Video transmission method, device, electronic device and storage medium

Abstract

The present application relates to the field of Internet technology, and in particular to a video transmission method, device, electronic device and storage medium. The method includes: obtaining wireless signal parameters from a device end to a wireless access point; obtaining network transmission parameters of a transmission network from a device end to a receiving end based on ACK feedback information fed back by a receiving end; obtaining current fusion feature parameters based on wireless signal parameters and network transmission parameters; determining the current network quality classification based on the current fusion feature parameters based on the fusion feature parameters corresponding to different predetermined network quality classifications; if the current network quality classification meets the transmission adjustment conditions, adjusting the current transmission control parameters, and transmitting the video according to the adjusted transmission control parameters. Since the present application can evaluate the network quality based on the network transmission parameters and the wireless signal parameters, it can improve the timeliness of the perception of network congestion; at the same time, quickly adjust the transmission control parameters to improve the efficiency of video transmission.

Description

Background Art

[0002] With the continuous development of wireless technology, the application scenarios of video transmission are becoming more and more extensive. Mobile phones, laptops, cameras and other devices can realize real-time transmission and reception of video data through Wi-Fi or mobile networks, which provides great convenience for scenarios such as telemedicine, smart homes, drone monitoring, and unmanned driving.

[0003] In the related technologies, video transmission under wireless signals may be affected by factors such as device location, wireless interference, network delay and resource competition, which may cause packet loss in the network transmission layer of video data, and further cause problems such as freezing, frame loss, delay and asynchrony in video playback. Since the related technologies determine the network quality through the network characteristics from the sender to the receiver of the video transmission, it is impossible to immediately perceive the abnormality of the wireless network. Instead, it is necessary to receive the acknowledgment (ACK) feedback information sent by the receiver before perceiving the abnormality of the current network status (such as high delay) based on the reception time of the ACK feedback information. However, the ACK feedback information is sent after the data is successfully received by the receiver, resulting in a lag in the perception of network abnormalities. In addition, from the time when the network abnormality occurs to the time when the ACK feedback information is received, the video data is still sent in large quantities as normal because the network abnormality has not yet been perceived, further exacerbating the network delay and packet loss rate. Summary of the invention

[0004] Embodiments of the present application provide a video transmission method, device, electronic device, and storage medium to improve the efficiency of video transmission.

[0005] A video transmission method provided in an embodiment of the present application includes:

[0006] During the video transmission process, the wireless signal parameters from the device to the wireless access point are obtained;

[0007] Based on the confirmation response ACK feedback information fed back by the receiving end, obtaining the network transmission parameters of the transmission network from the device end to the receiving end;

[0008] Obtaining current fusion feature parameters based on the wireless signal parameters and the network transmission parameters;

[0009] Based on the predetermined fusion feature parameters corresponding to different network quality classifications, determining the current network quality classification according to the current fusion feature parameters;

[0010] If the current network quality classification meets the transmission adjustment condition, the current transmission control parameter is adjusted, and the video is transmitted according to the adjusted transmission control parameter.

[0011] An embodiment of the present application provides a video transmission device, including:

[0012] A first acquisition unit is used to acquire wireless signal parameters from a device to a wireless access point during video transmission;

[0013] A second acquisition unit, configured to acquire a network transmission parameter of a transmission network from the device end to the receiving end based on ACK feedback information fed back by the receiving end;

[0014] A third acquisition unit, configured to obtain a current fusion feature parameter based on the wireless signal parameter and the network transmission parameter;

[0015] A determination unit, configured to determine a current network quality classification according to the current fused feature parameters based on the predetermined fused feature parameters corresponding to different network quality classifications;

[0016] The adjustment unit is used to adjust the current transmission control parameters if the current network quality classification meets the transmission adjustment conditions, and transmit the video according to the adjusted transmission control parameters.

[0017] Optionally, the wireless signal parameter includes at least one of the following:

[0018] Wireless signal strength RSSI, channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, wireless receiving signal-to-noise ratio;

[0019] The network transmission parameters include at least one of the following:

[0020] Round-trip delay, packet loss rate, and retransmission rate.

[0021] Optionally, the fusion feature parameter further includes a video quality parameter, and the device further includes:

[0022] A fourth acquisition unit, used to acquire a video quality parameter corresponding to the currently transmitted video;

[0023] Wherein, the current fusion feature parameter is obtained based on the wireless signal parameter, the network transmission parameter and the video quality parameter.

[0024] Optionally, the device further comprises:

[0025] The clustering unit is used to pre-determine the fusion feature parameters corresponding to different network quality classifications in the following manner:

[0026] Obtain historical fusion feature parameters at different times;

[0027] For each historical fusion feature parameter, determine the network quality classification corresponding to the historical fusion feature parameter according to whether the parameters corresponding to the historical fusion feature parameter meet the corresponding service constraints and the priority of the parameters;

[0028] The historical fusion feature parameters in each network quality classification are clustered, and the fusion feature parameters corresponding to different levels of network quality classification are determined according to the clustering results.

[0029] Optionally, the clustering unit is specifically used for:

[0030] The parameter with the highest priority among the parameters is used as the current parameter;

[0031] If the current parameter does not meet the corresponding service constraint, then according to the correspondence between different preset priorities and network quality classifications, determine the target network quality classification corresponding to the priority of the current parameter, which is the network quality classification corresponding to the one historical fusion feature parameter; otherwise, select the parameter of the next priority as the current parameter, and determine again whether the current parameter meets the corresponding service constraint;

[0032] If all parameters in the one historical fusion feature parameter meet the corresponding service constraints, it is determined that the one historical fusion feature parameter corresponds to a specified network quality classification.

