A method and system for secure transmission of electronic information privacy data

Abstract

The present invention relates to the field of video data processing technology, and in particular to a method and system for secure transmission of electronic information privacy data, the method comprising: iteratively segmenting the video data to be transmitted as target video frames in turn, analyzing the grayscale distribution of pixel blocks of the target video frames, the degree of grayscale difference in the neighborhood, and the gradient characteristics of document information distribution, constructing the intra-frame detail segmentation requirement, document segmentation correction coefficient, and document segmentation penalty factor; obtaining the intra-frame document correction segmentation requirement; analyzing the grayscale difference of pixel blocks at the same position of the target video frame and the video frame in the time neighborhood, constructing a grayscale motion index sequence and an inter-frame motion change rate; obtaining dynamic information complexity; and using a long edge conditional segmentation method to achieve adaptive dynamic segmentation of video frames to complete video optimization transmission. The present invention aims to achieve adaptive dynamic segmentation of video frames, retaining details while achieving better transmission effects.

Description

Technical Field

[0001] The present application relates to the technical field of video data processing, and in particular to a method and system for securely transmitting electronic information privacy data. Background Art

[0002] The video conferencing system integrates multiple technologies and hardware terminals such as video imaging and voice coding. The front-end acquisition module can collect video electronic information data, which is transmitted to different terminals through the network to establish a complete video conferencing system. However, due to limitations of network bandwidth, latency, and stability, the video quality may be affected, resulting in blur, freeze, or delay. Therefore, in order to improve the video quality of the appointment-based integrated conference system, an optimized transmission method is required.

[0003] Video coding is the process of converting video signals into digital data. In the appointment-based integrated conference system, the widely used video coding standards include H.264 and H.265. These coding standards use compression algorithms to reduce the amount of video data so that it can be transmitted under limited bandwidth. In the process of video compression coding, for each frame of the image, there is usually a certain correlation between adjacent pixels. In order to reduce information redundancy, the image is divided into blocks, and only the difference information between the coding blocks needs to be transmitted, rather than the pixel value of the entire image. At the same time, block division can also more accurately realize motion estimation and motion compensation between different video frames. However, when the block is large, it will cause more loss of detail information during compression, resulting in a decrease in the quality of video transmission; when the block is small, the image compression ratio will be reduced, and the data content to be transmitted will increase, thereby affecting the video transmission rate. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for secure transmission of electronic information privacy data to solve the existing problems. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for securely transmitting electronic information privacy data, the method comprising the following steps:

[0006] Obtain electronic information video data of online meetings and perform preprocessing;

[0007] The video data of each frame to be transmitted is sequentially used as the target video frame; in the process of iterative segmentation of the target video frame, the in-frame detail segmentation requirement of each pixel block is obtained according to the grayscale distribution of each pixel block of the target video frame; for each pixel block of the target video frame, the document segmentation correction coefficient and the document segmentation penalty factor of each pixel point are obtained according to the gradient distribution of all pixel points of the pixel block and the grayscale difference degree of the neighborhood of each pixel point; the in-frame document correction segmentation requirement of each pixel block is obtained according to the relationship between the in-frame detail segmentation requirement of each pixel block of the target video frame and the document segmentation penalty factor;

[0008] According to the grayscale change characteristics of each pixel block in the target video frame in the time neighborhood, the grayscale motion index sequence of each pixel block in the target video frame is constructed; according to the element distribution characteristics of the grayscale motion index sequence of each pixel block in the target video frame, the inter-frame motion change rate of each pixel block in the target video frame is obtained; and the dynamic information complexity of each pixel block in the target video frame is obtained by combining the inter-frame motion change rate of each pixel block in the target video frame and the intra-frame document correction segmentation requirement;

[0009] According to the dynamic information complexity of each pixel block of the target video frame, the long edge conditional segmentation method is used to realize the adaptive dynamic segmentation of the video frame; according to the segmented pixel blocks, the H.264 standard is used to complete the video optimization transmission.

