Data transmission method and device, computer equipment, medium and program product

Abstract

The invention relates to the technical field of computers, and discloses a data transmission method and device, computer equipment, a medium and a program product, and the method comprises the steps: obtaining a first network feature under a first transmission control strategy, determining a first network category based on the correlation between the first network feature and each network category, querying the transmission control strategy based on the first network category, and obtaining a second transmission control strategy, and controlling data transmission based on the second transmission control strategy. According to the method, the first network category is determined by calculating the correlation between the first network features and the network category, the first network features are screened, the number of the features is reduced, and the accuracy of subsequently determining the network category can be improved. And querying the corresponding transmission control strategy according to the obtained first network category, thereby determining the second transmission control strategy corresponding to the re-classified data transmission, and optimizing the data transmission process.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a data transmission method, apparatus, computer equipment, medium and program product. Background Art

[0002] The current Internet is full of various applications. Affected by the network quality, users' experience of using applications varies. Specifically, when the network environment is good, the data transmission performance is good; on the contrary, if the network condition is poor, the data transmission performance will be greatly reduced.

[0003] Based on this, network quality is usually divided into several levels, and optimization is performed for network scenarios with lower quality levels. Therefore, the results of network quality classification directly affect the optimization effect. Accordingly, a data transmission method needs to be provided to optimize data transmission. Summary of the invention

[0004] In view of this, the present disclosure provides a data transmission method, apparatus, computer equipment, medium and program product to solve the problem of data transmission optimization.

[0005] In a first aspect, the present disclosure provides a data transmission method, the method comprising:

[0006] Acquire a first network characteristic under a first transmission control strategy;

[0007] Determining a first network category based on the correlation between the first network feature and each network category;

[0008] querying a transmission control policy based on the first network category to obtain a second transmission control policy;

[0009] Data transmission is controlled based on the second transmission control strategy.

[0010] The data transmission method provided in this embodiment obtains the first network feature under the first transmission control strategy, determines the first network category based on the correlation between the first network feature and each network category, queries the transmission control strategy based on the first network category, obtains the second transmission control strategy, and then controls the data transmission based on the second transmission control strategy. This method determines the first network category by calculating the correlation between the first network feature and the network category, screens the first network feature, reduces the number of features, and can improve the accuracy of subsequent determination of the network category. According to the obtained first network category, the corresponding transmission control strategy is queried to determine the second transmission control strategy corresponding to the reclassified data transmission, thereby optimizing the data transmission process.

[0011] In a second aspect, the present disclosure provides a data transmission device, the device comprising:

[0012] A first feature acquisition module, used to acquire a first network feature under a first transmission control strategy;

[0013] A first category determination module, which determines a first network category based on the correlation between the first network feature and each network category;

[0014] A second policy determination module, configured to query a transmission control policy based on the first network category to obtain a second transmission control policy;

[0015] A data transmission module is used to control data transmission based on the second transmission control strategy.

[0016] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0018] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, where the computer instructions are used to enable a computer to execute the method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 It is a schematic diagram of user experience classification based on network quality of related technologies;

[0021] Figure 2 is a schematic diagram of user experience of network quality classification according to an embodiment of the present disclosure;

[0022] Figure 3 is a flowchart of a data transmission method according to an embodiment of the present disclosure;

[0023] Figure 4 is a schematic diagram of a data transmission method according to an embodiment of the present disclosure;

[0024] Figure 5 is a schematic diagram of a data transmission method according to an embodiment of the present disclosure;

[0025] Figure 6 is a performance diagram of a data transmission method according to an embodiment of the present disclosure;

[0026] Figure 7 is a performance diagram of a data transmission method according to an embodiment of the present disclosure;

[0027] Figure 8 is a structural block diagram of a data transmission device according to an embodiment of the present disclosure;

[0028] Fig. 9 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0030] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0031] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0034] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0035] In order to improve the quality of data transmission, network quality is usually classified, and then network scenarios with low network quality levels can be optimized. In related technologies, network quality is usually classified according to fixed design indicators, but a single network category may contain multiple different network scenarios. Different network quality optimization measures may need to be taken for different network scenarios, which may interfere with each other. In addition, there is a lot of overlap in network scenarios under multiple network categories, and optimization measures for fixed network scenarios are difficult to reuse in other network categories. Figure 1 As shown in the figure, several categories (A1, A2, A3) are distinguished under a relatively poor network quality classification method. Figure 1 It can be seen that under this network quality classification method, the distinction between different categories is low, resulting in large differences in user experience. Figure 2 This is a schematic diagram of user experience under the network quality classification method proposed in this method, Figure 2 As shown, the method proposed in this solution has a greater degree of distinction between different categories, and the difference in user experience is small, which can generally improve the user experience. The method proposed in the present invention is further described below.

