CN112217605B - Transmission policy selection method, device and storage medium - Google Patents

Transmission policy selection method, device and storage medium Download PDF

Info

Publication number
CN112217605B
CN112217605B CN202010928114.8A CN202010928114A CN112217605B CN 112217605 B CN112217605 B CN 112217605B CN 202010928114 A CN202010928114 A CN 202010928114A CN 112217605 B CN112217605 B CN 112217605B
Authority
CN
China
Prior art keywords
network system
transmission
network
preset
section
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010928114.8A
Other languages
Chinese (zh)
Other versions
CN112217605A (en
Inventor
王昱丹
陈文娟
陈文生
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wangsu Science and Technology Co Ltd
Original Assignee
Wangsu Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wangsu Science and Technology Co Ltd filed Critical Wangsu Science and Technology Co Ltd
Priority to CN202010928114.8A priority Critical patent/CN112217605B/en
Publication of CN112217605A publication Critical patent/CN112217605A/en
Application granted granted Critical
Publication of CN112217605B publication Critical patent/CN112217605B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
    • H04L1/0015—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the adaptation strategy
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/163—In-band adaptation of TCP data exchange; In-band control procedures

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Quality & Reliability (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a transmission strategy selection method, transmission strategy selection equipment and a storage medium. In the invention, the mapping table of the IP section and the network system is constructed based on the principle that the IP section and the network system from the same base station are corresponding, and before the transmission strategy is selected, the preset network system corresponding to the IP section information provided by the client is searched in the preset IP section and the network system mapping table, and then the searched network system is used as the target type of the network for TCP service transmission with the client for providing the IP section information, namely the target network system, thereby effectively ensuring the accuracy of the determined target network system, and finally, the adaptive target transmission strategy is selected in a targeted way according to the actually determined target network system, so that the transmission strategy according to which the TCP transmission service is transmitted can take account of the difference in transmission of different network systems, thereby avoiding the influence of different network systems on the transmission quality, and further effectively promoting the improvement of the overall transmission quality of the TCP transmission layer.