[0033] Optionally, the clustering unit is specifically used for:

[0034] According to a preset total number of levels, if the total number of levels is greater than the total number of network quality categories, determining the number of levels for each network quality category;

[0035] Clustering the historical fusion feature parameters in each network quality classification according to the corresponding number of levels;

[0036] For each network quality classification, the cluster centers corresponding to each level under a network quality classification are respectively used as fusion feature parameters corresponding to the corresponding level under the network quality classification.

[0037] Optionally, the transmission control parameter includes at least one of a congestion window size and a retransmission timeout period.

[0038] Optionally, the adjustment unit is specifically used for:

[0039] Determine the value of the adjustment factor corresponding to the current network quality classification based on the preset correspondence between different network quality classifications and the values ​​of the adjustment factors;

[0040] Based on the value of the adjustment factor, the current transmission control parameter is adjusted.

[0041] An electronic device provided by an embodiment of the present application includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the above-mentioned video transmission methods.

[0042] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is executed on an electronic device, the computer program is used to enable the electronic device to execute the steps of any one of the above-mentioned video transmission methods.

[0043] An embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any one of the above-mentioned video transmission methods.

[0044] The beneficial effects of this application are as follows:

[0045] The embodiments of the present application provide a video transmission method, apparatus, electronic device and storage medium. In the present application, the device end, that is, the transmitting end, can periodically detect the network quality during the video transmission process. Specifically, the transmitting end can obtain network transmission parameters based on ACK feedback information, and can also obtain wireless signal parameters from the device end to the wireless access point; the network transmission parameters and wireless signal parameters are combined to determine the quality of the current network.

[0046] Although the network transmission parameters in the present application are obtained based on ACK feedback information, the ACK feedback information can be the ACK feedback information of the current detection cycle or the ACK feedback information of the previous detection cycle. That is, even if the ACK feedback information is not received in the current detection cycle, the network transmission parameters can be determined based on the feedback information of the previous detection cycle, and then the current network quality classification can be determined in combination with the current wireless signal parameters. Compared with the prior art that only relies on network transmission parameters to judge the quality of the network, and can only rely on previous parameters to determine the network quality when no new ACK feedback information is received, the method of combining network transmission parameters and wireless signal parameters to judge network quality in the present application is more timely in perceiving network congestion and has higher accuracy in judgment.

[0047] Afterwards, the sender determines whether the current network quality classification meets the transmission adjustment conditions. If so, it adjusts the current transmission control parameters and transmits the video according to the adjusted transmission control parameters. This enables the transmission control parameters to be adjusted quickly, improves video transmission efficiency, reduces network transmission delay and packet loss rate, and ensures smooth video playback.

[0048] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0050] Figure 1A A schematic diagram of an application scenario of a video transmission method provided in an embodiment of the present application;

[0051] Figure 1B A schematic diagram of an application scenario of another video transmission method provided in an embodiment of the present application;

[0052] Figure 2 An overall flow chart of a video transmission method provided in an embodiment of the present application;

[0053] Figure 3 A schematic diagram of a scenario of real-time video transmission provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of obtaining fusion feature parameters corresponding to different network quality classifications provided in an embodiment of the present application;

[0055] Figure 5 An overall flow chart of another video transmission method provided in an embodiment of the present application;

[0056] Figure 6 A schematic diagram of the structure of a video transmission device provided in an embodiment of the present application;

[0057] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the technical solution of the present application, rather than all of the embodiments. Based on the embodiments recorded in the application documents, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the technical solution of the present application.

[0059] The following is an introduction to some concepts involved in the embodiments of the present application.

[0060] Round-trip delay: Round-trip delay refers to the total time it takes for a data packet (such as a video stream in this application) to be sent from the sender to the receiver and return a feedback confirming delivery.

[0061] Retransmission Timeout (RTO): The retransmission timeout is the maximum time the sender waits for feedback to confirm delivery after sending a data packet. If no feedback is received within the retransmission timeout, the sender will retransmit the data packet.

[0062] Congestion Window (CWND): The congestion window indicates the maximum number of bytes that the sender is allowed to send without receiving feedback. Reasonable control of the congestion window based on network quality (such as congestion, round-trip delay, and packet loss rate) can effectively improve network congestion and optimize data transmission efficiency.

[0063] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0064] like Figure 1A As shown, it is a schematic diagram of an application scenario of an embodiment of the present application. The application scenario diagram includes two device ends 110, a router 120, and a receiving end 130.

[0065] In the embodiment of the present application, the device end 110 is the sending end, which is responsible for sending the video. The device end 110 can be a device that can transmit video in real time, such as a camera, a mobile phone, a tablet computer, a laptop computer, a desktop computer, a car terminal and other terminal devices; the router 120 is a wireless access point; the receiving end 130 can be a server, such as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0066] If the device end 110 is a mobile phone, computer, etc., a video transmission-related client can be installed on the device end 110. The client can be software (such as a browser, video transmission software, etc.), or a web page, a small program, etc. The receiving end 130 is a background server corresponding to the software or web page, small program, etc., or a server specifically used for video transmission and storage, which is not specifically limited in this application.

[0067] It should be noted that the video transmission method in each embodiment of the present application is mainly executed by the device end 110 alone. For example, in the actual application scenario of real-time monitoring, the device end 110 is generally a wireless camera device, and the receiving end 130 is generally a cloud server. The device end 110 can be connected to the receiving end 130 via Wi-Fi. This process is implemented through network devices such as routers 120. In this way, the device end 110 can send the captured monitoring video in the form of a video packet through the router 120 in real time to the receiving end 130. If the receiving end 130 receives the video packet, it will feedback an ACK signal to the device end 110, that is, ACK feedback information. In this process, the device end 110 senses the wireless signal parameters between the device end 110 and the router 120, and determines the network transmission parameters based on the ACK feedback information, and further periodically detects the current network quality based on the network transmission parameters and the wireless signal parameters.