[0036] According to an embodiment of the present disclosure, an embodiment of a data transmission method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] In this embodiment, a data transmission method is provided, which can be used in terminals such as computers and tablet computers. Figure 3 is a flow chart of a data transmission method according to an embodiment of the present disclosure. Figure 3 As shown, the process includes the following steps:

[0038] Step S101, obtaining a first network characteristic under a first transmission control strategy.

[0039] The first transmission control strategy represents the default congestion control algorithm (CCA). During data transmission, the system will monitor the arrival of each acknowledgment (ACK) packet at each network connection, and will use the default first transmission control strategy to collect network parameters of the network connection for data transmission in the process. The network parameters may include performance indicators about the network connection. Taking the Transmission Control Protocol (TCP) connection as an example, the performance and stability of the TCP connection are affected by multiple key variables, which play a vital role in the data transmission process. The TCP connection may specifically include Congestion Window, RTT (Round Trip Time), Throughput, SACK Packets, Retransmission, Packet Loss, etc.

[0040] A variety of different types of network features are used to calculate the characteristics of network parameters. Different functions can be used to calculate the corresponding characteristics of different network parameters. The network parameters collected in each network connection may be different, so the corresponding calculated characteristics are different. For a type of network feature, the characteristics of a certain network parameter in each network connection are calculated to form a characteristic value set of the feature, which is the first network feature. In this step, the first transmission control strategy includes multiple data transmissions, that is, multiple network connections, so the first network feature can refer to a characteristic value set of one or more features.

[0041] Step S102: determining the first network category based on the correlation between the first network feature and each network category.

[0042] Each network connection will be initially classified to obtain the corresponding category label of each network connection. The collection of category labels of all network connections constitutes the type label set. Let the type label set be L = {l1,l2,…,l m}, where l m Represents the category label of connection m. Set the set of values ​​of any network feature f in all network connections to be V f ={v1,v2,…,v m},v m represents the value of the network feature f in the connection m. In this embodiment, the first network feature may include multiple feature value sets V f .

[0043] By calculating L and V fThe statistical correlation can specifically obtain the correlation between the network feature and the category. If there is a network feature with a significant correlation with the category, the subsequent classification task can be performed through the network feature, and then the category to which each network connection belongs after adjustment, that is, the first network category, can be obtained. Exemplarily, the FRESH method (scalable time series feature extraction algorithm) can be used to analyze the correlation between the first network feature and the network category, and the HNSW method (graph-based search algorithm) can be used to perform network classification based on the screened network features to obtain the first network category. The specific correlation analysis method and network classification method are not limited in this embodiment.

[0044] Step S103: query the transmission control policy based on the first network category to obtain a second transmission control policy.

[0045] There are the most suitable transmission control strategies for different network categories. Specifically, the correspondence between network categories and transmission control strategies can be determined in advance through experiments and stored. Based on the query of the first network category, the transmission control strategy corresponding to the first network category can be obtained, that is, for any network connection, according to the first network category to which the network connection belongs, the second transmission control strategy (congestion control algorithm) that best matches the network connection can be determined.

[0046] Step S104: Control data transmission based on the second transmission control strategy.

[0047] After the second transmission control strategy is determined, a congestion control algorithm corresponding to the second transmission control strategy is run to control data transmission.

[0048] For example, it is assumed that the transmission control strategy is queried through an offline database. The method shown in this embodiment is as follows: Figure 4 As shown, the default CCA algorithm is used in the data collection phase. The default CCA algorithm is the first transmission control strategy. After correlation analysis, the network quality classification is performed to determine the first network category to which the network connection belongs, and the optimal CCA algorithm corresponding to the first network category is queried in the offline database (i.e., the second transmission control strategy), and the second transmission control strategy is returned. Data transmission is controlled based on the second transmission control strategy. Exemplarily, the algorithms in the figure include Cubic algorithm (Cubic TCP Congestion Control, TCP congestion control algorithm), BBR algorithm (Bottleneck Bandwidthand Round-Trip Time, bottleneck bandwidth and round-trip delay, TCP congestion control algorithm), Copa algorithm (delay-based congestion control algorithm), etc.