Description

Transmission policy selection method, device and storage medium
Technical Field
The embodiment of the invention relates to the technical field of computer networks, in particular to a transmission strategy selection method, transmission strategy selection equipment and a storage medium.
Background
At present, domestic network modes are divided into wireless network WIFI and MOBILE network MOBILE (comprising 2G, 3G, 4G and 5G), and WIFI and 4G are the most common at present. WIFI is mainly suitable for indoor, 4G is more suitable for outdoor, and for the user, the transmission quality of WIFI is mainly influenced by the distance between equipment and a router and the performance of the router, and the transmission quality of 4G is influenced by the congestion degree of a base station, the performance of equipment and the signal strength which can be received by the equipment. In most cases, WIFI surfing is stable, and transmission quality is relatively good in 4G. For the CDN manufacturer, the acceleration service makes a transmission policy targeted mainly according to the service characteristics and the evaluation index, for example, when the evaluation index of the on-demand service is a katon rate, in order to reduce video playing katon, the transmission policy needs to be configured to send packets at a faster and more stable speed, but the transmission policy can cause congestion and even packet loss of the transmission service more easily; in contrast, when the evaluation index is the packet loss rate, the transmission policy needs to be configured to reduce the packet loss as much as possible.
However, since a fixed transmission policy is generally selected for the acceleration service of the same domain name at present, it is difficult to consider the transmission difference of different network systems in policy, so that the influence of different network systems on quality is ignored, and the transmission quality cannot be sufficiently improved.
Disclosure of Invention
An object of an embodiment of the present invention is to provide a method, an apparatus, and a storage medium for selecting a transmission policy, which aim to solve the above technical problems.
In order to solve the above technical problems, an embodiment of the present invention provides a method for selecting a transmission policy, including the following steps:
acquiring IP section information of a client;
searching a preset network system corresponding to the IP section information in a preset IP section and network system mapping table;
taking the searched preset network system as a target network system;
and selecting a transmission strategy from preset transmission strategies as a target transmission strategy according to the target network system, so as to execute Transmission Control Protocol (TCP) transmission service based on the target transmission strategy.
The embodiment of the invention also provides a transmission strategy selection device, which comprises:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the transmission policy selection method as described above.
Embodiments of the present invention also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements a method of selecting a transmission policy as described above.
Compared with the prior art, the embodiment of the invention constructs the mapping table of the IP section and the network system based on the principle that the IP section and the network system from the same base station are corresponding, and before selecting the transmission strategy, searches the preset network system corresponding to the IP section information provided by the client in the preset IP section and the network system mapping table, and further uses the searched network system as the target type of the network for TCP service transmission with the client for providing the IP section information, namely the target network system, thereby effectively ensuring the accuracy of the determined target network system, and finally, according to the actually determined target network system, the adaptive target transmission strategy is selected in a targeted manner, so that the transmission strategy according to which the TCP transmission service is transmitted can take account of the difference in transmission of different network systems, thereby avoiding the influence of different network systems on the transmission quality, and further effectively promoting the improvement of the overall transmission quality of the TCP transmission layer.
In addition, after searching the preset network system corresponding to the IP segment information in the preset IP segment and network system mapping table, the method further comprises the following steps: if a preset network system corresponding to the IP section information is found in a preset IP section and network system mapping table, executing the step of taking the found preset network system as a target network system; otherwise, acquiring the characteristic information of the TCP transmission layer, analyzing and processing the characteristic information by using a preset network system determining model, determining a network system corresponding to the characteristic information, taking the determined network system group as the target network system, and executing the step of selecting one transmission strategy from preset transmission strategies as a target transmission strategy according to the target network system. When the preset network system corresponding to the IP section information provided by the client is not found in the preset IP section and network system mapping table, the characteristic information of the TCP transmission layer is analyzed and processed through a network system determining model obtained based on pre-training, so that the network system is determined, and the defects of the IP section and the network system mapping table are overcome.
In addition, after the characteristic information is analyzed and processed by using the preset network system determining model and the network system corresponding to the characteristic information is determined, the method further comprises: and establishing a corresponding relation between the IP section information and the network system, and adding the corresponding relation into the mapping table of the IP section and the network system. By updating the preset IP section and network system mapping table according to actual conditions, the information recorded in the IP section and network system mapping table can be richer, and more network systems suitable for different clients are covered.
In addition, the training of the network type determining model comprises the following steps: acquiring characteristic information of a TCP transmission layer corresponding to a known network system and a network system class mark of the known network system to obtain a training sample; constructing a network training model according to a preset machine learning algorithm; and carrying out iterative training on the network type training model by using the training sample until a preset iteration termination condition is met, so as to obtain the network type determining model.
In addition, the obtaining the characteristic information of the TCP transmission layer corresponding to the known network system includes: and acquiring the maximum message segment length received by the TCP transmission layer and the initial receiving window size of the client during the period from the start of establishing the connection to the start of sending the packet, and obtaining the characteristic information of the TCP transmission layer corresponding to the known network system. The maximum message segment length and the initial receiving window size of the client are selected as characteristic information of the TCP transmission layer corresponding to the known network system, so that the network system determination model obtained by final training has certain generalization while giving consideration to the accuracy, namely, one network system determination model can be suitable for TCP transmission services of clients and servers in different areas.
In addition, the obtaining the maximum segment length received by the TCP transport layer and the initial receiving window size of the client during the period from the start of establishing the TCP connection to the start of sending the packet, to obtain the characteristic information of the TCP transport layer corresponding to the known network system, includes: and acquiring the maximum message segment length carried in the first TCP request received by the TCP transmission layer and the initial receiving window size of the client during the period from the start of the connection establishment to the start of the packet sending, and obtaining the characteristic information of the TCP transmission layer corresponding to the known network system. For long connection, only the first TCP request has a value, so that when a network type determining model is trained, only the maximum message segment length carried in the first TCP request and the initial receiving window size of the client are obtained as the characteristic information of the TCP transmission layer corresponding to the known network type, and the influence of multiple accesses of a single client IP can be avoided.
