method and system that integrates card storage and cloud storage to solve the following technical problems:

[0007] However, video data is usually stored according to time periods. When a surveillance video with a certain feature needs to be queried, users cannot smoothly switch and view data from different storage ends, which affects the efficiency of users in obtaining effective information.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] A video data collaborative management method integrating card storage and cloud storage includes the following steps:

[0010] Use the device control platform to detect whether card storage and cloud storage are enabled on any monitoring device, and set the corresponding card storage configuration and cloud storage configuration;

[0011] Encode the audio and video collected by the monitoring equipment and synthesize them into a video file. The video file is first saved to the memory card. When the storage capacity of the memory card reaches the preset capacity, the current video file is divided into several video frames, and key frames are extracted from the video frames according to the set keywords;

[0012] Save the key frame to the memory card, upload the current video file to the cloud storage and delete it locally;

[0013] In the cloud storage, a video segment containing a key frame in the current video file is selected and marked as a key video segment, where the duration of the key video segment is t and the key frame is the middle frame of the key video segment; the cloud storage is divided into a high-speed partition and a low-speed partition, the entire video file is stored in the low-speed partition, and the key video segment is stored in the high-speed partition;

[0014] Based on the query keywords entered by the user on the platform query page, the corresponding key frames and key video segments are retrieved in the storage card and high-speed partition through a private protocol, and the corresponding key frames and links to the key video segments are displayed. Based on the user's choice, playback instructions or download instructions are sent to the storage card device and cloud storage server.

[0015] As a further solution of the present invention: the specific process of extracting key frames is:

[0016] Obtain the compression code of each video frame, exclude the inter-frame compression-coded video frames, retain the intra-frame compression-coded video frames, mark them as pending frames, encode the pending frames into a common vector space based on a pre-trained ResNet model, output an image feature vector, index the image feature vector, associate the indexed image feature vector with the video frame ID, and store it in a constructed video feature database; encode the set keywords into a common vector space based on a pre-trained BERT model, output a text feature vector, and for any text feature vector, search the video feature database for the index corresponding to the image feature vector closest to the text feature vector. If the pending frame corresponding to the index matches the keyword, the pending frame is marked as a key frame.

[0017] As a further solution of the present invention, the specific process of storing the video file in the memory card is as follows:

[0018] The SDK provided by the chip is used to encode audio and video, and the video files are synthesized according to a specific private protocol. When the platform issues the card storage configuration, the monitoring device checks whether the memory card has been mounted to the Linux directory and confirms its normal availability. If the memory card status meets the requirements, the monitoring device saves the synthesized video files to the memory card.

[0019] As a further solution of the present invention: the training process of the ResNet model and the BERT model is:

[0020] S1: Collect a sample data set, which includes pre-paired keywords and corresponding key images, and collect n pairs of paired samples;

[0021] S2: The key images and keywords in all sample pairs are input into the ResNet model and the BERT model respectively. The ResNet model outputs the image feature vector I n , the BERT model outputs the text feature vector T n , pair each image feature vector with all text feature vectors in turn to obtain several sample pairs, and mark the pre-corresponding sample pairs as I i T i , as positive sample pairs, the sample pairs that are not pre-paired are marked as I i T g , as a negative sample pair, i=1,2,...,n, g=1,2,...,n, i≠g;

[0022] S3: Calculate the similarity S of the sample pair and the model loss function L using the following formula:

[0023] ;

[0024] ;

[0025] In the similarity formula, A j and B j Represent the components of vectors I and T, i∈1,...,n, respectively. In the model loss function, the coefficients is a set hyperparameter, e is a natural constant, q and k represent text feature vectors and image feature vectors respectively, where k+ represents a positive sample, k j Represents the jth sample; the numerator of the model loss function L represents the similarity between positive examples, and the denominator represents the similarity between positive examples and negative examples;

[0026] S4: Calculate the sample similarity and loss function, and adjust the model parameters according to the calculation results so that the similarity of positive samples approaches 1 and the similarity of negative samples approaches 0. When the output value of the loss function L is less than or equal to the preset threshold, the model converges and the trained ResNet model and BERT model are obtained.