[0068] Specifically, Figure 1B As shown, it is a schematic diagram of another application scenario provided by an embodiment of the present application, in which the white blocks are video packets, the black blocks are retransmission packets, the solid lines are the transmission process of the video packets, and the dotted lines are the transmission process of the control flow, including the transmission process of ACK feedback information, the transmission process of wireless signal parameters, the comprehensive evaluation process, and the adjustment of transmission control parameters.

[0069] The video packet sending module of the device end 110 cuts the video stream into video packets of different sizes, such as the video I frame packet group and the video P frame packet group in the figure. The video packet sends data to the router 120 through the wireless network perception module and the wireless driver module, and the router 120 further sends the data to the receiving end 130; during this period, the wireless driver module perceives the changes in the wireless signal parameters of the wireless signal in real time, and sends the wireless signal parameters to the wireless network perception module for comprehensive evaluation; after receiving the video packet data, the receiving end 130 returns ACK feedback information to the device end 110; the wireless network perception module of the device end 110 will conduct a comprehensive evaluation of the network quality based on the wireless signal parameters and the network transmission parameters fed back by the ACK feedback information, and further combine the video quality parameters to judge the current network quality classification, and adjust the transmission control parameters accordingly; finally, the video packet sending module of the device end 110 sends new video data according to the adjusted transmission control parameters, or retransmits the video data that has been sent but has not received confirmation of delivery feedback.

[0070] In an optional implementation, the device end 110 and the receiving end 130 may communicate via a communication network, and the communication network in the present application is mainly a wireless network.

[0071] It should be noted that Figure 1A and Figure 1B The figure is only an example. In fact, the number of device ends and receiving ends is not limited, and is not specifically limited in the embodiments of the present application.

[0072] In addition, the embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation and other scenarios.

[0073] The following describes the video transmission method provided by the exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation of the present application is not limited in this regard.

[0074] See also Figure 2 As shown, it is an implementation flow chart of a video transmission method provided in an embodiment of the present application. The specific implementation process of the method is as follows S201-S203:

[0075] S201: During the video transmission process, the device side obtains wireless signal parameters from the device side to the wireless access point.

[0076] S202: The device end obtains network transmission parameters of the transmission network from the device end to the receiving end based on the confirmation response ACK feedback information fed back by the receiving end.

[0077] In this application, network transmission parameters are used to reflect the transmission performance of the network from the device end, that is, the sending end to the receiving end; wireless signal parameters are used to reflect the transmission performance of the network from the device end to the wireless access point (mainly a router).

[0078] Exemplarily, the wireless signal parameters include at least one of wireless signal strength (Received Signal Strength Indication, RSSI), channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, and wireless receiving signal-to-noise ratio; the network transmission parameters include at least one of round-trip delay, packet loss rate, and retransmission rate.

[0079] Since the method proposed in this application is mainly used in the scenario of real-time video transmission, for example, Figure 3 As shown, it is a schematic diagram of a video real-time transmission scenario provided by an embodiment of the present application. The camera device transmits the captured images to the cloud server in real time through a router, and then a terminal device accesses the cloud server through Wi-Fi or a mobile network to view the real-time captured images or alarm recordings of the monitored area in real time. The camera device is the device end / sender end, and the cloud server is the receiving end.

[0080] The specific values ​​of the network transmission parameters can be obtained based on the data transmission conditions of each video stream in the network, and the update depends on the ACK feedback information fed back by the receiving end after the video packet of the video stream arrives at the receiving end and the receiving end receives the video packet; for example, according to the ACK feedback information, the round-trip delay, one-way delay, delay variation, etc. of the video packet transmission can be known. For the video packet that has not been received due to timeout, it can be determined that it is lost, and it can be retransmitted later, so as to obtain the packet loss rate and retransmission rate according to the loss and retransmission conditions within a certain time period; it can be seen that the network transmission parameters need to be updated according to the feedback ACK feedback information, so there will be a delay in the update of the network transmission parameters, that is, there is a certain delay between the network situation reflected by the network transmission parameters and the actual network situation, especially when the overall network is congested, the delay phenomenon is more serious. In summary, the existing technology only judges the network quality according to the network transmission parameters, and then adjusts the transmission control parameters according to the judgment result. The method is too dependent on ACK feedback information and has poor timeliness.

[0081] The specific values ​​of the wireless signal parameters can be calculated and obtained by the device in real time, which will not be repeated here.

[0082] The method for detecting network quality in the present application, that is, the step of determining the current network quality classification based on network transmission parameters and wireless signal parameters can be executed periodically, for example, once every 10ms, once every 100ms, etc., or set to be executed after receiving an instruction, and the present application does not make specific limitations. In each detection cycle, the device side can detect whether new ACK feedback information is received in this cycle. If not, the network transmission parameters of the previous detection cycle are used. If received, the network transmission parameters of the previous detection cycle can be updated based on the received ACK feedback information, and the updated network transmission parameters are used to perform subsequent operations. The detailed process of determining the current network quality classification will be described in detail later and will not be repeated here.

[0083] It should be noted that the specific examples of network transmission parameters and wireless signal parameters mentioned above are only for illustration and are not specifically limited in this application.

[0084] S203: The device side obtains current fusion feature parameters based on the wireless signal parameters and the network transmission parameters.

[0085] S204: The device determines the current network quality classification based on the pre-determined fusion feature parameters corresponding to different network quality classifications and the current fusion feature parameters.