[0010] Preferably, the step of obtaining the intra-frame detail segmentation requirement of each pixel block according to the grayscale distribution of each pixel block in the target video frame includes:

[0011] For each pixel block of the target video frame, the pixels with the same grayscale value in the pixel block are classified into one category to obtain the number of types of the pixel blocks; the grayscale mean and grayscale standard deviation of all the pixel points in the pixel block are calculated; the absolute value of the difference between the grayscale value of each pixel point in the pixel block and the grayscale mean is calculated; the absolute value of the difference of all the pixel points in the pixel block is averaged; the product of the number of types, the grayscale standard deviation and the result is used as the intra-frame detail segmentation requirement of the pixel block; wherein, before the iterative segmentation, the pixel block is the target video frame, and during the iterative segmentation process, each pixel block is the result of the target video frame after the previous iterative segmentation.

[0012] Preferably, for each pixel block of the target video frame, the document segmentation correction coefficient and the document segmentation penalty factor of each pixel are obtained according to the gradient distribution of all pixels in the pixel block and the grayscale difference degree of the neighborhood of each pixel, specifically:

[0013] Taking each pixel point of the pixel block as the center, a neighborhood with a side length of W is obtained, where W is a preset value; calculating the absolute value of the difference between the grayscale value of each pixel point in the pixel block and the remaining pixel points in the neighborhood; calculating the average of the absolute value of the difference calculated for each pixel point in the pixel block; obtaining the gradient mean and gradient standard deviation of all pixel points in the neighborhood of each pixel point in the pixel block; taking the product of the gradient mean, the gradient standard deviation and the mean as the document segmentation correction coefficient of each pixel point;

[0014] The average value of the document segmentation correction coefficients of all pixel points in each pixel block of the target video frame is recorded as the document segmentation penalty factor of each pixel block.

[0015] Preferably, the intra-frame document correction segmentation requirement of each pixel block of the target video frame is specifically:

[0016] The product of the intra-frame detail segmentation requirement and the document segmentation penalty factor of each pixel block of the target video frame is calculated, and the normalized value of the product is used as the intra-frame document correction segmentation requirement of each pixel block of the target video frame.

[0017] Preferably, the grayscale motion index sequence of each pixel block of the target video frame is constructed according to the grayscale change characteristics of each pixel block of the target video frame in the time neighborhood, and the specific expression is:

[0018]

[0019] In the formula, Represents the value of the grayscale motion index sequence of the i-th pixel block of the target video frame at the t-th moment; Represents the number of pixels in the i-th pixel block in the target video frame; Represents the gray value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-th moment in the time neighborhood of the target video frame; Represents the grayscale value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-1th moment in the time neighborhood of the target video frame.

[0020] Preferably, the motion reference frame is specifically a video frame at S moments centered on the target video frame, where S is a preset value.

[0021] Preferably, the step of obtaining the inter-frame motion change rate of each pixel block of the target video frame according to the element distribution characteristics of the grayscale motion index sequence of each pixel block of the target video frame comprises:

[0022] For each pixel block of the target video frame, the extreme value of the grayscale motion index sequence of the pixel block is obtained; the ratio of each element of the grayscale motion index sequence of the pixel block to the extreme value is calculated; and the average of the ratios of all elements of the grayscale motion index sequence of the pixel block is taken as the inter-frame motion change rate of the pixel block.

[0023] Preferably, the dynamic information complexity of each pixel block of the target video frame is specifically a normalized value of the product of the inter-frame motion change rate of each pixel block of the target video frame and the intra-frame document correction segmentation requirement.

[0024] Preferably, the method of implementing adaptive dynamic segmentation of the video frame by using the long edge conditional segmentation method according to the dynamic information complexity of each pixel block of the target video frame includes:

[0025] A segmentation threshold is set. When each pixel block of the target video frame meets the segmentation condition, the long-side condition segmentation method is used to evenly divide the pixel block into two parts according to the longest side of the pixel block; wherein the segmentation condition is: the dynamic information complexity of the pixel block is greater than the segmentation threshold.