[0027] As a further solution of the present invention: when the capacity of the key frames stored in the memory card reaches a second preset capacity, the key frames are sorted in chronological order from near to far, and half of the key frames in the back column are uploaded to the high-speed partition of the cloud storage.

[0028] As a further solution of the present invention: the reading and writing speed of the high-speed partition is faster than that of the low-speed partition.

[0029] As a further solution of the present invention: the audio data collected by the monitoring device mic is encoded based on g711a, and the video data collected by the monitoring device sensor is encoded based on H264 / H265.

[0030] The present invention also includes a video data collaborative management system integrating card storage and cloud storage, which is used to implement the above-mentioned video data collaborative management method integrating card storage and cloud storage, including:

[0031] The initialization module is used to detect whether card storage and cloud storage are enabled on any monitoring device through the device control platform, and set the corresponding card storage configuration and cloud storage configuration;

[0032] The video analysis module is used to encode the audio and video collected by the monitoring equipment and synthesize them into a video file. The video file is first saved to the memory card. When the storage capacity of the memory card reaches the preset capacity, the current video file is divided into several video frames and key frames are extracted from the video frames according to the set keywords;

[0033] A data transmission module, used to save the key frames to a memory card, upload the current video file to cloud storage and delete it locally;

[0034] The data management module is configured to select, from the cloud storage, a video segment containing a key frame in the current video file and mark it as a key video segment, where the duration of the key video segment is t and the key frame is an intermediate frame of the key video segment; divide the cloud storage into a high-speed partition and a low-speed partition, store the entire video file in the low-speed partition, and store the key video segment in the high-speed partition;

[0035] The query and download module is used to retrieve the corresponding key frames and key video segments in the storage card and high-speed partition through a private protocol based on the query keywords entered by the user on the platform query page, and display the corresponding key frames and links to the key video segments, and send playback instructions or download instructions to the storage card device and cloud storage server according to the user's selection.

[0036] Beneficial effects of the present invention:

[0037] (1) By storing part of the video data on the device card, the pressure on cloud storage can be reduced and the response speed and processing capability of the device can be improved. At the same time, the device card has a fast read and write speed, which can meet the needs of recording real-time video streams and viewing key information, thereby improving the overall performance of the device.

[0038] (2) Device card storage has limitations such as limited capacity and susceptibility to physical damage, while cloud storage has the characteristics of large capacity, high reliability and scalability. By integrating the two, storage resources can be flexibly allocated according to actual needs, avoiding waste and redundancy of storage resources and improving storage efficiency;

[0039] (3) Preliminary processing and uploading of video data on the device side can ensure the consistency and synchronization of local data with cloud data. This helps users seamlessly switch and access video data between different devices and platforms, improving user experience;

[0040] (4) The present invention combines natural language processing and computer vision technology to fully explore the information contained in each frame from the perspective of video frame image content, including the content appearing in the frame image, the relationship between each content, and the overall description of the frame image. It also establishes a massive video retrieval feature library based on the keyword database, allowing users to quickly find the video information they need. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below with reference to the accompanying drawings.

[0042] Figure 1 This is a module diagram of a video data collaborative management system that integrates card storage and cloud storage according to the present invention;

[0043] Figure 2 This is a schematic diagram of the platform-side configuration device-side storage process of the present invention;

[0044] Figure 3 It is a schematic diagram of the device side storage process of the present invention;

[0045] Figure 4 It is a schematic diagram of the video query, download and playback process of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] See also Figure 1-4 As shown, the present invention provides a method for collaboratively managing video data that integrates card storage and cloud storage. The detailed design scheme involves configuring device functions on the platform to determine whether card storage and cloud storage are supported, and then distributing the relevant parameters to the device. The device extracts key frames from card-stored and video files based on the platform-configured parameters, and implements partitioned storage of video files in the cloud. Based on the device node, the platform can query the corresponding device's cloud-stored and card-stored videos and download or play them.

[0048] The platform side configures the device side storage function:

[0049] Storage Plan Settings: Storage plans are configured on a weekly basis. Users can select the days of the week and time periods for recording based on their needs. After completing the configuration, users can save it as a template and give it a name for quick application or modification.

