Method, device and equipment for regulating and controlling national standard video and storage medium

Abstract

The invention provides a national standard video regulation and control method, device and equipment and a storage medium, and the method comprises the steps: determining audio and video parameters and SIP signaling parameters of national standard camera equipment through deep data packet detection, determining a quality score of a video link according to the audio and video parameters and an evaluation model, determining a grade score according to the SIP signaling parameters, and adjusting and controlling the national standard video according to the grade score. According to the quality score and the grade score, the audio and video parameters are corrected to obtain the corrected audio and video parameters, the quality score and the grade score of the video link can be automatically detected and judged, the audio and video parameters are automatically corrected, and the corrected audio and video parameters are transmitted to national standard camera equipment for use. Therefore, timely automatic regulation and control are realized.

Description

Technical Field

[0001] The present application relates to the field of video surveillance, and in particular to a method, device, equipment and storage medium for regulating national standard video. Background Art

[0002] At present, the video surveillance system / platform composed of multiple national standard camera devices plays an important role in information collection in the IoT application of security management. National standard camera devices are usually connected using national standard protocols such as GB / T28181 and GB / T35114, and the collected audio and video data provide a large amount of basic information for security management. However, nowadays, due to the large number of national standard camera devices connected to the video surveillance system / platform, it is difficult for manual monitoring to inspect the transmission of audio and video data in real time. For example, in some cases, the network is poor, and the transmission of high-resolution audio and video data will fail, making it difficult for manual control in real time and in a timely manner. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment and storage medium for controlling a national standard video to solve at least one problem existing in the related art. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides a method for regulating a national standard video, including:

[0005] Determine the audio and video parameters and SIP signaling parameters of national standard camera equipment through deep data packet inspection;

[0006] Determining a quality score of the video link according to the audio and video parameters and the evaluation model;

[0007] Determining a grade score according to the SIP signaling parameters;

[0008] According to the quality score and the grade score, the audio and video parameters are modified to obtain modified audio and video parameters, and the modified audio and video parameters are transmitted to the national standard camera device for use.

[0009] In one implementation, determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection includes:

[0010] Through deep data packet detection, the streaming media network traffic data of the edge cloud access node to which the national standard camera device is connected is collected, XDR communication data is generated, the header information of the RTP packet of the XDR communication data is detected, and the audio and video parameters are determined;

[0011] Through deep data packet inspection, the signaling network traffic data of the edge cloud access node is collected, SIP signaling data is generated, and SIP signaling parameters are extracted from the SIP signaling data.

[0012] In one implementation, determining the quality score of the video link according to the audio and video parameters and the evaluation model includes:

[0013] Transmitting the audio and video parameters to a central analysis node;

[0014] By using the evaluation model of the central analysis node and a homogeneous integration algorithm to analyze the audio and video parameters, a quality score of the video link is determined;

[0015] The homogeneous integration algorithm includes one of a random forest algorithm, a decision tree algorithm and an extreme random number algorithm.

[0016] In one implementation, determining the grade score according to the SIP signaling parameter includes:

[0017] Determine, through the central analysis node, a mapping relationship between the synchronization source identifier in the SIP signaling parameter and a preset national standard camera device identifier;

[0018] According to the mapping relationship, the detection level corresponding to the target national standard camera equipment identification is determined to obtain a level score.

[0019] In one implementation, the modifying the audio and video parameters according to the quality score and the grade score to obtain modified audio and video parameters includes:

[0020] When the quality score represents low quality and the grade score represents an ordinary device, the bit rate and resolution in the audio and video parameters are both reduced by a preset level to obtain modified audio and video parameters.

[0021] In one implementation, the transmitting the corrected audio and video parameters to the national standard camera device includes:

[0022] Synchronize the corrected audio and video parameters to the redirection server;

[0023] Sending the corrected audio and video parameters to the registration center through the redirection server;

[0024] The national standard camera equipment is used to obtain the corrected audio and video parameters from the registration center in a preset heartbeat cycle.

[0025] In one embodiment, the method further comprises:

[0026] The audio and video data are transmitted to the streaming media of the edge cloud access node by using the corrected audio and video parameters through the national standard camera device;

[0027] Return to the step of determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection.