[0049] The data transmission method provided in this embodiment obtains the first network feature under the first transmission control strategy, determines the first network category based on the correlation between the first network feature and each network category, queries the transmission control strategy based on the first network category, obtains the second transmission control strategy, and then controls the data transmission based on the second transmission control strategy. This method determines the first network category by calculating the correlation between the first network feature and the network category, screens the first network feature, reduces the number of features, and can improve the accuracy of subsequent determination of the network category. According to the obtained first network category, the corresponding transmission control strategy is queried to determine the second transmission control strategy corresponding to the reclassified data transmission, thereby optimizing the data transmission process.

[0050] In this embodiment, a data transmission method is provided, and the method comprises the following steps:

[0051] Step S201, obtaining a first network characteristic under a first transmission control strategy.

[0052] Specifically, step S201 includes the following steps:

[0053] Step S2011, acquiring response information, and obtaining network parameters of at least one network connection.

[0054] During data transmission, the system will monitor the arrival of each ACK packet at each network connection, that is, the response information, and will use the default first transmission control strategy to collect network parameters of at least one network connection. The network parameters are variables, and the state of each variable is collected during each response process. The network characteristics of the network connection at K responses can be collected according to the actual application scenario, and the network connection includes one or more.

[0055] Step S2012: perform feature calculation based on network parameters to obtain a network feature set corresponding to all network connections.

[0056] The network feature set includes a feature vector corresponding to at least one first network feature.

[0057] Perform feature calculation on network parameters. Different functions can be used to calculate the corresponding features for different network parameters. Calculate the features of any network parameter in each network connection. If multiple types of network features are used for feature calculation, the features of any network parameter in each network connection can be calculated for each type of network feature. The collection of features in all network connections is the feature vector of the first network feature. The network feature set includes at least one feature vector corresponding to the first network feature.

[0058] In some optional implementations, the above step S2012 includes:

[0059] Step a1: perform at least one type of feature calculation based on network parameters to obtain feature values ​​of network features corresponding to each network connection.

[0060] The type includes at least one of a time domain feature, a frequency domain feature, and a statistical feature.

[0061] Time domain features are used to capture the evolution of time series patterns over time, frequency domain features can be used to describe the frequency of change of time series within a specific frequency band, and statistical features describe the statistical properties or probability distribution of time series variables, such as minimum value and skewness. For different types of features, different methods can be used to calculate the characteristics of network parameters. For any network parameter, calculate its characteristic value under any characteristic type in each network connection, so as to obtain the characteristic value of the network characteristic corresponding to each network connection. Exemplarily, in a network connection, for the collected network parameter CongestionWindow, calculate its time domain characteristics, which can be calculated specifically through autocorrelation. Autocorrelation can be used to detect repetitive patterns in the packet loss time series, and obtain the characteristic value of the network parameter in a network connection with respect to the time domain characteristics.

[0062] Step a2: for the same network feature, the feature values ​​corresponding to all network connections are merged to obtain a feature vector corresponding to the first network feature, so as to obtain a network feature set.

[0063] After obtaining the characteristic values ​​of the same network feature in each network connection, all characteristic values ​​are fused to form a characteristic vector corresponding to the first network feature. The first network feature represents the collection of characteristic values ​​of any network feature in all network connections.

[0064] Step S202: determining the first network category based on the correlation between the first network feature and each network category.

[0065] Specifically, step S202 includes the following steps:

[0066] Step S2021, obtaining the initial network category of each network connection.

[0067] Preliminarily classify the categories of each network connection to determine the initial network category corresponding to each network connection.

[0068] Step S2022: based on the correlation between the first network feature and each initial network category, the initial network category of each network connection is updated to determine the first network category.

[0069] The correlation between the first network feature and each initial network category is analyzed, so as to screen the network features corresponding to the first network feature, further classify the network based on the screened network features, and adjust the category to which each network connection belongs. After the adjustment, the category to which each network connection belongs is the first network category.

[0070] In some optional implementations, the above step S2022 includes:

[0071] Step b1, determining a first network category set based on each initial network category;

[0072] Step b2, analyzing the correlation between the first network feature and the first network category set to obtain a first analysis result;

[0073] Step b3: Screening the network features based on the first analysis result, and updating the initial network category of each network connection based on the screened network features to determine the first network category.

[0074] Each network connection will be initially classified to obtain the category label corresponding to each network connection. The collection of category labels of all network connections constitutes a network category set. Let the first network category be L = {l1,l2,…,l m}, where l m Represents the category label of connection m. Set the set of values ​​of any network feature f in all network connections to be V f ={v1,v2,…,v m},v m represents the value of the network feature f in the connection m. In this embodiment, the first network feature may include multiple feature value sets V f .