[0026] In a second aspect, an embodiment of the present invention further provides a system for securely transmitting electronic information privacy data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0027] The present invention has at least the following beneficial effects:

[0028] The present invention realizes dynamic adaptive division of pixel blocks in the process of optimizing transmission of traditional video, thereby improving the compression rate and transmission quality of video transmission. Specifically, by analyzing the grayscale distribution of pixel blocks in the video frame, and combining the gradient characteristics of document information to obtain the intra-frame document correction segmentation requirement of each pixel block, the document information and detail richness of each pixel block in the target video frame are measured; then, by analyzing the grayscale change of pixel blocks at the same position in the time neighborhood of the target video frame, the inter-frame motion change rate of each pixel block is analyzed to measure the motion change characteristics of the pixel blocks in the target video frame in the time neighborhood; the dynamic information complexity of each pixel block is calculated in combination with the above intra-frame document correction segmentation requirement, and an adaptive dynamic block segmentation method for video frames is realized, which can effectively avoid the loss of more detail information during video transmission due to excessive block segmentation, and the problem of low compression ratio due to too small segmentation, and at the same time, it can avoid the incomplete image segmentation caused when the same frame image is divided into blocks of different sizes, so that the video image details are retained while achieving better transmission effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A flowchart of a method and system for securely transmitting electronic information privacy data provided by the present invention;

[0031] Figure 2 Flowchart for obtaining dynamic information complexity. DETAILED DESCRIPTION

[0032] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a method and system for secure transmission of electronic information privacy data proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0033] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0034] The following is a detailed description of a method and system for securely transmitting electronic information privacy data provided by the present invention in conjunction with the accompanying drawings.

[0035] An embodiment of the present invention provides a method and system for securely transmitting electronic information privacy data.

[0036] Specifically, the following electronic information privacy data secure transmission method and system are provided, please refer to Figure 1 , the method comprises the following steps:

[0037] Step S001: Acquire electronic information video data of the online conference and perform pre-processing.

[0038] This embodiment uses a multi-person video conference in the company as the background, and dynamically adjusts the size of each segment of the target video frame according to the details and degree of change of the target video frame, thereby realizing real-time optimization of video transmission to ensure that the picture is smoothly transmitted to the terminal of each participant. When multiple people are online at the same time, providing efficient video transmission is very important to ensure the smooth progress of the meeting. When optimizing the transmission of video data, sampling is performed at a frequency of 30 frames per second to obtain the video frame stream data corresponding to the meeting, and then the original video frame is subjected to image preprocessing, including image denoising, sharpening and other operations. This embodiment uses bilateral filtering to remove noise in the image and uses the Laplace operator to sharpen the image. This is a known technology and will not be described in detail here.

[0039] At this point, the electronic information video data to be transmitted is obtained.

[0040] Step S002: Analyze the detail level of the video frame and construct the intra-frame detail segmentation requirement; analyze the possibility of document information being contained in the video frame, construct a document segmentation penalty factor, and obtain the intra-frame detail segmentation requirement of the video frame pixel block.

[0041] In predictive coding, the pixel data in the current image frame (I frame) can be predicted by the previous reference frame (P frame or B frame), thereby reducing the redundancy of the data and achieving the purpose of compressing the video. Therefore, if the consecutive frames in the video are similar, then predictive coding can work better, thereby improving the video quality. This embodiment mainly considers appointment-based integrated conferences. Since most of its video content is PPT reports, keynote speeches and other activities, these activities usually keep the pictures relatively similar for a long time, so better optimization effects can be obtained when performing video transmission.

[0042] In video transmission, in order to maintain the transmission rate, it is usually necessary to compress and encode the video data before real-time transmission. Conventional video coding standards include H.264 (AVC) and H.265 (HEVC), etc. The encoding process includes time compression and space compression. In space compression, each frame in the video is divided into multiple blocks, and then each block is independently discrete cosine transformed, which can reduce the local redundant information inside the image.

[0043] In this embodiment, each frame of video data to be transmitted is analyzed as a target video frame in turn, and the detail richness of the video frame is evaluated to select a suitable block segmentation size. In this embodiment, the long edge condition segmentation method is considered to dynamically segment the target video frame, and the analysis is carried out based on the pixel block. For the convenience of description, all pixel blocks in the target video frame are numbered from left to right and from top to bottom according to the segmentation state. It should be noted that before the iterative segmentation, the pixel block is the target video frame, and during the iterative segmentation process, each pixel block is the result of the previous iterative segmentation of the target video frame.