[0028] In a second aspect, an embodiment of the present application provides a control device for a national standard video, including:

[0029] A determination module, used to determine the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection;

[0030] A first scoring module, used to determine a quality score of a video link according to the audio and video parameters and the evaluation model;

[0031] A second scoring module, used to determine a grade score according to the SIP signaling parameters;

[0032] The correction module is used to correct the audio and video parameters according to the quality score and the grade score to obtain corrected audio and video parameters, and transmit the corrected audio and video parameters to the national standard camera device for use.

[0033] In one embodiment, the correction module is further used to:

[0034] The audio and video data are transmitted to the streaming media of the edge cloud access node by using the corrected audio and video parameters through the national standard camera device;

[0035] Return to the step of determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement a method in any one of the above-mentioned embodiments.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed, the method in any one of the above-mentioned embodiments is implemented.

[0038] The beneficial effects of the above technical solution include at least:

[0039] Through deep data packet inspection, the audio and video parameters and SIP signaling parameters of the national standard camera equipment are determined, the quality score of the video link is determined according to the audio and video parameters and the evaluation model, and the grade score is determined according to the SIP signaling parameters. According to the quality score and the grade score, the audio and video parameters are corrected to obtain the corrected audio and video parameters. It can automatically detect and determine the quality score and the grade score of the video link, automatically correct the audio and video parameters, and transmit the corrected audio and video parameters to the national standard camera equipment for use, thereby realizing timely automatic regulation.

[0040] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.

[0042] Figure 1 This is a schematic diagram of the steps of the method for controlling the national standard video according to an embodiment of the present application;

[0043] Figure 2 This is a structural block diagram of a device for controlling national standard video according to an embodiment of the present application;

[0044] Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0046] Reference Figure 1 , a flow chart of a method for regulating a national standard video according to an embodiment of the present application is shown. The method for regulating a national standard video may at least include steps S100-S400:

[0047] S100: Determine the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection.

[0048] S200: Determine a quality score of the video link according to audio and video parameters and an evaluation model.

[0049] S300: Determine the grade score according to the SIP signaling parameters.

[0050] S400, modifying the audio and video parameters according to the quality score and the grade score to obtain modified audio and video parameters, and transmitting the modified audio and video parameters to the national standard camera device for use.

[0051] The technical solution of the embodiment of the present application determines the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet detection, determines the quality score of the video link according to the audio and video parameters and the evaluation model, determines the grade score according to the SIP signaling parameters, and corrects the audio and video parameters according to the quality score and the grade score to obtain corrected audio and video parameters. It can automatically detect and determine the quality score and the grade score of the video link, automatically correct the audio and video parameters, and transmit the corrected audio and video parameters to the national standard camera device for use, thereby realizing timely automatic regulation.

[0052] In one embodiment, step S100 includes steps S110-S130:

[0053] S110. Through deep data packet detection, the streaming network traffic data of the edge cloud access node to which the national standard camera device is connected is collected, XDR communication data is generated, the header information of the RTP packet of the XDR communication data is detected, and the audio and video parameters are determined.

[0054] Optionally, through deep data packet inspection DPI, the streaming media network traffic data of the edge cloud access node to which the national standard camera device is connected is collected to generate XDR communication data, and then the XDR communication data is detected to determine the audio and video parameters in the header information of the RTP packet, including but not limited to the RTP version number (V), marker bit (M), payload type (PT), sequence number (SN), timestamp, synchronization source identifier (SSRC), bit rate, resolution, bit stream, I frame interval, bit stream type, video compression format, etc. Among them, the national standard camera device is a GB / T 28181 national standard device, which is connected to the edge cloud access node of the GB / T 28181 video surveillance platform.

[0055] It should be noted that the deep packet inspection (DPI) module captures the streaming network traffic data of the devices accessing the streaming server transmission at the distributed edge node, parses the captured data layer by layer, identifies the data protocol header information, distinguishes the IP protocol header, TCP / UDP header and RTP packet protocol, and then performs protocol identification. Based on the parsed RTP packet header information, the traffic data characteristics of a single port, namely the audio and video parameters, are recorded.