[0050] Cloud bucket setup: Users need to name the cloud bucket and specify its address, which typically involves selecting a cloud service provider and a specific data center location. To ensure data security, users also need to configure encryption parameters, such as access keys and key management policies.

[0051] Storage Configuration Selection: Based on customer needs, users can choose between card storage, cloud storage, or both. Cloud storage bucket upload parameters can be configured, including the S3 bucket name, whether to enable S3 functionality, specifying a prefix directory, configuring encryption and compression parameters, setting the endpoint address, enabling SSL encrypted communication, specifying the region, and setting access and secret keys. These configurations enable efficient and secure video data management.

[0052] Device-side storage function:

[0053] On the device side, the SDK provided by the chip is used to encode audio and video, and the video files are synthesized according to a specific proprietary protocol. When the platform sends the card storage configuration, the device checks whether the card storage device is mounted to the Linux directory and confirms its normal availability. If all is normal, the device saves the synthesized video to the card storage device. When the card storage device reaches the storage limit, the system automatically overwrites the old video files. In addition, when the platform sends the cloud storage configuration, the device configures the cloud storage settings according to these parameters and securely transmits the video data to the cloud.

[0054] Video query, download and playback function

[0055] On the platform side, users can query and download video files by following the steps below:

[0056] 1. Check the video stored on the card:

[0057] Select a device and enter the video query interface: After the user selects a specific device on the platform, he can enter the video query interface of the device.

[0058] Select Card Recording: In the query interface, users can select the "Card Recording" option to view the local recording data stored on the device.

[0059] Send query command: The platform sends a command to query the video stored in the card to the device side, requiring the device to return the names of all video files currently stored in the card.

[0060] Obtain and display video information: After receiving the command, the device returns the list of video files stored in the card to the platform, and the user can view the information of these video files on the platform.

[0061] 2. Download or play video stored on the card

[0062] Select and play / download video: Users select the video file stored on the card that needs to be downloaded or played on the platform.

[0063] Send play / download instructions: The platform sends corresponding play or download instructions to the device side based on the user's selection.

[0064] Data interaction: After receiving the instruction, the device side sends the corresponding video data back to the platform for users to watch or download according to the requirements of the instruction.

[0065] 3. Query cloud-stored videos

[0066] Select a device and enter the video query interface: Similar to the above steps, the user first needs to select a specific device on the platform.

[0067] Select cloud-stored recordings: In the query interface, users can select the "Cloud-stored recordings" option to view the cloud-stored recording data stored on the device.

[0068] Send query command: The platform sends a request to the cloud storage server, requesting a list of cloud storage videos on the device.

[0069] Obtain and display cloud-stored video information: The cloud-stored server responds to the platform's request and returns a list of cloud-stored videos to the platform. Users can view the information of these video files on the platform.

[0070] 4. Download or play cloud-stored videos

[0071] Select and play / download video: Users select the cloud-stored video file they want to download or play on the platform.

[0072] Send play / download instructions: The platform sends corresponding play or download instructions to the cloud storage server based on the user's selection.

[0073] Data interaction: After receiving the instruction, the cloud storage server sends the corresponding video data back to the platform for users to watch or download according to the requirements of the instruction.

[0074] Through these steps, users can easily query, play and download audio and video recording files on the device side and cloud storage on the platform.

[0075] In another preferred embodiment of the present invention, the specific process of extracting key frames is:

[0076] Obtaining the compression code of the video frame: First, extract the compression code of each frame from the video. These codes usually contain the basic information of the frame image.

[0077] Excluding inter-frame compressed video frames: In video coding, some frames are compressed by referencing surrounding frames (i.e., inter-frame prediction), while others are encoded independently (i.e., intra-frame compression). Here, we exclude frames compressed by inter-frame prediction because they may not contain complete information.

[0078] Keep and mark intra-frame compressed video frames as pending frames: Only those frames that are independently encoded are kept and marked as "pending frames" for subsequent processing.

[0079] Encode the pending frames using a ResNet model: Use a pre-trained ResNet model to encode each pending frame into a common vector space. ResNet is a deep convolutional neural network that is well suited for extracting image features.

[0080] Output image feature vector and compile index: Output the encoded image feature vector and compile an index for each vector.