[0044] First, the grayscale distribution of each pixel block in the target video frame is analyzed, and the intra-frame detail segmentation requirement of the pixel block is calculated. The expression is:

[0045]

[0046] In the formula, Indicates the intra-frame detail segmentation requirement of the i-th pixel block in the target video frame; Indicates the number of types of pixels in the i-th pixel block in the target video frame; Represents the number of pixels in the i-th pixel block in the target video frame; Represents the gray value of the jth pixel in the i-th pixel block in the target video frame; Represents the grayscale mean of all pixels in the i-th pixel block in the target video frame; represents the grayscale standard deviation of all pixels in the ith pixel block in the target video frame. It should be noted that the method for obtaining the number of types of pixels in the ith pixel block is: classifying the pixels with the same grayscale value in the ith pixel block into one type.

[0047] When there are more types of grayscale value distribution in a pixel block, and the difference in pixel grayscale value distribution is greater, that is, the standard deviation is larger, it indicates that there are more details inside the pixel block, and the current pixel block needs further segmentation, that is, the greater the demand for intra-frame detail segmentation, so that richer detail information can be retained in video transmission. Conversely, it indicates that the inside of the pixel block is smoother and the details are fewer, and the current pixel block does not need further segmentation, that is, the demand for intra-frame detail segmentation is lower, so that the data compression rate during video transmission is higher.

[0048] However, considering that high-contrast text information will appear in the pixel blocks of the target video frame, the pixel values ​​of the text information are concentrated in one area. At this time, the text pixel area presents relatively few gray levels. If distortion occurs during image compression or transmission, the clarity and readability of the text information may decrease, affecting the user's viewing experience. Therefore, when processing pixel blocks containing text information, more details need to be retained for the text information to ensure the clarity and readability of the text information. Therefore, although the pixel gray value distribution is relatively concentrated at this time, the document should also be further segmented.

[0049] Since the pixel blocks containing text information are distributed differently from other pixel blocks, the grayscale values ​​of the former are usually more concentrated, and the gradient values ​​between pixels are also more concentrated and change more extreme, that is, the gradient is too large or too small; while the pixel changes of the latter are more gentle, and the grayscale value distribution is more discrete. For the i-th pixel block in the target video frame, the gradient value of each pixel point is calculated by the Sobel operator to obtain the gradient distribution map of the pixel block , where each element represents the grayscale gradient size of the pixel point, wherein obtaining the gradient distribution map by the Sobel operator is a well-known technique and will not be described here. Then, taking each pixel point in the i-th pixel block as the center, a neighborhood with a side length of W is obtained. In this embodiment, W is 5. Further, according to the gradient distribution map of the i-th pixel block and the grayscale distribution characteristics of the neighborhood of the pixel point, the document segmentation correction coefficient of each pixel point in the pixel block is calculated. The expression is:

[0050]

[0051] In the formula, represents the document segmentation correction coefficient of the jth pixel in the i-th pixel block in the target video frame; Represents the total number of neighborhood pixels of the jth pixel in the i-th pixel block in the target video frame; Represents the gray value of the jth pixel in the i-th pixel block in the target video frame; Represents the gray value of the kth pixel in the neighborhood of the jth pixel in the i-th pixel block in the target video frame; Represents the mean value of the neighborhood pixel gradient of the jth pixel in the i-th pixel block in the target video frame; Represents the standard deviation of the neighborhood pixel gradient of the jth pixel in the i-th pixel block in the target video frame.

[0052] Furthermore, the document segmentation penalty factor of the i-th pixel block is calculated according to the distribution of the document segmentation correction coefficients of all pixels in the i-th pixel block, and the expression is:

[0053]

[0054] In the formula, represents the document segmentation penalty factor of the i-th pixel block in the target video frame; represents the document segmentation correction coefficient of the jth pixel in the i-th pixel block in the target video frame; Indicates the number of pixels in the i-th pixel block in the target video frame.

[0055] The greater the difference in grayscale value between the jth pixel point of the ith pixel block in the target video frame and its surrounding neighborhood pixels, that is, the more obvious the grayscale change is, it indicates that the pixel point is more likely to contain the edge stroke information of the text, and its document segmentation correction coefficient should be larger. If the document segmentation correction coefficient of all pixels in the pixel block is larger, it means that the possibility of the pixel block containing document information is greater; conversely, the smaller the document segmentation correction coefficient is, the less likely the pixel block contains document information, and its document segmentation penalty factor should be smaller; at the same time, when the grayscale gradient standard deviation and mean of the neighborhood of each pixel point in the pixel block are larger, it indicates that the pixel point is more likely to be the document area, and its document penalty factor should be larger. Conversely, it indicates that the pixel point is less likely to be the document area, and its document penalty factor should be smaller.