[0056] S120. Collect signaling network traffic data of edge cloud access nodes through deep data packet inspection, generate SIP signaling data, and extract SIP signaling parameters from the SIP signaling data.

[0057] Optionally, the signaling network traffic data of the edge cloud access node is collected through deep data packet inspection DPI to generate SIP signaling data; wherein SIP (Session Initiation Protocol) is a communication protocol for establishing, modifying and terminating multimedia sessions. Then, SIP signaling parameters are extracted from the SIP signaling data, including but not limited to the request method, the user or service (URI) identifying the request address, the request initiator (From), the request receiver (To), the unique identifier of the session (Call-ID), the SDP user name, the SDP network type and address, the media type, the transmission port and the transmission protocol (SDP-Meida(m)), the synchronization source identifier (SSRC), etc.

[0058] In the embodiment of the present application, by cyclically using the circular buffer pool and allocating the sizes of different circular buffer pools, data such as audio and video parameters and SIP signaling parameters are stored, and statistical counting and data filtering are performed at periodic intervals to control information flow and reduce the load pressure on the information pipeline.

[0059] In one implementation, step S200 includes steps S210-S220:

[0060] S210: Transmit the audio and video parameters to the central analysis node.

[0061] It should be noted that the audio and video parameters and SIP signaling parameters can be transmitted to the central analysis node for analysis after preprocessing and data formatting. For example, the SIP signaling parameters are classified by format and transmitted to the central analysis node through information pipeline technology.

[0062] S220: Analyze the audio and video parameters using the evaluation model of the central analysis node and the homogeneous integration algorithm to determine the quality score of the video link.

[0063] Optionally, the central analysis node uses a homogeneous integration algorithm through its pre-trained evaluation model to analyze audio and video parameters. For example, it can analyze and obtain indicators such as packet loss rate, delay data, timestamp data, frame integrity rate, jitter, etc., so as to determine the quality score of the video link; the homogeneous integration algorithm includes one of the random forest algorithm, decision tree algorithm and extreme random number algorithm.

[0064] Optionally, the quality score includes a low quality score and a high quality score, the low quality score represents a delayed video traffic link, a stuck video traffic link, and a video traffic link with severe packet loss, and the high quality score represents a normal video traffic link.

[0065] In the embodiment of the present application, the homogeneous integration algorithm is taken as a random forest algorithm as an example for explanation. When constructing the random forest algorithm, training samples and features are randomly selected. For each decision tree, a part of samples need to be randomly selected from the training set as training samples. At the same time, a part of features need to be randomly selected as candidate features. The purpose of doing so is to reduce the correlation between decision trees, thereby reducing the risk of overfitting. For the construction of the training set, the historical production environment backup data of the national standard camera equipment is obtained from the enterprise knowledge base. The data includes the signaling interaction data between the national standard camera equipment and the national standard video surveillance platform and the complete data of the streaming media transmission. The data classification is marked with delayed video traffic links, stuck video traffic links, severe packet loss video traffic links and normal video traffic links; wherein, the delayed video traffic link may be manifested in that the video stream data packet received by the streaming media server has a certain delay relative to the traffic data packet generated by the terminal device; the stuck video traffic link may be manifested in that the video stream data packet received by the media stream server has frame loss, frame skipping, timestamp jumping, and the display of moving objects in the picture is stuck; the severe packet loss video traffic link may be manifested in that the video stream data received by the media stream server is lost and cannot be completely restored, resulting in a flower screen, a large area of ​​green screen, and other effects.

[0066] In the embodiment of the present application, for each decision tree, the following steps are followed to construct it:

[0067] 1. For the features of the root node, I find an optimal split point so that the split point can maximize the reduction of heterogeneity between child nodes, put important features at the root node, and then select important features in the subtree and put them at the root node of the subtree; this process is measured using indicators such as information gain and Gini index.

[0068] 2. According to the optimal segmentation point, the training samples are divided into multiple sub-nodes.

[0069] 3. For each child node, recursively select features and split points until the stopping condition is met. The stopping condition usually includes:

[0070] (1) Subtree classification is completed: the sub-data sets on the node all belong to the same category, and the node is no longer divided downward.

[0071] (2) All features have been classified: All features have been classified, and the height of the tree is equal to the number of features.