[0081] Associating image feature vectors with video frame IDs: Associating the indexed image feature vectors with their corresponding video frame IDs and storing this information in the constructed video feature database.

[0082] Encoding keywords using the BERT model: Similarly, using the pre-trained BERT model, the set keywords are also encoded into the same common vector space, outputting a text feature vector. BERT is a powerful natural language processing model that can effectively process and understand text data.

[0083] Matching text feature vectors with image feature vectors: For any text feature vector, find the index of the image feature vector that is closest to it in the video feature database. This "distance" is usually determined by calculating the cosine similarity or other similarity metrics between the two vectors.

[0084] Mark the matching pending frame as a key frame: Once the closest image feature vector is found, it can be determined that the corresponding pending frame matches the keyword. Then, this pending frame is marked as a "key frame".

[0085] In another preferred embodiment of the present invention, the specific process of storing the video file in the memory card is as follows:

[0086] The SDK provided by the chip is used to encode audio and video, and the video files are synthesized according to a specific private protocol. When the platform issues the card storage configuration, the monitoring device checks whether the memory card has been mounted to the Linux directory and confirms its normal availability. If the memory card status meets the requirements, the monitoring device saves the synthesized video files to the memory card.

[0087] In another preferred embodiment of the present invention, the training process of the ResNet model and the BERT model is as follows:

[0088] S1: Collect a sample data set, which includes pre-paired keywords and corresponding key images, and collect n pairs of paired samples;

[0089] S2: The key images and keywords in all sample pairs are input into the ResNet model and the BERT model respectively. The ResNet model outputs the image feature vector I n , the BERT model outputs the text feature vector T n , pair each image feature vector with all text feature vectors in turn to obtain several sample pairs, and mark the pre-corresponding sample pairs as I i T i , as positive sample pairs, the sample pairs that are not pre-paired are marked as I iT g , as a negative sample pair, i=1,2,...,n, g=1,2,...,n, i≠g;

[0090] S3: Calculate the similarity S of the sample pair and the model loss function L using the following formula:

[0091] ;

[0092] ;

[0093] In the similarity formula, A j and B j Represent the components of vectors I and T, i∈1,...,n, respectively. In the model loss function, the coefficients is a set hyperparameter, e is a natural constant, q and k represent text feature vectors and image feature vectors respectively, where k+ represents a positive sample, k j Represents the jth sample; the numerator of the model loss function L represents the similarity between positive examples, and the denominator represents the similarity between positive examples and negative examples;

[0094] S4: Calculate the sample similarity and loss function, and adjust the model parameters according to the calculation results so that the similarity of positive samples approaches 1 and the similarity of negative samples approaches 0. When the output value of the loss function L is less than or equal to the preset threshold, the model converges and the trained ResNet model and BERT model are obtained.

[0095] In another preferred embodiment of the present invention, when the capacity of the key frames stored in the memory card reaches a second preset capacity, the key frames are sorted in chronological order from near to far, and half of the key frames in the back column are uploaded to the high-speed partition of the cloud storage.

[0096] In another preferred embodiment of the present invention, an innovative storage architecture is employed that is particularly suitable for applications requiring efficient data processing and rapid access. In this embodiment, the storage device is divided into two main parts: a high-speed partition and a low-speed partition.

[0097] High-speed partitions utilize advanced storage technologies, such as solid-state drives (SSDs) or non-volatile memory (NVM), which offer extremely high data read and write speeds. The key advantages of high-speed partitions are their low latency and high throughput, making them ideal for frequent read and write operations. For example, in video processing applications, high-speed partitions can be used to store temporary video frame buffers, key frame data, or frequently accessed index information, ensuring fast data retrieval and processing speeds.

[0098] Low-speed partitions use traditional mechanical hard disk drives (HDDs) or other cost-effective but slower storage media. While these devices don't have the same read and write speeds as high-speed partitions, they offer greater storage capacity and lower costs, making them suitable for storing infrequently accessed data such as historical records, backup files, or large amounts of uncompressed video data.