[0056] In summary, this embodiment combines the intra-frame detail segmentation requirement and the document segmentation penalty factor to obtain the intra-frame document correction segmentation requirement in the same video frame, as follows:

[0057]

[0058] In the formula, represents the intra-frame document correction segmentation requirement of the i-th pixel block in the target video frame; Indicates the intra-frame detail segmentation requirement of the i-th pixel block in the target video frame; Represents the document segmentation penalty factor for the i-th pixel block in the target video frame.

[0059] At this point, the intra-frame document correction segmentation requirement of the target video frame is obtained.

[0060] Step S003: Analyze the changes of pixel blocks at the same position between video frames, construct the inter-frame motion change rate of the pixel blocks; and obtain the complexity of dynamic information in combination with the intra-frame document correction segmentation requirement.

[0061] During video transmission, segmenting and compressing video images will affect both intra-frame data and inter-frame data. This means that when segmenting the data of each frame, the degree of image motion between frames needs to be considered. The effect of segmentation size on intra-frame data is that larger segmentation blocks can better utilize the spatial correlation of intra-frame images, thereby improving compression efficiency. However, if the selected segmentation block is too large, detailed information may not be captured when there is large image motion between frames, resulting in distortion.

[0062] Therefore, when compressing each frame of the video, it is necessary to calculate the inter-frame motion change rate of the corresponding pixel block in its temporal neighborhood. In this embodiment, when calculating the inter-frame motion change rate of the video, S video frames centered on the target video frame are considered as motion reference frames, and the value of S in this embodiment is 31.

[0063] Specifically, the analysis is performed based on the i-th pixel block of the target video frame in combination with the i-th pixel block of the motion reference frame. It should be noted that the size of the i-th pixel block of the motion reference frame is the same as the position of the i-th pixel block of the target video frame, and the result is only used to determine whether the pixel block of the target video frame needs to be further divided. The grayscale motion index sequence in its temporal neighborhood is constructed through the grayscale changes of the corresponding pixel blocks in its temporal neighborhood, and the expression is:

[0064]

[0065] In the formula, Represents the value of the grayscale motion index sequence of the i-th pixel block of the target video frame at the t-th moment; Represents the number of pixels in the i-th pixel block in the target video frame; Represents the gray value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-th moment in the time neighborhood of the target video frame; Represents the grayscale value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-1th moment in the time neighborhood of the target video frame.

[0066] The greater the grayscale change between corresponding positions of adjacent frame images, the greater the possibility of object motion in the video at that position and moment, that is, the greater the grayscale motion index of the pixel block at this moment; conversely, the greater the grayscale motion index of the pixel block at this moment, the greater the possibility of object motion in the video at that position and moment, that is, the smaller the grayscale motion index of the pixel block at this moment.

[0067] Then, according to the fluctuation of the grayscale motion index sequence of the target video frame in the time neighborhood, the motion change of the i-th pixel block in the time period can be calculated, that is, the inter-frame motion change rate, which is expressed as:

[0068]

[0069] In the formula, represents the inter-frame motion change rate of the i-th pixel block of the target video frame; Indicates the number of motion reference frames of the target video frame; Represents the value of the grayscale motion index sequence of the i-th pixel block of the target video frame at the t-th moment; Represents the grayscale motion index sequence of the i-th pixel block of the target video frame; , They represent the maximum function and the minimum function respectively.

[0070] The larger the value of the grayscale motion index sequence at each moment, the more obvious the change of the i-th pixel block in the temporal neighborhood of the target video frame is, so the inter-frame motion change rate is larger. Further, the dynamic information complexity of the i-th pixel block is determined according to the intra-frame document correction segmentation requirement and the inter-frame motion change rate, and the expression is:

[0071]

[0072] In the formula, Represents the dynamic information complexity of the i-th pixel block of the target video frame; represents the inter-frame motion change rate of the i-th pixel block of the target video frame; represents the intra-frame document correction segmentation requirement of the i-th pixel block in the target video frame; Represents the normalized function. The process of obtaining dynamic information complexity is as follows: Figure 2 shown.

[0073] When the intra-frame document correction segmentation requirement of the pixel block is greater or the inter-frame motion change rate is greater, it means that the detail level and change of the pixel block are greater, that is, the dynamic information complexity of the pixel block is greater.