[0072] (3) All samples have been classified: All sample data have been classified.

[0073] Information gain g(D,A): Given a sample set D, the entropy of the sample set D before partitioning is certain, which is represented by H(D). Use a certain feature A to partition the data set D, and calculate the entropy of the data subset after partitioning, which is represented by H(D|A). Then information gain = H(D)-H(D|A), which can also be expressed as:

[0074] g(D,A)=H(D)-H(D|A)

[0075] In this embodiment, the information gain of the packet loss rate and the information gain of the RTP packet disorder are analyzed:

[0076] (1) Information gain of packet loss rate: Entropy is 100 video links, representing uncertainty. According to the packet loss rate characteristics, 10 video links with packet loss rates higher than 30% are divided out. The video links that cannot be reconstructed and restored are selected from these 10 video links, instead of selecting 1 from 100 video links to selecting 1 from 10 video links. The uncertainty of 90 video links is eliminated.

[0077] (2) Information gain of RTP packet disorder: Entropy is 100 video links, representing uncertainty; according to the RTP packet disorder feature, 30 video links with RTP packet disorder higher than 30% are divided out, and the video links that cannot be reassembled and restored are selected from these 30 video links. From selecting 1 out of 100 video links to selecting 1 out of 30 video links; the uncertainty of 70 video links is eliminated. Therefore, the information gain of packet loss rate is higher than the information gain of RTP packet disorder, that is, the feature segmentation of packet loss rate is implemented before the feature segmentation of RTP packet disorder.

[0078] In one implementation, step S300 includes steps S310-S320:

[0079] S310: Determine, through a central analysis node, a mapping relationship between a synchronization source identifier in a SIP signaling parameter and a preset national standard camera device identifier.

[0080] Optionally, a mapping relationship between a synchronization source identifier in a SIP signaling parameter and a preset national standard camera device identifier is determined through a central analysis node.

[0081] S320: Determine the detection level corresponding to the target national standard camera equipment identification according to the mapping relationship to obtain a level score.

[0082] Optionally, the detection level corresponding to the synchronization source identifier (SSRC) is preset in advance, so the detection level of the corresponding preset synchronization source identifier can be determined based on the mapping relationship as the current detection point level, and the corresponding grade score is determined based on the current detection point level. It should be noted that the grade score can represent ordinary equipment, attention equipment, and key equipment; when determining the grade score, the grade score of the terminal equipment can also be fitted based on factors such as the user's demand for using national standard camera equipment, user level, time period, etc. It should be noted that a neural network model can be used for fitting, or the grade score can be determined based on user feedback, and the grade score is in different ranges and corresponds to the above-mentioned different types of equipment; the grade score determines the priority of resource use, and the priority is from low to high, namely ordinary equipment, attention equipment, and key equipment. Among them, equipment with historical problems in various types of equipment is recorded as historical problem equipment, and will be assigned a detailed score according to the number of problems and the severity of the problems.

[0083] In one implementation, in step S400, the audio and video parameters are modified according to the quality score and the grade score to obtain modified audio and video parameters, including step S410:

[0084] S410: When the quality score indicates low quality and the grade score indicates an ordinary device, the bit rate and resolution in the audio and video parameters are reduced by a preset level to obtain modified audio and video parameters.

[0085] Optionally, when the quality score represents low quality and the grade score represents an ordinary device, the bit rate and resolution in the audio and video parameters are both reduced by a preset level to obtain modified audio and video parameters.

[0086] S420. When the quality score indicates low quality and the grade score indicates key equipment, the national standard camera equipment is migrated to a new streaming node (edge ​​cloud access node), thereby obtaining corrected audio and video parameters based on the new streaming node.

[0087] In one implementation, the modified audio and video parameters are transmitted to the national standard camera device in step S400, including steps S420-S440:

[0088] S420: Synchronize the corrected audio and video parameters to the redirection server.

[0089] S430: Send the corrected audio and video parameters to the registration center through the redirection server.

[0090] S440. Obtain the corrected audio and video parameters from the registration center in a preset heartbeat cycle through a national standard camera device.