[0099] In another preferred embodiment of the present invention, the audio data captured by the monitoring device's microphone is first fed into an encoder, which compresses it based on the A-law algorithm in the G.711 standard. G.711 is a widely used pulse code modulation (PCM) speech coding standard that provides two compression algorithms: A-law and μ-law. In this embodiment, the A-law algorithm was chosen because it is more common in Europe and other regions and offers good voice quality at a lower bit rate (64 kbps). In this way, the original audio data is effectively compressed, reducing required storage space and bandwidth while maintaining acceptable sound quality.

[0100] The video data captured by the image sensor in the monitoring device is processed by another encoder that supports the H.264 or H.265 video compression standard. Both standards are currently among the most advanced technologies in the field of video coding. They can significantly reduce the amount of data while maintaining high video quality. H.264 is a relatively mature standard and is widely used in various network video transmission and storage scenarios. As its successor, H.265 provides higher compression efficiency and can reduce the file size by about half under the same conditions, but it also requires more powerful processing capabilities. In this embodiment, based on actual needs and system resources, you can choose to use one or both methods to encode the video data.

[0101] The present invention also includes a video data collaborative management system integrating card storage and cloud storage, which is used to implement the above-mentioned video data collaborative management method integrating card storage and cloud storage, including:

[0102] The initialization module is used to detect whether card storage and cloud storage are enabled on any monitoring device through the device control platform, and set the corresponding card storage configuration and cloud storage configuration;

[0103] The video analysis module is used to encode the audio and video collected by the monitoring equipment and synthesize them into a video file. The video file is first saved to the memory card. When the storage capacity of the memory card reaches the preset capacity, the current video file is divided into several video frames and key frames are extracted from the video frames according to the set keywords;

[0104] A data transmission module, used to save the key frames to a memory card, upload the current video file to cloud storage and delete it locally;

[0105] The data management module is configured to select, from the cloud storage, a video segment containing a key frame in the current video file and mark it as a key video segment, where the duration of the key video segment is t and the key frame is an intermediate frame of the key video segment; divide the cloud storage into a high-speed partition and a low-speed partition, store the entire video file in the low-speed partition, and store the key video segment in the high-speed partition;

[0106] The query and download module is used to retrieve the corresponding key frames and key video segments in the storage card and high-speed partition through a private protocol based on the query keywords entered by the user on the platform query page, and display the corresponding key frames and links to the key video segments, and send playback instructions or download instructions to the storage card device and cloud storage server according to the user's selection.

[0107] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A video data collaborative management method integrating card storage and cloud storage, characterized in that: The following steps are involved: Use the device control platform to detect whether card storage and cloud storage are enabled on any monitoring device, and set the corresponding card storage configuration and cloud storage configuration; Encode the audio and video collected by the monitoring equipment and synthesize them into video files. First, save the video files to the memory card. When the storage capacity of the memory card reaches the preset capacity, divide the current video file into several video frames, and extract key frames from the video frames according to the set keywords; The key frame is saved to the memory card, the current video file is uploaded to the cloud storage and deleted locally; In the cloud storage, a video segment where a key frame is located in the current video file is selected and marked as a key video segment, wherein the duration of the key video segment is t, and the key frame is an intermediate frame of the key video segment; the cloud storage is divided into a high-speed partition and a low-speed partition, the entire video file is stored in the low-speed partition, and the key video segment is stored in the high-speed partition; According to the query keywords entered by the user on the platform query page, the corresponding key frames and key video segments are retrieved in the storage card and high-speed partition through a private protocol, and the corresponding key frames and links to the key video segments are displayed. According to the user's choice, playback instructions or download instructions are sent to the storage card device and cloud storage server.

2. The video data collaborative management method integrating card storage and cloud storage according to claim 1 is characterized in that: The specific process of extracting key frames is: Obtain the compression code of each video frame, exclude the video frames with inter-frame compression code, retain the video frames with intra-frame compression code, mark them as pending frames, encode the pending frames into the common vector space based on the pre-trained ResNet model, output the image feature vector, index the image feature vector, associate the indexed image feature vector with the video frame ID and store it in the constructed video feature database; encode the set keywords into the common vector space based on the pre-trained BERT model, output the text feature vector, for any text feature vector, search the video feature database for the index corresponding to the image feature vector that is closest to the text feature vector, then the pending frame corresponding to the index matches the keyword, and the pending frame is marked as a key frame.