[0086] The present application also takes into account that the main purpose of video transmission is to ensure the quality of the video. Therefore, in addition to the wireless signal parameters and the network transmission parameters, the video quality parameters corresponding to the currently transmitted video can also be added to the fusion feature parameters. That is, the current network quality classification is judged in combination with the video quality parameters, the wireless signal parameters and the network transmission parameters. Specifically, the device side obtains the current fusion feature parameters based on the wireless signal parameters, the network transmission parameters and the video quality parameters, and then determines the current network quality classification according to the fusion feature parameters corresponding to the predetermined different network quality classifications.

[0087] Video quality parameters may specifically include picture delay, freeze rate, frame loss rate, video bit rate, etc.

[0088] There are usually multiple network quality classifications, and the quality of the network represented by each network quality classification is different. For example, four network quality classifications can be pre-divided, namely network quality classification L1, network quality classification L2, network quality classification L3, and network quality classification L4. Among them, the network situation represented by network quality classification L1 is the worst network quality, and the network situation represented by network quality classification L4 is the best network quality. Afterwards, some historical data groups are divided into major categories, and each historical data group is divided into corresponding network quality classifications.

[0089] The correspondence between the network quality classification and the fusion feature parameter is obtained by further dividing the historical data group contained in each network quality classification after the historical data group is divided into major categories. Each network quality classification contains at least one fusion feature parameter.

[0090] The above two division processes are introduced in detail below.

[0091] An optional implementation is to obtain historical fusion feature parameters at different times;

[0092] For each historical fusion feature parameter, the network quality classification corresponding to the historical fusion feature parameter is determined according to whether the parameters corresponding to the historical fusion feature parameter meet the corresponding business constraints and the priority of each parameter; then, the historical fusion feature parameters in each network quality classification are clustered, and the fusion feature parameters corresponding to different levels of network quality classification are determined according to the clustering results.

[0093] In the above, the historical fusion feature parameters are obtained by extracting features, normalizing, and fusing features of the historical data group. A historical data group includes multiple parameters at a historical moment. For example, a historical data group may include wireless signal parameters and network transmission parameters at a historical moment; or, it may include video quality parameters, wireless signal parameters, and network transmission parameters at a historical moment. Therefore, the process of dividing and classifying the historical data group is the process of dividing and classifying the corresponding historical fusion feature parameters.

[0094] Wireless signal parameters may further include at least one of wireless signal strength, channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, and wireless receiving signal-to-noise ratio; network transmission parameters may include at least one of round-trip delay, packet loss rate, and retransmission rate; video quality parameters may include at least one of surface delay, freeze rate, frame loss rate, and video bit rate.

[0095] Assume that a historical data set includes video quality parameters, wireless signal parameters, and network transmission parameters. Specifically, the video quality parameters include a frame loss rate of 0.5% and a video bit rate of 3 Mbps. The wireless signal parameters include a wireless signal strength of -30 dBm and a channel utilization of 20%. The network transmission parameters include a packet loss rate of 0.8%, a round-trip delay of 45 ms, and a retransmission rate of 1%.

[0096] By performing feature extraction, normalization, feature fusion and other processing on the above data, historical fusion feature parameters corresponding to the historical data group can be obtained. Specifically, in the feature extraction step, the frame loss rate of 0.5%, the video bit rate of 3Mbps, the wireless signal strength of -30dBm, the channel utilization rate of 20%, the packet loss rate of 0.8%, the round-trip delay of 45ms, and the retransmission rate of 1% can be directly used as feature 1, feature 2, feature 3, feature 4, feature 5, feature 6, and feature 7. Normalization is to unify the above parameters into the interval [0, 1] to reduce the difference between the numerical values; feature fusion is to fuse the above seven features based on the feature weights, which can be fused into a numerical value, or into a vector or matrix, that is, the historical fusion feature parameter can be a numerical value, a vector or a matrix, which can be selected according to the actual situation and is not specifically limited in this application.

[0097] The process of determining the network quality classification corresponding to the historical fusion feature parameters, that is, the process of major classification can be carried out in the following manner: the parameter with the highest priority among all parameters is taken as the current parameter; if the current parameter does not meet the corresponding business constraints, then according to the correspondence between different preset priorities and network quality classifications, the target network quality classification corresponding to the priority of the current parameter is determined, which is the network quality classification corresponding to a historical fusion feature parameter; otherwise, the parameter with the next priority is selected as the current parameter, and it is determined again whether the current parameter meets the corresponding business constraints; if all parameters in a historical fusion feature parameter meet the corresponding business constraints, a historical fusion feature parameter is determined to correspond to the specified network quality classification.

[0098] In the above, each parameter is the parameter required for obtaining the historical fusion feature parameter, such as the wireless signal parameter, network transmission parameter and video quality parameter in the previous embodiment. These three parameters have preset priorities. For example, considering that the most important thing for video transmission is to ensure video quality, the video quality parameter can be set to the highest priority. Compared with the wireless signal parameter, the network transmission parameter has a greater impact on the overall network quality. The network transmission parameter can be set to the second priority, and the wireless signal parameter can be set to the third priority, that is, the lowest priority.

[0099] The highest priority can be further set to correspond to the network quality classification L1, which indicates extremely poor network quality; the second priority can be set to correspond to the network quality classification L2, which indicates relatively poor network quality; the third priority can be set to correspond to the network quality classification L3, which indicates average network quality. The designated network quality classification can be the network quality classification L4, which indicates good network quality. That is, the network signal quality from L1 to L4 is getting better and better.

[0100] The service constraints can also be set into three types, namely, video transmission quality constraints corresponding to video quality parameters, network transmission quality constraints corresponding to network transmission parameters, and wireless quality constraints corresponding to wireless signal parameters.