[0091] Optionally, after obtaining the corrected audio and video parameters, they are synchronized to the redirection server, and the corrected audio and video parameters are sent to the registration center through the redirection server; then, the national standard camera equipment will obtain the corrected audio and video parameters from the registration center in a preset heartbeat cycle, thereby utilizing the corrected audio and video parameters.

[0092] In one implementation, the method for controlling the national standard video in the embodiment of the present application may further include steps S510-S520:

[0093] S510, using the corrected audio and video parameters through the national standard camera equipment, transmitting the audio and video data to the streaming media of the edge cloud access node.

[0094] Optionally, after obtaining the corrected audio and video parameters, the national standard camera device will use the corrected audio and video parameters to transmit the corresponding corrected audio and video data to the streaming media of the edge cloud access node. Among them, the national standard camera device obtains the corrected audio and video parameters in the following ways: including but not limited to GB / T28181-2020 protocol, enterprise standard control heartbeat protocol, group standard protocol, and industry standard protocol.

[0095] S520 , returning to the step of determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection.

[0096] Then, the process returns to the step of determining the audio and video parameters of the national standard camera equipment and the SIP signaling parameters through deep data packet inspection, thereby continuously performing inspection and analysis and dynamically determining whether the audio and video parameters need to be adjusted, which is conducive to maintaining the effective transmission of audio and video data.

[0097] It should be noted that if the number of adjustments is higher than the number threshold, and the quality score of the national standard camera device still indicates low quality, a prompt message is issued to prompt manual intervention.

[0098] Through the method of the embodiment of the present application, distributed deep data packet detection is used to automatically detect the network status and video link of distributed edge access streaming media. Through deep learning, an automatic judgment mechanism for the network and monitoring video quality of national standard camera equipment is established, and automatic scheduling and audio and video parameter control are realized for the connected national standard camera equipment, thereby reducing the workload of manual operation and maintenance and regulation, reducing operation and maintenance costs, and improving the access efficiency of monitoring points and the efficiency of video surveillance quality control.

[0099] The method of the embodiment of the present application can be applied to the video surveillance convergence system of the operator, and the operator's private network resources and the dedicated advantages of the private network are utilized to enable the surveillance convergence system to better monitor and more scientifically and accurately regulate the traffic data; it makes up for the shortcomings of the traditional GB / T 28181 and GB / T 35114 terminal equipment parameters that need to be manually adjusted, especially the parameter data such as bit rate, bit rate, I frame interval, resolution, etc. that require a lot of industry experience, which greatly reduces the technical threshold of terminal equipment operation and maintenance personnel, and greatly reduces the cost of the social point laying stage; it makes up for the traditional video quality judgment method. Traditional video quality monitoring is mainly through manual inspection and identification or GPU video detection and identification. Manual inspection depends on the technical threshold of operation and maintenance personnel, and GPU video detection requires GPU hardware support and consumes the monitoring system's review capabilities. This application combines the use of DPI deep packet inspection technology and decision tree algorithm to filter distributed nodes before GPU detection, greatly reducing resource consumption; the use of DPI deep packet inspection technology increases the ability of distributed host non-invasive detection, and can independently perform video quality detection and regulation based on GB / T 28181 national standard video outside the original third-party video surveillance platform, greatly reducing the upgrade and change operations of the original system and reducing the cost of system intelligence.

[0100] The following is a specific example for explanation:

[0101] Assume that there are national standard camera equipment 201, edge cloud access SIP service / DPI-SIP service 202, edge cloud streaming service / DPI-RTP service 203, registration center 204 (the registration center has registration services for multiple protocols, including enterprise standard heartbeat registration service 2041, GB / T 28181-2020 redirection service 2042, group standard protocol redirection service 2043, industry standard API registration center 2044), and DPI-ANALYSE analysis center 205.

[0102] The national standard camera device 201 can obtain the above-mentioned audio and video parameters, SIP signaling parameters, firmware upgrade parameters, GB / T28181 related parameters, OSD parameters, longitude and latitude coordinate calibration information and other configuration information from the registration center 204 through the enterprise standard heartbeat registration protocol, GB / T 28181-2020 redirection protocol, group standard redirection protocol, and industry standard API protocol, taking firmware upgrade as an example.