3. The video data collaborative management method integrating card storage and cloud storage according to claim 1 is characterized in that: The specific process of saving video files in the memory card is as follows: Use the SDK provided by the chip to encode the audio and video, and synthesize the video file according to a specific private protocol. When the platform sends the card storage configuration, the monitoring device will check whether the memory card has been mounted to the Linux directory and confirm its normal availability. If the memory card status meets the requirements, the monitoring device will save the synthesized video file to the memory card.

4. The video data collaborative management method integrating card storage and cloud storage according to claim 1, characterized in that: The training process of ResNet model and BERT model is as follows: S1: Collect a sample data set, wherein the sample data set includes pre-paired keywords and corresponding key images, and collect n pairs of paired sample pairs; S2: The key images and keywords in all sample pairs are input into the ResNet model and the BERT model respectively, and the ResNet model outputs the image feature vector I n , the BERT model outputs the text feature vector T n , pair each image feature vector with all text feature vectors in turn to obtain several sample pairs, and mark the pre-corresponding sample pairs as I i T i , as positive sample pairs, and mark the sample pairs that are not pre-paired as I i T g , as a negative sample pair, i=1,2,...,n, g=1,2,...,n, i≠g; S3: Calculate the similarity S of the sample pair and the model loss function L by the following formula: ； ； In the similarity formula, A j and B j Represent the components of vectors I and T, i∈1,...,n, respectively. In the model loss function, the coefficient is a set hyperparameter, e is a natural constant, q and k represent text feature vectors and image feature vectors respectively, where k+ represents a positive sample, k j represents the jth sample; the numerator of the model loss function L represents the similarity between positive examples, and the denominator represents the similarity between positive examples and negative examples; S4: Calculate the similarity of samples and the loss function, and adjust the model parameters according to the calculation results so that the similarity of positive samples approaches 1 and the similarity of negative samples approaches 0. When the output value of the loss function L is less than or equal to the preset threshold, the model converges and the trained ResNet model and BERT model are obtained.

5. The video data collaborative management method integrating card storage and cloud storage according to claim 1 is characterized in that: When the capacity of the key frames stored in the memory card reaches a second preset capacity, the key frames are sorted from recent to far in chronological order, and half of the key frames in the last column are uploaded to the high-speed partition of the cloud storage.

6. The video data collaborative management method integrating card storage and cloud storage according to claim 1, characterized in that: The reading and writing speed of the high-speed partition is faster than that of the low-speed partition.

7. The video data collaborative management method integrating card storage and cloud storage according to claim 1 is characterized in that: The audio data collected by the monitoring device mic is encoded based on g711a, and the video data collected by the monitoring device sensor is encoded based on H264 / H265.

8. A video data collaborative management system integrating card storage and cloud storage, used to implement a video data collaborative management method integrating card storage and cloud storage as claimed in any one of claims 1 to 7, characterized in that: include: The initialization module is used to detect whether the card storage and cloud storage are turned on for any monitoring device through the device control platform, and set the corresponding card storage configuration and cloud storage configuration; The video analysis module is used to encode the audio and video collected by the monitoring equipment and synthesize them into a video file. The video file is first saved to the memory card. When the storage capacity of the memory card reaches the preset capacity, the current video file is divided into several video frames, and key frames are extracted from the video frames according to the set keywords; A data transmission module, used to save the key frame to a memory card, upload the current video file to a cloud storage and delete it locally; The data management module is used to select the video segment where the key frame is located in the current video file in the cloud storage, mark it as the key video segment, the duration of the key video segment is t, and the key frame is the middle frame of the key video segment; divide the cloud storage into a high-speed partition and a low-speed partition, save the entire video file in the low-speed partition, and store the key video segment in the high-speed partition; The query and download module is used to retrieve the corresponding key frames and key video segments in the storage card and high-speed partition through a private protocol according to the query keywords entered by the user on the platform query page, and display the corresponding key frames and links to the key video segments, and send playback instructions or download instructions to the storage card device and cloud storage server according to the user's selection.

Images