[0101] Since the video quality parameter has the highest priority, we first determine whether the video quality parameter corresponding to a historical fusion feature parameter (or a historical data group) meets the video transmission quality constraint. If not, we directly classify the historical fusion feature parameter (or the historical data group) into the network quality classification L1. That is, the historical fusion feature parameter (or the historical data group) corresponds to the network quality classification L1.

[0102] If it is satisfied, then determine whether the network transmission parameters of the second priority meet the network transmission quality constraints. If not, then classify the historical fusion feature parameters (or the historical data group) into network quality classification L2, that is, the historical fusion feature parameters (or the historical data group) correspond to the network quality classification L2.

[0103] If it is satisfied, determine whether the wireless signal parameters of the third priority level meet the wireless quality constraints; if not, classify the historical fusion feature parameters (or the historical data group) into network quality classification L3, that is, the historical fusion feature parameters (or the historical data group) correspond to the network quality classification L3.

[0104] If all parameters corresponding to the historical fusion feature parameter (or the historical data group) can meet their respective business constraints, it means that the current network quality is good, and the historical fusion feature parameter (or the historical data group) can be classified into the specified network quality classification L4, that is, the historical fusion feature parameter (or the historical data group) corresponds to the network quality classification L4.

[0105] To determine whether the parameters meet the corresponding business constraints, it can be done by pre-setting thresholds. For example, the threshold of the video transmission quality constraint is set to α, the threshold of the network transmission quality constraint is set to β, and the threshold of the wireless quality constraint is set to λ. In a historical data group, the corresponding values ​​of the video quality parameters, network transmission parameters, and wireless signal parameters are weighted summed respectively, and the three calculation results are compared with α, β, and λ respectively. Finally, it is determined whether the parameters meet the corresponding business constraints based on the comparison results.

[0106] Afterwards, the historical fusion feature parameters in each network quality classification are clustered. Exemplarily, the number of levels for each network quality classification can be determined based on a preset total number of levels. If the total number of levels is greater than the total number of network quality classifications, the number of levels for each network quality classification can be determined. The historical fusion feature parameters in each network quality classification are clustered according to the corresponding number of levels. For each network quality classification, the cluster centers corresponding to each level under a network quality classification are respectively used as the fusion feature parameters corresponding to the corresponding level under the network quality classification.

[0107] Assuming that there are 4 network quality categories, if the total number of pre-set levels is also 4, each network quality category corresponds to 1 level. If the total number of pre-set levels is 8, each network quality category can be set to correspond to 2 levels. If the total number of pre-set levels is 5, one of the network quality categories can be set to correspond to 2 levels, and the other network quality categories can each correspond to 1 level.

[0108] Based on the number of levels of each network quality classification, the historical fusion feature parameters contained in each network quality classification are clustered respectively. Assuming that the network quality classification L1 corresponds to n levels, recorded as L1-K1, L1-K2, ..., L1-Kn, n clustering centers can be clustered eventually. These n clustering centers are used as the fusion feature parameters of L1-K1, L1-K2, ..., L1-Kn respectively. That is, the network quality classification L1 corresponds to n fusion feature parameters in total.

[0109] The above clustering process can be completed using clustering algorithms such as kmeans, which is not specifically limited in this application.

[0110] In summary, if Figure 4 As shown, it is a schematic diagram of obtaining fusion feature parameters corresponding to different network quality classifications provided by an embodiment of the present application, which can be completed by a classification model using a clustering method. The classification model extracts each parameter in the historical data group respectively, which can be specifically wireless signal parameters, network transmission parameters and video quality parameters. The wireless signal parameters include wireless signal strength, channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, and wireless receiving signal-to-noise ratio; the network transmission parameters include round-trip delay, packet loss rate, and retransmission rate; the video quality parameters include surface delay, freeze rate, frame loss rate, and video bit rate.

[0111] The classification model first extracts video features, network features, and wireless features from the above parameters, and then performs normalization and feature fusion. It then combines business constraints and the priority of each parameter.

[0112] The historical data group is divided into four major categories; in the figure, it is divided into four major categories, that is, there are four network quality classifications; after the major classification is completed, clustering is performed using kmeans and other clustering algorithms according to the preset total number of levels (the total number of levels in the figure is 8, and each network quality classification contains two levels). Each network quality level obtains two cluster centers (such as the hexagonal star in the figure), and each cluster center is used as the fusion feature parameter corresponding to the corresponding level of the corresponding network quality classification, and finally the corresponding relationship between network quality classification-level-fusion feature parameters is obtained.

[0113] Then, in an actual application scenario, the current fusion feature parameter in S203 is input into the model, and the model can output the network quality classification corresponding to the current fusion feature parameter and the specific level under the network quality classification according to the corresponding relationship between the network quality classification-level-fusion feature parameter. This process can be achieved by calculating the distance between the current fusion feature parameter and each fusion feature parameter under each network quality classification, and finally the network quality classification-level corresponding to the fusion feature parameter with the shortest distance is used as the network quality classification-level of the current fusion feature parameter.

[0114] Furthermore, the model can be continuously updated with new data over time to ensure the accuracy of the model.

[0115] S205: If the current network quality classification meets the transmission adjustment condition, the device side adjusts the current transmission control parameters and transmits the video according to the adjusted transmission control parameters.