[0075] The correlation between the first network feature and the first network category set is analyzed to obtain a first analysis result, which includes the correlation between each network feature and the network category. If there is a network feature with a small correlation with any network category, the network features below the correlation threshold can be screened and removed according to the set correlation threshold to obtain screened network features, which have a significant correlation with the network category. The screened network features are used as the basis for network classification, so as to update the network category to which each network connection belongs, and obtain the first network category.

[0076] Step S203: query the transmission control policy based on the first network category to obtain a second transmission control policy.

[0077] Specifically, the above step S203 includes: using the first network category to query the transmission control policy database to obtain the second transmission control policy. The transmission control policy database is used to characterize the optimal transmission control policy corresponding to each network category, and the transmission control policy database is determined based on the correlation between the second network feature of the network connection and each network category.

[0078] The transmission control strategy database is determined based on multiple experiments. Specifically, the optimal transmission control strategy corresponding to different network categories can be determined based on the correlation between the second network feature of the network connection and each network category, that is, the optimal CCA algorithm. After determining the first network category corresponding to each network connection, the transmission control strategy database is queried according to the network category corresponding to each network connection, so as to determine the second transmission control strategy corresponding to each network connection.

[0079] Step S204: Control data transmission based on the second transmission control strategy.

[0080] For details, please see Figure 3 Step S104 of the illustrated embodiment will not be described in detail here.

[0081] In some optional implementations, the data transmission method described in the embodiment of the present invention further includes the following steps:

[0082] Step S301: Obtain a second network feature corresponding to a first connection of a third transmission control strategy.

[0083] The first connection refers to any network connection, and the network connection may be a TCP connection. The third transmission control strategy is a CCA algorithm for data transmission by default, and the default CCA algorithm is used for data transmission in a network connection to collect the corresponding second network feature. The method for obtaining the first network feature is consistent with the method for obtaining the first network feature in step S101 of the above embodiment, and will not be repeated here.

[0084] Step S302: Determine the second network category based on the correlation between the second network feature and each network category.

[0085] The correlation between the second network feature and each network category is analyzed to determine the second network category.

[0086] Specifically, step S302 includes the following steps:

[0087] Step S3021: determine a second network category set based on each network category.

[0088] Step S3022: Analyze the correlation between the second network feature and the second network category set to obtain a second analysis result.

[0089] Step S3023: Filter the network features based on the second analysis result, and update each network category based on the filtered network features to determine the second network category.

[0090] The network category may be an initially set network category or a network category to which a network connection obtained after multiple iterations belongs. A category label corresponding to each network connection is further obtained, and the collection of category labels of all network connections constitutes a second network category set.

[0091] Analyze the correlation between the second network feature and the second network category set to obtain a second analysis result, which includes the correlation between each network feature and the network category. If there is a network feature with a small correlation with any network category, the network features below the correlation threshold can be screened and removed according to the set correlation threshold to obtain the screened network features, which have a significant correlation with the network category. The screened network features are used as the basis for network classification, so as to update the network category to which each network connection belongs, and obtain the second network category.

[0092] Step S303: Use multiple transmission control strategies to control data transmission and obtain performance corresponding to each transmission control strategy.

[0093] During the data transmission process, a variety of transmission control strategies (CCA algorithms) are randomly run, and the algorithm performance corresponding to each transmission control strategy is collected during the data transmission process.

[0094] Step S304: determine the transmission control strategy with the best performance as the optimal transmission control strategy corresponding to the second network category.

[0095] The collected algorithm performances are statistically analyzed to determine the optimal transmission control strategy corresponding to each second network category. The optimal transmission control strategy corresponding to each category may be the same or different.

[0096] Step S305: write the second network category and the corresponding optimal transmission control policy into the transmission control policy database to obtain the transmission control policy database.

[0097] The corresponding relationship between the second network category and the optimal transmission control strategy is stored in the transmission control strategy database, thereby generating a transmission control strategy database. By continuously iterating the above steps S301 to S305, the optimal transmission control strategy corresponding to each network category is formed, and an offline transmission control strategy database can be formed according to actual needs.

[0098] Illustratively, the method of this embodiment is as follows Figure 5As shown in the figure, firstly, in the data collection phase, the default CCA algorithm is used to continue data collection, collect network parameters of network connections, and then classify network quality. The obtained network categories are uploaded to the offline database. In addition, various CCA algorithms are randomly run to obtain the performance of the CCA algorithm when different CCA algorithms are used for network connections of the same network category. Figure 5 As shown in Figure 1, taking network classification 1 as an example, the corresponding algorithm with the best performance is algorithm A.