[0103] Firmware upgrade parameters, used to notify the national standard camera device 201, synchronize the firmware version number, including but not limited to the latest firmware version number, update identifier, and update center address; GB / T28181 related parameters: including but not limited to activation identifier, SIP server ID, SIP service IP, SIP server domain, SIP server port, SIP user name / SIP user authentication ID (device national standard ID), video channel encoding ID (bit channel ID), alarm channel ID (20-bit alarm channel ID), audio channel ID (20-bit audio channel ID), 28181 access password ciphertext, stream index, registration validity period, heartbeat cycle, registration interval, maximum heartbeat timeout number, 35114 mode activation identifier; video stream related parameters, i.e., audio and video parameters, including but not limited to main stream information and sub-stream information, wherein each main stream information or sub-stream information includes but is not limited to encoding mode, encoding complexity, resolution width, resolution height, frame rate, bit rate type, picture quality, bit rate, I frame interval, etc.

[0104] The national standard camera device 201 communicates with the server through the standard national standard registration process (register) and the real-time video transmission process (invite) to transmit real-time on-demand streaming media data; the edge cloud access SIP service / DPI-SIP service 202 captures the device access national standard video signaling data transmitted by the signaling server through the deep packet inspection DPI-SIP module, and captures the network traffic data used for streaming media.

[0105] Optionally, the edge cloud access SIP service 202 initiates a SIP-INVITE signaling to the national standard camera device 201, and the national standard camera device 201 replies with a SIP-OK signaling. The current signaling interaction includes the flow link communication information record that constitutes the xDR communication data call list of this session, i.e., XDR communication data, which contains multiple parameters, including but not limited to device ID, source IP, source port, target IP, target port, synchronization source identifier (SSRC), and is transmitted to the central DPI-ANALYSE analysis center 205 through the information pipeline as a device information mapping storage association relationship.

[0106] There are many storage record methods, such as micro embedded database sqlite, descriptive script file json, and memory cache database redis. This embodiment uses redis middleware to store key-value pair information and hash information.

[0107] Optionally, the edge cloud streaming service / DPI-RTP service 203 uses deep packet inspection technology to capture the UDP / TCP traffic data of all streaming media designated transmission ports of the edge cloud streaming server, and performs preliminary parsing and reorganization of the data. Obtain the IP layer information of the current video stream link, including but not limited to source IP, source port, target IP, and target port; obtain the RTP-UDP / RTP-TCP data of the current video stream link, filter and extract relevant audio and video parameters, including but not limited to RTP version number (V), marker bit (M), payload type (PT), sequence number (SN), timestamp, synchronization source identifier (SSRC), and complete data collection through a series of analysis and cleaning strategies, and transmit it to the central DPI-ANALYSE analysis center 205 through an information pipeline.

[0108] Optionally, it includes a DPI-RTP packet analysis module: it performs RTP packet assembly and analyzes the RTP data quality, including but not limited to packet loss rate, delay data, timestamp data, frame integrity rate, and jitter.

[0109] It should be noted that jitter is a key indicator in network transmission, reflecting the degree of change in network delay, which is particularly important for audio and video communications. The calculation of jitter is based on the actual difference in arrival time between two consecutive RTP packets and the theoretical difference based on the timestamp. By calculating the absolute value of the difference between the two, the packet-to-packet delay change, i.e. jitter, can be obtained. The sliding average method is used to further smooth this value, which helps to filter out outliers or occasional network fluctuations, making the jitter calculation more stable and reliable.

[0110] Specifically, the RTP packet arrival time difference:

[0111] D a =(t tarrival,current -t tarrival,previous )×1000

[0112] Timestamp difference D t :

[0113]

[0114] Among them, t represents the timestamp data of the packet arrival, t tarrival,current is the timestamp data of the current packet arrival, t tarrival,previois It is the timestamp data of the previous packet (predecessor packet) arrival. Timestamp represents the timestamp data contained in the RTP packet. current The timestamp data contained in the current RTP packet, timestamp previousThis is the timestamp data contained in the previous RTP packet. 90 is converted based on the assumed sampling rate of 90000 Hz, that is, the timestamp increases by 90 every millisecond.

[0115] Jitter difference D:

[0116] D=|D a -D t |

[0117] The absolute value between the two time differences is calculated to obtain the deviation between the actual time difference and the theoretical time difference between the current RTP packet and the previous packet.