[0074] At this point, the dynamic information complexity of each pixel block of the target video frame is obtained.

[0075] Step S004: according to the complexity of dynamic information of the video frame, adaptive dynamic segmentation of the video frame is realized during the optimized transmission process.

[0076] This embodiment uses the long-edge condition segmentation method to divide each frame of the video into blocks. The specific segmentation conditions are: first set the segmentation threshold, traverse each pixel block in the image, and when the dynamic information complexity of the target pixel block is greater than the segmentation threshold, the target pixel block is divided into two parts using the long-edge segmentation method, and one side of the long edge is evenly divided into two pixel blocks. If the segmentation condition is not met, no further segmentation is performed; then re-traverse all pixel blocks and repeat the segmentation operation until the dynamic information complexity of all pixel blocks in the target video frame is less than the threshold. The dynamic information complexity is The value range of is [0,1], and the segmentation threshold value in this embodiment is 0.5.

[0077] Considering that the segmented video blocks may have equal length and width, if segmentation is still required, it is stipulated to be left-right segmentation, that is, the video blocks with equal length and width are divided into left and right parts.

[0078] Finally, video optimized transmission is implemented according to the adaptively segmented pixel blocks. The optimized transmission adopts the H.264 standard, which is a well-known technology and will not be described in detail in this embodiment.

[0079] At this point, the video optimization transmission of the appointment-based integrated conference system is completed.

[0080] In summary, the embodiment of the present invention realizes dynamic adaptive division of pixel blocks in the process of optimizing transmission of traditional video, thereby improving the compression rate and transmission quality of video transmission. Specifically, by analyzing the grayscale distribution of pixel blocks in the video frame, and combining the gradient characteristics of document information to obtain the intra-frame document correction segmentation requirement of each pixel block, the document information and detail richness of each pixel block in the target video frame are measured; then, by analyzing the grayscale changes of pixel blocks at the same position in the time neighborhood of the target video frame, the inter-frame motion change rate of each pixel block is analyzed to measure the motion change characteristics of the pixel blocks in the target video frame in the time neighborhood; the dynamic information complexity of each pixel block is calculated in combination with the above intra-frame document correction segmentation requirement, and an adaptive dynamic block segmentation method for video frames is realized, which can effectively avoid the loss of more detail information during video transmission due to excessive block segmentation, and the problem of low compression ratio due to too small segmentation, and at the same time, it can avoid the incomplete image segmentation caused when the same frame image is divided into blocks of different sizes.

[0081] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0083] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a system for securely transmitting electronic information privacy data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above methods for securely transmitting electronic information privacy data are implemented.