[0116] The transmission control parameter may include at least one of the congestion window size and the retransmission timeout. Other parameters that can limit the data transmission in the network may also be included, which are not specifically limited in this application. When the network is congested, the amount of data being transmitted in the network can be changed by adjusting the transmission control parameters, reducing the transmission of data to alleviate congestion and improve network quality. The transmission adjustment condition may be that if the current network quality classification is lower than a preset classification level threshold. For example, the network quality classifications are L1, L2, L3, and L4, and each network quality classification includes two levels, namely L1-K1, L1-K2, L2-K3, L2-K4, L3-K5, L3-K6, L4-K7, and L4-K8. Among them, L4-K8 has the highest classification level and L1-K1 has the lowest. Assuming that the classification level threshold is L4-K8, if the current network quality classification is not L4-K8, the transmission control parameters need to be adjusted; assuming that the classification level threshold is L4-K7, if the current network quality classification is lower than L4-K7, the transmission control parameters need to be adjusted.

[0117] Exemplarily, the device side can determine the value of the adjustment factor corresponding to the current network quality classification based on the pre-set correspondence between different network quality classifications and the values ​​of the adjustment factor; and adjust the current transmission control parameters based on the value of the adjustment factor.

[0118] In the present application, the value of the adjustment factor corresponding to the network quality classification can be pre-set by relevant personnel. As shown in Table 1, a network quality classification and adjustment factor comparison table provided in an embodiment of the present application still assumes that the network quality classification is divided into four major categories: L1, L2, L3, and L4. Each major category contains two levels, that is, a total of eight levels. The eight levels increase from top to bottom, and the corresponding network quality increases from top to bottom, that is, L1-K1 corresponds to the worst network quality, and L4-K8 corresponds to the best network quality. Each level corresponds to two adjustment factors θ and γ.

[0119]

[0120] Table 1 Network quality classification and adjustment factor comparison table

[0121] Thereafter, the current transmission control parameters may be adjusted based on the adjustment factor. For example, the congestion window size may be multiplied by the adjustment factor θ to obtain the adjusted congestion window size, and the retransmission timeout period may be multiplied by the adjustment factor γ to obtain the adjusted retransmission timeout period.

[0122] In Table 1, except A4-K8, the remaining network quality classifications (levels) need to adjust the transmission control parameters. That is, in the scenario corresponding to Table 1, the preset classification level threshold is A4-K8. If the current network quality classification is not A4-K8, the device side needs to adjust the transmission control parameters.

[0123] The above adjustment factors and adjustment methods can be changed based on actual conditions, and this application does not make specific limitations.

[0124] Another optional implementation is that the adjustment factor in the present application can also be obtained through a model. Specifically, a large number of training samples can be used to pre-train an adjustment model, and each training sample contains specific values ​​corresponding to historical video quality parameters, specific values ​​corresponding to historical network transmission parameters, specific values ​​corresponding to historical wireless signal parameters, and a sample label. The sample label is the optimal adjustment factor corresponding to the network transmission control parameter under the network quality described by the parameters in the training sample.

[0125] After the adjustment model is trained using the training samples, the detected parameters can be directly input into the trained adjustment model, and the adjustment model can output the corresponding adjustment factors.

[0126] In addition, if the current network quality classification is not lower than the preset classification level threshold, it is divided into the following two cases.

[0127] Case 1: If the current network quality classification is not lower than the preset classification level threshold and no ACK feedback information is received in this detection cycle, it indicates that the current network quality classification is directly determined based on the previously acquired network transmission parameters, that is, it is determined by the unupdated network transmission parameters. At this time, you can return to the step of obtaining the wireless signal parameters and restart the execution of the entire video transmission method proposed in this application.

[0128] Case 2: If the current network quality classification is not lower than the preset classification level threshold, and ACK feedback information is received in this detection cycle, it indicates that the current network quality classification is determined based on the newly acquired network transmission parameters in this detection cycle, that is, it is determined by the updated network transmission parameters. At this time, there is no need to adjust the transmission control parameters, and the next set of video streams can be directly transmitted based on the previous transmission control parameters.

[0129] Based on the above process, Figure 5 As shown, it is an overall flow chart of another video transmission method provided in an embodiment of the present application, and the server specifically performs the following steps:

[0130] Step 501: The device obtains current transmission control parameters.

[0131] Transmission control parameters are used to control data transmission in the network and may include congestion window size, retransmission timeout, etc.

[0132] Step 502: The device obtains wireless signal parameters, network transmission parameters and video quality parameters.

[0133] For the convenience of description, the network transmission parameters in this step are the network transmission parameters of the previous detection cycle, that is, they are obtained based on the ACK feedback information received in the previous detection cycle.

[0134] Among them, the network transmission parameters reflect the transmission performance of the network from the device end to the receiving end, and the wireless signal parameters reflect the transmission performance of the network from the device end to the router.

[0135] Step 503: The device determines the current network quality classification.

[0136] Step 504: The device determines whether ACK feedback information is received. If so, execute step 506; otherwise, execute step 505.

[0137] Step 505: The device determines whether the current network quality classification is lower than the classification level threshold. If so, execute step 508; otherwise, execute step 501.

[0138] The current network quality classification in this step is obtained based on the wireless signal parameters, network transmission parameters and video quality parameters acquired in step 502 .

[0139] Step 506: The device updates various parameters; and redetermines the current network quality classification based on the updated parameters.

[0140] The parameters include at least network transmission parameters, and may also include video quality parameters and wireless signal parameters.

[0141] Step 507: The device determines whether the current network quality classification is lower than the classification level threshold. If so, execute step 508; otherwise, execute step 510.

[0142] The current network quality classification in this step is obtained based on the video quality parameters, network transmission parameters and video quality parameters acquired in step 506 .

[0143] Step 508: The device obtains an adjustment factor corresponding to the current network quality classification.

[0144] Step 509: The device adjusts the transmission control parameters based on the adjustment factor.

[0145] Step 510: The device sends the next set of video streams based on the latest transmission control parameters.