[0099] The method provided in the embodiment of the present invention realizes that under the same total number of network categories, each category has a smaller difference in application user experience, which lays a foundation for further optimizing the user experience. Figure 6 As shown in the figure, it is a CDF (Cumulative Distribution Function) curve graph, and Relative PredictionError is the relative prediction error, which is one of the indicators to measure the performance of the prediction model. Compared with the existing related technologies, this solution achieves a relative prediction error of 16.93% on the median, and improves the median prediction accuracy by 15.27%-29.26%. Figure 7 As shown, the data transmission method can achieve better transmission performance. Compared with the existing algorithm in file download completion time (FCT), the present scheme has better performance. The smaller the FCT, the better. Among them, the existing congestion control algorithms include CUBIC algorithm (Cubic TCP Congestion Control), BBR algorithm (Bottleneck Bandwidth and Round-Trip Time), West. (TCP Westwood algorithm), Illinois algorithm (Illinois algorithm, adaptive additive increase multiplicative decrease (AIMD) congestion control algorithm), Reno algorithm (Reno algorithm), Vegas algorithm (Vegas algorithm, delay-based TCP congestion control algorithm), Copa algorithm (delay-based congestion control algorithm). This method is also compared with the following methods, including ORCA algorithm (Optimal Reciprocal Collision Avoidance, dynamic obstacle avoidance algorithm), PCC algorithm (Pearson's correlation coefficient, Pearson correlation coefficient algorithm), Aurora (database technology), RR algorithm (Round-Robin Scheduling Algorithm, round-robin scheduling algorithm), Oracle (database technology), etc.

[0100] In this embodiment, a network classification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0101] This embodiment provides a data transmission device, such as Figure 8 As shown, including:

[0102] A first feature acquisition module 401, used to acquire a first network feature under a first transmission control strategy;

[0103] A first category determination module 402, which determines a first network category based on the correlation between the first network feature and each network category;

[0104] A second policy determination module 403, configured to query a transmission control policy based on the first network category to obtain a second transmission control policy;

[0105] The data transmission module 404 is used to control data transmission based on the second transmission control strategy.

[0106] In some optional implementations, the first feature acquisition module 401 includes:

[0107] A parameter acquisition unit, used to acquire the response information and obtain network parameters of at least one network connection;

[0108] A feature set determination unit is used to perform feature calculation based on the network parameters to obtain a network feature set corresponding to all the network connections, wherein the network feature set includes a feature vector corresponding to at least one of the first network features.

[0109] In some optional implementations, the feature set determination unit includes:

[0110] a feature calculation subunit, configured to perform at least one type of feature calculation based on the network parameters to obtain a feature value of a network feature corresponding to each of the network connections, wherein the type includes at least one of a time domain feature, a frequency domain feature, and a statistical feature;

[0111] The feature set generating subunit is used to fuse the feature values ​​corresponding to all the network connections for the same network feature, obtain the feature vector corresponding to the first network feature, and obtain the network feature set.

[0112] In some optional implementations, the first category determination module 402 includes:

[0113] an initial category acquisition unit, configured to acquire an initial network category of each of the network connections;

[0114] The first category determination unit is configured to update the initial network category of each of the network connections based on the correlation between the first network feature and each of the initial network categories, and determine the first network category.

[0115] In some optional implementations, the first category determination unit includes:

[0116] A first category set determining subunit, configured to determine a first network category set based on each of the initial network categories;

[0117] a first analysis result determination subunit, configured to analyze the correlation between the first network feature and the first network category set to obtain a first analysis result;

[0118] The first category determination subunit is used to screen the network features based on the first analysis result, and update the initial network category of each of the network connections based on the screened network features to determine the first network category.

[0119] In some optional implementations, the second strategy determination module 403 includes:

[0120] A query unit is used to use the first network category to query the transmission control policy database to obtain the second transmission control policy, the transmission control policy database is used to characterize the optimal transmission control policy corresponding to each network category, and the transmission control policy database is determined based on the correlation between the second network feature of the network connection and each of the network categories.