[0084] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Modifications to the technical solutions recorded in the aforementioned embodiments, or equivalent replacement of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for securely transmitting electronic information privacy data, characterized in that: The method comprises the following steps: Obtain electronic information video data of online meetings and perform preprocessing; The video data of each frame to be transmitted is sequentially used as the target video frame; in the process of iterative segmentation of the target video frame, the in-frame detail segmentation requirement of each pixel block is obtained according to the grayscale distribution of each pixel block of the target video frame; for each pixel block of the target video frame, the document segmentation correction coefficient and the document segmentation penalty factor of each pixel point are obtained according to the gradient distribution of all pixel points of the pixel block and the grayscale difference degree of the neighborhood of each pixel point; the in-frame document correction segmentation requirement of each pixel block is obtained according to the relationship between the in-frame detail segmentation requirement of each pixel block of the target video frame and the document segmentation penalty factor; According to the grayscale change characteristics of each pixel block in the target video frame in the time neighborhood, the grayscale motion index sequence of each pixel block in the target video frame is constructed; according to the element distribution characteristics of the grayscale motion index sequence of each pixel block in the target video frame, the inter-frame motion change rate of each pixel block in the target video frame is obtained; and the dynamic information complexity of each pixel block in the target video frame is obtained by combining the inter-frame motion change rate of each pixel block in the target video frame and the intra-frame document correction segmentation requirement; According to the dynamic information complexity of each pixel block of the target video frame, the long edge condition segmentation method is used to realize the adaptive dynamic segmentation of the video frame; according to the segmented pixel blocks, the H.264 standard is used to complete the video optimization transmission; The step of obtaining the intra-frame detail segmentation requirement of each pixel block according to the grayscale distribution of each pixel block in the target video frame includes: For each pixel block of the target video frame, the pixels with the same grayscale value in the pixel block are classified into one category, and the number of types of the pixel points in the pixel block is obtained; the grayscale mean and grayscale standard deviation of all the pixel points in the pixel block are calculated; the absolute value of the difference between the grayscale value of each pixel point in the pixel block and the grayscale mean is calculated; the result of averaging the absolute value of the difference of all the pixel points in the pixel block is calculated; the product of the number of types, the grayscale standard deviation and the result is used as the intra-frame detail segmentation requirement of the pixel block; wherein, before the iterative segmentation, the pixel block is the target video frame, and during the iterative segmentation process, each pixel block is the result of the previous iterative segmentation of the target video frame; For each pixel block of the target video frame, the document segmentation correction coefficient and document segmentation penalty factor of each pixel are obtained according to the gradient distribution of all pixels in the pixel block and the grayscale difference degree of the neighborhood of each pixel, which is specifically: Taking each pixel point of the pixel block as the center, a neighborhood with a side length of W is obtained, where W is a preset value; calculating the absolute value of the difference between the grayscale values ​​of each pixel point in the pixel block and the remaining pixel points in the neighborhood; calculating the average of the absolute values ​​of the difference calculated for each pixel point in the pixel block; obtaining the gradient mean and gradient standard deviation of all pixel points in the neighborhood of each pixel point in the pixel block; taking the product of the gradient mean, the gradient standard deviation and the average of the absolute values ​​of the difference as the document segmentation correction coefficient of each pixel point; The average value of the document segmentation correction coefficients of all pixel points in each pixel block of the target video frame is recorded as the document segmentation penalty factor of each pixel block; The intra-frame document correction segmentation requirement of each pixel block of the target video frame is specifically: Calculate the product of the intra-frame detail segmentation requirement and the document segmentation penalty factor of each pixel block of the target video frame, and use the normalized value of the product as the intra-frame document correction segmentation requirement of each pixel block of the target video frame; The grayscale motion index sequence of each pixel block of the target video frame is constructed according to the grayscale change characteristics of each pixel block of the target video frame in the time neighborhood. The specific expression is: In the formula, Represents the value of the grayscale motion index sequence of the i-th pixel block of the target video frame at the t-th moment; Represents the number of pixels in the i-th pixel block in the target video frame; Represents the gray value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-th moment in the time neighborhood of the target video frame; Represents the grayscale value of the jth pixel in the i-th pixel block in the motion reference frame corresponding to the t-1th moment in the time neighborhood of the target video frame.

2. A method for securely transmitting electronic information privacy data as claimed in claim 1, characterized in that: The motion reference frame is specifically a video frame at S moments centered on the target video frame, where S is a preset value.

3. A method for securely transmitting electronic information privacy data as claimed in claim 1, characterized in that: The step of obtaining the inter-frame motion change rate of each pixel block of the target video frame according to the element distribution characteristics of the grayscale motion index sequence of each pixel block of the target video frame includes: For each pixel block of the target video frame, the extreme value of the grayscale motion index sequence of the pixel block is obtained; the ratio of each element of the grayscale motion index sequence of the pixel block to the extreme value is calculated; and the average of the ratios of all elements of the grayscale motion index sequence of the pixel block is taken as the inter-frame motion change rate of the pixel block.

4. A method for securely transmitting electronic information privacy data as claimed in claim 1, characterized in that: The dynamic information complexity of each pixel block of the target video frame is specifically a normalized value of the product of the inter-frame motion change rate of each pixel block of the target video frame and the intra-frame document correction segmentation requirement.

5. A method for securely transmitting electronic information privacy data as claimed in claim 1, characterized in that: The method of implementing adaptive dynamic segmentation of a video frame by using a long edge conditional segmentation method according to the dynamic information complexity of each pixel block of a target video frame comprises: A segmentation threshold is set. When each pixel block of the target video frame meets the segmentation condition, the long-side condition segmentation method is used to evenly divide the pixel block into two parts according to the longest side of the pixel block; wherein the segmentation condition is: the dynamic information complexity of the pixel block is greater than the segmentation threshold.

6. A system for secure transmission of electronic information privacy data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

Images