[0146] In addition, subsequent retransmission data packets will also be transmitted based on the latest transmission control parameters.

[0147] In summary, in order to solve the problem of poor timeliness of the method for adjusting transmission control parameters in the prior art, the present application analyzes the current network quality in combination with video quality parameters, network transmission parameters and wireless signal parameters. Compared with the method of judging the network quality by only waiting for the update of network transmission parameters, the present application can improve the timeliness of the perception of network congestion, and the judgment of network quality is more accurate. At the same time, the transmission control parameters are quickly adjusted based on the changes in wireless signals, which can improve the video transmission efficiency.

[0148] Ultimately, the method proposed in this application can improve problems such as increased network transmission delay and sudden increase in packet loss rate caused by untimely congestion perception, reduce network transmission delay, reduce packet loss, ensure the smoothness of video playback, and reduce cache occupancy at the sending and playback ends.

[0149] Based on the same inventive concept, the embodiment of the present application also provides a video transmission device. Figure 6 As shown, it is a schematic diagram of the structure of a video transmission device, which may include:

[0150] The first acquisition unit 601 is used to acquire wireless signal parameters from the device to the wireless access point during video transmission;

[0151] The second acquisition unit 602 is used to acquire the network transmission parameters of the transmission network from the device end to the receiving end based on the ACK feedback information fed back by the receiving end;

[0152] A third acquisition unit 603 is used to obtain current fusion feature parameters based on wireless signal parameters and network transmission parameters;

[0153] A determination unit 604, configured to determine a current network quality classification according to a current fused feature parameter based on the predetermined fused feature parameters corresponding to different network quality classifications;

[0154] The adjustment unit 605 is configured to adjust the current transmission control parameters if the current network quality classification satisfies the transmission adjustment condition, and transmit the video according to the adjusted transmission control parameters.

[0155] Optionally, the wireless signal parameter includes at least one of the following:

[0156] Wireless signal strength RSSI, channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, wireless receiving signal-to-noise ratio;

[0157] The network transmission parameters include at least one of the following:

[0158] Round-trip delay, packet loss rate, and retransmission rate.

[0159] Optionally, the fused feature parameter also includes a video quality parameter, and the device further includes:

[0160] A fourth acquisition unit 606 is used to acquire a video quality parameter corresponding to the currently transmitted video;

[0161] Wherein, the current fusion feature parameters are obtained based on the wireless signal parameters, the network transmission parameters and the video quality parameters.

[0162] Optionally, the device further comprises:

[0163] The clustering unit 607 is used to pre-determine the fusion feature parameters corresponding to different network quality classifications in the following manner:

[0164] Obtain historical fusion feature parameters at different times;

[0165] For each historical fusion feature parameter, determine a network quality classification corresponding to the historical fusion feature parameter according to whether each parameter corresponding to the historical fusion feature parameter satisfies a corresponding service constraint and the priority of each parameter;

[0166] The historical fusion feature parameters in each network quality classification are clustered, and the fusion feature parameters corresponding to different levels of network quality classification are determined according to the clustering results.

[0167] Optionally, the clustering unit 607 is specifically used for:

[0168] The parameter with the highest priority among all parameters is taken as the current parameter;

[0169] If the current parameter does not meet the corresponding business constraints, the target network quality classification corresponding to the priority of the current parameter is determined according to the correspondence between different preset priorities and network quality classifications, which is a network quality classification corresponding to a historical fusion feature parameter. Otherwise, the parameter of the next priority is selected as the current parameter, and it is determined again whether the current parameter meets the corresponding business constraints.

[0170] If all parameters in a historical fusion feature parameter meet the corresponding service constraints, it is determined that a historical fusion feature parameter corresponds to a specified network quality classification.

[0171] Optionally, the clustering unit 607 is specifically used for:

[0172] According to the preset total number of levels, if the total number of levels is greater than the total number of network quality categories, determine the number of levels for each network quality category;

[0173] The historical fusion feature parameters in each network quality classification are clustered according to the corresponding level number;

[0174] For each network quality classification, the cluster centers corresponding to each level under a network quality classification are respectively used as fusion feature parameters corresponding to the corresponding level under a network quality classification.

[0175] Optionally, the transmission control parameter includes at least one of a congestion window size and a retransmission timeout period.

[0176] Optionally, the adjusting unit 605 is specifically configured to:

[0177] Determine the value of the adjustment factor corresponding to the current network quality classification based on the preset correspondence between different network quality classifications and the values ​​of the adjustment factors;

[0178] Based on the value of the adjustment factor, the current transmission control parameter is adjusted.

[0179] After introducing the video transmission method and device according to the exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is introduced.

[0180] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0181] Refer to the following Figure 7 The electronic device 700 implemented according to this embodiment of the present application is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0182] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The electronic device can be a mobile phone, a computer, a camera device, such as Figure 1A and Figure 1B The device end 110 is shown. The components of the electronic device 700 may include but are not limited to: the at least one processor 701, the at least one memory 702, and a bus 703 connecting different system components (including the memory 702 and the processor 701).

[0183] Bus 703 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0184] The memory 702 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 7021 and / or a cache memory 7022 , and may further include a read-only memory (ROM) 7023 .

[0185] The memory 702 may also include a program / utility 7025 having a set (at least one) of program modules 7024, such program modules 7024 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0186] The electronic device 700 may also communicate with one or more external devices 704 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other electronic devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 705.