[0118] Jitter smoothing update:

[0119]

[0120] It should be noted that the above formula is a sliding average formula. By gradually introducing new jitter deviation J new , smoothly update the jitter value, reduce the mutation and exception processing in the calculation, where J old The initial value is 0, which means no jitter, and 16 is the smoothing experience value.

[0121] Optionally, jitter calculation can use more rigorous and complex calculation methods, such as weighted moving average, variance and standard deviation, and adaptive filtering techniques, such as Kalman Filter, which can estimate the state of variables in a noisy system. Kalman filter is an extremely efficient recursive filter that only uses the current input measurement data and the state at the previous time point to estimate the current state, thereby tracking jitter more accurately.

[0122] In this embodiment, a ring cache mechanism is introduced to count network jitter at different time scales for jitter data, and multiple time windows are used to further smooth the data. Monitoring at different time scales is performed according to the hardware computing capabilities of different implementation environments. Short time scales represent temporary jitter, and medium and long time scales represent frequent jitter, which requires attention and processing.

[0123] In this embodiment, a circular buffer of 1 second, 10 seconds, 30 seconds, 1 minute, and 5 minutes of 5 different time scales is generated by the circular buffer processing unit, and the bit rate of the current video stream is determined by analyzing the RTP data, so as to obtain the size of the generated circular buffer, and the circular buffer data is counted in different statistical intervals. Among them, after the circular buffer is full, the first data to enter is overwritten to ensure that the latest data can enter the buffer. This is also the significance of the circular buffer, without frequent increase or decrease of memory, and reuse. If no new data is added to the current video stream port within a 1-minute time interval, all the circular buffers of the port are closed.

[0124] Optionally, the information pipeline technology method can be MQ. MQ is a cross-process communication mechanism used for pipeline-based information transmission between upstream and downstream, and can also be used for decoupled communication between distributed applications, including but not limited to Kafka, RabbitMQ, RocketMQ, ZeroMQ, and ActiveMQ. The embodiment of the present application uses Kafka to transmit data messages between the edge cloud access SIP service / DPI-SIP service 202, the edge cloud streaming media service / DPI-RTP service 203, and the DPI-ANALYSE analysis center 205.

[0125] Optionally, if a video channel detects a packet loss rate of 0.35 (certified by wireshark), a low-quality Q1 score is obtained. The device is automatically adjusted by the system as a common monitoring device, and the bit rate is reduced from 2M / s to 1M / s. At the same time, the resolution is reduced from 1920*1080 to 1280*720, and then restored after the network is restored.

[0126] Optionally, the revised preset parameters will be synchronized to the central heartbeat (redirection server or configuration center), and the configuration center will issue parameters to different protocol servers, enterprise standard heartbeat registration service 2041, GB / T 28181-2020 redirection service 2042, group standard protocol redirection service 2043, and industry standard API registration center 2044 according to the information of the national standard camera device 201. The national standard camera device 201 obtains configuration parameters, i.e., revised audio and video parameters, from the enterprise standard heartbeat registration service 2041, GB / T28181-2020 redirection service 2042, group standard protocol redirection service 2043, and industry standard API registration center 2044 in the set heartbeat cycle, thereby completing the new configuration.

[0127] Reference Figure 2 , shows a structural block diagram of a control device for national standard video according to an embodiment of the present application, and the device may include:

[0128] A determination module, used to determine the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection;

[0129] A first scoring module, used to determine the quality score of the video link according to the audio and video parameters and the evaluation model;

[0130] A second scoring module is used to determine a grade score according to the SIP signaling parameters;

[0131] The correction module is used to correct the audio and video parameters according to the quality score and the grade score to obtain the corrected audio and video parameters, and transmit the corrected audio and video parameters to the national standard camera equipment for use.

[0132] In one embodiment, the correction module is further configured to:

[0133] The audio and video data are transmitted to the streaming media of the edge cloud access node through the national standard camera equipment using the corrected audio and video parameters;

[0134] Return to the step of determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep packet inspection.

[0135] The functions of each module in each device in the embodiments of the present application can be found in the corresponding description in the above method, and will not be repeated here.