[0121] In some optional embodiments, the device further comprises:

[0122] A second feature acquisition module, used to acquire a second network feature corresponding to the first connection of a third transmission control policy;

[0123] A second category determination module, configured to determine a second network category based on the correlation between the second network feature and each network category;

[0124] A performance acquisition module, used to control data transmission using multiple transmission control strategies and obtain the performance corresponding to each transmission control strategy;

[0125] An optimal strategy determination module, used to determine the transmission control strategy with the best performance as the optimal transmission control strategy corresponding to the second network category;

[0126] The database determination module is used to write the second network category and the corresponding optimal transmission control policy into a transmission control policy database to obtain the transmission control policy database.

[0127] In some optional implementations, the second category determination module includes:

[0128] A second category set determining unit, configured to determine a second network category set based on each network category;

[0129] A second analysis unit, configured to analyze the correlation between the second network feature and the second network category set to obtain a second analysis result;

[0130] The second category determination unit is used to screen the network features based on the second analysis result, and update each network category based on the screened network features to determine a second network category.

[0131] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0132] The data transmission device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0133] The present disclosure also provides a computer device having the above Figure 8 The data transmission device shown.

[0134] See also Fig. 9 , Fig. 9 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Fig. 9 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 10 is taken as an example.

[0135] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0136] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0137] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0139] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0140] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0141] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0142] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the present invention.

Claims

1. A data transmission method, characterized in that: The method comprises: Acquire a first network characteristic under a first transmission control strategy; Determining a first network category based on the correlation between the first network feature and each network category; querying a transmission control policy based on the first network category to obtain a second transmission control policy; Data transmission is controlled based on the second transmission control strategy.

2. The method according to claim 1, characterized in that The obtaining of the first network characteristic under the first transmission control strategy includes: Acquire response information and obtain network parameters of at least one network connection; Feature calculation is performed based on the network parameters to obtain a network feature set corresponding to all the network connections, wherein the network feature set includes a feature vector corresponding to at least one of the first network features.

3. The method according to claim 2, characterized in that The performing feature calculation based on the network parameters to obtain a network feature set corresponding to all the network connections includes: Perform at least one type of feature calculation based on the network parameters to obtain feature values ​​of network features corresponding to each of the network connections, where the type includes at least one of a time domain feature, a frequency domain feature, and a statistical feature; For the same network feature, the feature values ​​corresponding to all the network connections are merged to obtain the feature vector corresponding to the first network feature, so as to obtain the network feature set.

4. The method according to claim 2, characterized in that: The determining the first network category based on the correlation between the first network feature and each network category includes: Obtaining an initial network category of each of the network connections; Based on the correlation between the first network feature and each of the initial network categories, the initial network category of each of the network connections is updated to determine the first network category.

5. The method according to claim 4, characterized in that The updating of the initial network category of each of the network connections based on the correlation between the first network feature and each of the initial network categories to determine the first network category includes: Determine a first network category set based on each of the initial network categories; Analyzing the correlation between the first network feature and the first network category set to obtain a first analysis result; The network features are screened based on the first analysis result, and the initial network category of each of the network connections is updated based on the screened network features to determine the first network category.

6. The method according to claim 1, characterized in that The querying of the transmission control policy based on the first network category to obtain the second transmission control policy includes: The first network category is used to query the transmission control policy database to obtain the second transmission control policy. The transmission control policy database is used to characterize the optimal transmission control policy corresponding to each network category. The transmission control policy database is determined based on the correlation between the second network feature of the network connection and each of the network categories.

7. The method according to claim 6, characterized in that The method further comprises: Obtain a second network characteristic corresponding to the first connection of the third transmission control policy; Determining a second network category based on the correlation between the second network feature and each network category; Using multiple transmission control strategies to control data transmission and obtain performance corresponding to each of the transmission control strategies; Determining the transmission control strategy with the best performance as the optimal transmission control strategy corresponding to the second network category; The second network category and the corresponding optimal transmission control policy are written into a transmission control policy database to obtain the transmission control policy database.

8. The method according to claim 6, characterized in that The determining the second network category based on the correlation between the second network feature and each network category includes: determining a second set of network categories based on the respective network categories; analyzing the correlation between the second network feature and the second network category set to obtain a second analysis result; The network features are screened based on the second analysis result, and each network category is updated based on the screened network features to determine a second network category.

9. A data transmission device, characterized in that: The device comprises: A first feature acquisition module, used to acquire a first network feature under a first transmission control strategy; A first category determination module, which determines a first network category based on the correlation between the first network feature and each network category; A second policy determination module, configured to query a transmission control policy based on the first network category to obtain a second transmission control policy; A data transmission module is used to control data transmission based on the second transmission control strategy.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the data transmission method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the data transmission method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the data transmission method according to any one of claims 1 to 8.

Images