[0187] In addition, the electronic device 700 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through the network adapter 706. Figure 7 As shown, the network adapter 706 communicates with other modules for the electronic device 700 via the bus 703. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0188] In an exemplary embodiment, a storage medium is also provided, in which a computer executable instruction is stored, and the computer executable instruction is used to implement the method for configuring the message address of the embodiment of the present application. When the computer executable instruction in the storage medium is executed by the processor of the electronic device, the electronic device can execute the above-mentioned method for configuring the message address. Optionally, the storage medium can be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0189] In an exemplary embodiment, the electronic device of the present application may include at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor may execute the steps of the corresponding message address configuration method provided in the embodiment of the present application.

[0190] In an exemplary embodiment, a computer program product is also provided. When the computer program product is executed by an electronic device, the electronic device can implement any exemplary method provided in the present application.

[0191] Furthermore, the computer program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0192] The program product for message address configuration in the embodiment of the present application may adopt a CD-ROM and include program code, and may be run on a computing device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, an apparatus or a device.

[0193] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0194] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0195] Program codes for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network such as a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect via the Internet).

[0196] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0197] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0198] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0199] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0200] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0201] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0202] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A video transmission method, characterized in that: The method comprises: During the video transmission process, the wireless signal parameters from the device to the wireless access point are obtained; Based on the confirmation response ACK feedback information fed back by the receiving end, obtaining the network transmission parameters of the transmission network from the device end to the receiving end; Obtaining current fusion feature parameters based on the wireless signal parameters and the network transmission parameters; Based on the predetermined fusion feature parameters corresponding to different network quality classifications, determining the current network quality classification according to the current fusion feature parameters; If the current network quality classification meets the transmission adjustment condition, the current transmission control parameter is adjusted, and the video is transmitted according to the adjusted transmission control parameter.

2. The method according to claim 1, characterized in that The wireless signal parameters include at least one of the following: Wireless signal strength RSSI, channel utilization, wireless packet loss rate, wireless retransmission rate, wireless negotiation rate, wireless receiving signal-to-noise ratio; The network transmission parameters include at least one of the following: Round trip delay, packet loss rate, and retransmission rate.

3. The method according to claim 1, characterized in that The fusion feature parameters also include video quality parameters, and the method further includes: Get the video quality parameters corresponding to the currently transmitted video; Wherein, the current fusion feature parameter is obtained based on the wireless signal parameter, the network transmission parameter and the video quality parameter.

4. The method according to any one of claims 1 to 3, characterized in that: The fusion feature parameters corresponding to different network quality classifications are determined in advance in the following manner: Obtaining historical fusion feature parameters at different moments; the historical fusion feature parameters are obtained by extracting features, normalizing, and fusing features of a historical data group; a historical data group includes wireless signal parameters and network transmission parameters at a historical moment, or includes video quality parameters, wireless signal parameters, and network transmission parameters at the historical moment; For each historical fusion feature parameter, determine the network quality classification corresponding to the historical fusion feature parameter according to whether the parameters corresponding to the historical fusion feature parameter meet the corresponding service constraints and the priority of the parameters; The historical fusion feature parameters in each network quality classification are clustered, and the fusion feature parameters corresponding to different levels of network quality classification are determined according to the clustering results.

5. The method according to claim 4, characterized in that The determining, according to whether each parameter corresponding to a historical fusion feature parameter satisfies a corresponding service constraint and the priority of each parameter, a network quality classification corresponding to the historical fusion feature parameter includes: The parameter with the highest priority among the parameters is used as the current parameter; If the current parameter does not meet the corresponding service constraint, then according to the correspondence between different preset priorities and network quality classifications, determine the target network quality classification corresponding to the priority of the current parameter, which is the network quality classification corresponding to the one historical fusion feature parameter; otherwise, select the parameter of the next priority as the current parameter, and determine again whether the current parameter meets the corresponding service constraint; If all parameters in the one historical fusion feature parameter meet the corresponding service constraints, it is determined that the one historical fusion feature parameter corresponds to a specified network quality classification.

6. The method according to claim 4, characterized in that Cluster the historical fusion feature parameters in each network quality classification, and determine the fusion feature parameters corresponding to different levels of network quality classification based on the clustering results, including: According to a preset total number of levels, if the total number of levels is greater than the total number of network quality categories, determining the number of levels for each network quality category; Clustering the historical fusion feature parameters in each network quality classification according to the corresponding number of levels; For each network quality classification, the cluster centers corresponding to each level under a network quality classification are respectively used as fusion feature parameters corresponding to the corresponding level under the network quality classification.

7. The method according to any one of claims 1 to 3, 5 to 6, characterized in that: The transmission control parameter includes at least one of a congestion window size and a retransmission timeout period.

8. The method according to claim 1, characterized in that Adjust the current transmission control parameters, including: Determine the value of the adjustment factor corresponding to the current network quality classification based on the preset correspondence between different network quality classifications and the values ​​of the adjustment factors; Based on the value of the adjustment factor, the current transmission control parameter is adjusted.

9. A video transmission device, characterized in that: include: A first acquisition unit is used to acquire wireless signal parameters from a device to a wireless access point during video transmission; A second acquisition unit, configured to acquire a network transmission parameter of a transmission network from the device end to the receiving end based on ACK feedback information fed back by the receiving end; A third acquisition unit, configured to obtain a current fusion feature parameter based on the wireless signal parameter and the network transmission parameter; A determination unit, configured to determine a current network quality classification according to the current fused feature parameters based on the predetermined fused feature parameters corresponding to different network quality classifications; The adjustment unit is used to adjust the current transmission control parameters if the current network quality classification meets the transmission adjustment conditions, and transmit the video according to the adjusted transmission control parameters.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: It includes a computer program, and when the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any method described in claims 1 to 8.

12. A computer program product, characterized in that The method comprises a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device executes the steps of any one of the methods described in claims 1 to 8.

Images