[0136] Reference Figure 3 , shows a structural block diagram of an electronic device according to an embodiment of the present application, the electronic device includes: a memory 310 and a processor 320, the memory 310 stores instructions that can be run on the processor 320, and the processor 320 loads and executes the instructions to implement the national standard video control method in the above embodiment. The number of the memory 310 and the processor 320 can be one or more.

[0137] In one embodiment, the electronic device also includes a communication interface 330 for communicating with external devices and performing data exchange transmission. If the memory 310, the processor 320 and the communication interface 330 are implemented independently, the memory 310, the processor 320 and the communication interface 330 can be interconnected through a bus and complete mutual communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0138] Optionally, in a specific implementation, if the memory 310, the processor 320 and the communication interface 330 are integrated on a chip, the memory 310, the processor 320 and the communication interface 330 can communicate with each other through an internal interface.

[0139] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the national standard video control method provided in the above embodiment.

[0140] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0141] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0142] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0143] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0144] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0145] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0146] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0147] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0149] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0150] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0151] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for regulating national standard video, characterized in that: include: Determine the audio and video parameters and SIP signaling parameters of national standard camera equipment through deep data packet inspection; Determining a quality score of the video link according to the audio and video parameters and the evaluation model; Determining a grade score according to the SIP signaling parameters; According to the quality score and the grade score, the audio and video parameters are modified to obtain modified audio and video parameters, and the modified audio and video parameters are transmitted to the national standard camera device for use.

2. The method for controlling the national standard video according to claim 1, characterized in that: Determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection includes: Through deep data packet detection, the streaming media network traffic data of the edge cloud access node to which the national standard camera device is connected is collected, XDR communication data is generated, the header information of the RTP packet of the XDR communication data is detected, and the audio and video parameters are determined; Through deep data packet inspection, the signaling network traffic data of the edge cloud access node is collected, SIP signaling data is generated, and SIP signaling parameters are extracted from the SIP signaling data.

3. The method for controlling the national standard video according to claim 1 or 2, characterized in that: Determining the quality score of the video link according to the audio and video parameters and the evaluation model includes: Transmitting the audio and video parameters to a central analysis node; By using the evaluation model of the central analysis node and a homogeneous integration algorithm to analyze the audio and video parameters, a quality score of the video link is determined; The homogeneous integration algorithm includes one of a random forest algorithm, a decision tree algorithm and an extreme random number algorithm.

4. The method for controlling the national standard video according to claim 3, characterized in that: Determining the grade score according to the SIP signaling parameter includes: Determine, through the central analysis node, a mapping relationship between the synchronization source identifier in the SIP signaling parameter and a preset national standard camera device identifier; According to the mapping relationship, the detection level corresponding to the target national standard camera equipment identification is determined to obtain a level score.

5. The method for controlling the national standard video according to claim 4, characterized in that: The step of modifying the audio and video parameters according to the quality score and the grade score to obtain modified audio and video parameters includes: When the quality score represents low quality and the grade score represents an ordinary device, the bit rate and resolution in the audio and video parameters are reduced by a preset level to obtain modified audio and video parameters.

6. The method for controlling the national standard video according to claim 3, characterized in that: The transmitting the corrected audio and video parameters to the national standard camera device comprises: Synchronize the corrected audio and video parameters to the redirection server; Sending the corrected audio and video parameters to the registration center through the redirection server; The national standard camera equipment is used to obtain the corrected audio and video parameters from the registration center in a preset heartbeat cycle.

7. The method for controlling the national standard video according to claim 2, characterized in that: The method further comprises: The audio and video data are transmitted to the streaming media of the edge cloud access node by using the corrected audio and video parameters through the national standard camera device; Return to the step of determining the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection.

8. A national standard video control device, characterized in that: include: A determination module, used to determine the audio and video parameters and SIP signaling parameters of the national standard camera device through deep data packet inspection; A first scoring module, used to determine a quality score of a video link according to the audio and video parameters and the evaluation model; A second scoring module, used to determine a grade score according to the SIP signaling parameters; The correction module is used to correct the audio and video parameters according to the quality score and the grade score to obtain corrected audio and video parameters, and transmit the corrected audio and video parameters to the national standard camera device for use.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images