In addition, the obtaining the network type class label of the known network type includes: acquiring a log or a URL reported by a client; and obtaining the network type class mark of the known network type from the log or the URL.
In addition, the obtaining the network type class mark of the known network type from the log or the URL includes: analyzing the log or the URL to obtain an analysis result; judging whether the analysis result comprises network system information or not; and if the network type information is included, acquiring the network type class mark of the known network type from the network type information.
In addition, after the determining whether the analysis result includes network system information, the method further includes: if the analysis result does not include the network system information, a testing environment is built, the known network system is marked manually based on the packet capturing identification of the testing environment, and the network system class mark of the known network system is obtained.
In addition, the construction of the IP segment and the network mapping table includes: analyzing and processing sample characteristic information in a sample characteristic set by using the network type determining model, and determining a network type corresponding to each piece of sample characteristic information, wherein the sample characteristic information is characteristic information of a TCP transmission layer provided by clients of different IPs in the same IP section collected in advance; counting the number of the IP corresponding to the determined different network systems; selecting network systems with the number of the IPs meeting preset conditions as preset network systems corresponding to the IP sections; and establishing a corresponding relation between the IP section and the preset network system to obtain a mapping table of the IP section and the network system.
Drawings
One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which the figures of the drawings are not to be taken in a limiting sense, unless otherwise indicated.
Fig. 1 is a specific flowchart of a selection method of a transmission policy according to a first embodiment of the present application;
fig. 2 is a specific flowchart of a method of selecting a transmission policy according to a second embodiment of the present application;
fig. 3 is a schematic diagram of a junction structure of a selection device of a transmission policy according to a third embodiment of the present application;
fig. 4 is a schematic structural view of a transmission policy selection device according to a fourth embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those of ordinary skill in the art that in various embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the claimed technical solution of the present application can be realized without these technical details and various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not be construed as limiting the specific implementation of the present application, and the embodiments can be mutually combined and referred to without contradiction.
The first embodiment relates to a transmission policy selection method, which is applied to a transmission policy selection device, and in practical application, the transmission policy selection device is, for example, a server, and for convenience of explanation, this embodiment uses the transmission policy selection device as an example to explain.
Implementation details of the selection method of the transmission policy of the present embodiment are described below, and the following details are provided only for convenience of understanding, and are not necessary to implement the present embodiment.
The specific flow of this embodiment is shown in fig. 1, and specifically includes the following steps:
and step 101, acquiring IP segment information of the client.
Specifically, the IP address is allocated by the network interface controller (Network Information Center, NIC) according to the network size of the user unit and the recent development plan. Conceptually, each IP address may consist of two parts, namely a network identification netid and a host identification hostid. In fact, IP addresses can be classified into three categories A, B, C.
That is, in general, the acquired IP section information may include class a IP section information (ip_a section information), class B IP section information (ip_b section information), class C IP section information (ip_c section information).
Typically, ip_a segment addresses are assigned to a few very large-scale networks, ip_b segment addresses are assigned to medium-scale networks, and ip_c segment addresses are assigned to small-scale networks. Therefore, in actual use, whether the acquired IP section information is the ip_a section information, the ip_b section information, or the ip_c section information may be set according to the size of the network scale.
For convenience of explanation, this embodiment takes the IP segment information obtained from the client as the ip_c segment information as an example, that is, the IP segment information used to determine the target network system is the ip_c segment information.
In addition, it should be noted that in this embodiment, the IP segment information is selected to determine the network system, because the IP segment information coming out of the same base station, whether it is ip_a segment information, ip_b segment information, or ip_c segment information, is fixed, and because in practical application, the number of base stations is limited, the target network system of the network where the client is currently located can be quickly determined by means of table lookup based on the limited number and the fixed IP segment information.
Step 102, searching a preset network system corresponding to the IP segment information in a preset IP segment and network system mapping table.
As can be seen from the above description, the selected IP segment information in the present embodiment is the ip_c segment information, so the preset IP segment and the network mapping table also need to be a mapping table established based on the ip_c segment information and the corresponding network.
Accordingly, when executing the step 102, specifically, a preset network system corresponding to the ip_c piece information obtained from the client in the step 101 is searched in a preset ip_c piece information and network system mapping table.
It should be understood that the above examples are only examples listed for better understanding of the technical solution of the present embodiment, and are not the only limitation of the present embodiment.
In addition, in order to facilitate understanding of the technical solution provided in this embodiment, a description will be given here of a technical name of "network system".
The term "network system" is actually the type of network. At present, network systems are generally divided into two main types, one type is wireless network WIFI, and the other type is MOBILE network MOBILE. The MOBILE class can be divided into 2G, 3G, 4G and 5G. Since 5G is not yet fully popular at present, and 2G and 3G have been basically replaced by 4G, the MOBILE described later in this embodiment is mainly 4G.
Accordingly, the preset network system found in step 102 is either WIFI, i.e. the wireless network type, or 4G, i.e. the mobile network type.
It should be understood that, in practical applications, in order to ensure implementation of the above steps, the above IP segment and network mapping table needs to be constructed before executing step 102.
In order to facilitate understanding, the embodiment provides a specific manner of constructing the mapping table of the IP segment and the network system, which is specifically as follows:
(1) And analyzing and processing the sample characteristic information in the sample characteristic set by using a preset network system determining model, and determining the network system corresponding to each sample characteristic information.
Specifically, the sample characteristic information is characteristic information of a TCP transport layer corresponding to a client request of different IPs in the same IP segment collected in advance from a server.
(2) And counting the number of the IP corresponding to the determined different network systems.
For ease of understanding, the following description of the IP segment and network mapping statistics is given in connection with table 1:
table 1IP segment and network system mapping statistics table
IP section IP number of MOBILE IP quantity of WIFI
IP section 1 83 2
IP section 2 101 7
IP section 3 91 6
IP section 4 2 151
IP section 5 1 169
IP section 6 1 157
As can be seen from the contents described in table 1, for the IP segment 1, 83 network systems corresponding to IP are MOBILE, and 2 network systems corresponding to IP are WIFI; for the IP section 2, 101 network systems corresponding to the IP are MOBILE, and 7 network systems corresponding to the IP are WIFI; for the IP section 3, 91 network systems corresponding to the IP are MOBILE, and 6 network systems corresponding to the IP are WIFI; for the IP section 4, 2 network systems corresponding to the IP are MOBILE, and 151 network systems corresponding to the IP are WIFI; for the IP section 5, 1 network system corresponding to the IP is MOBILE, and 169 network systems corresponding to the IP are WIFI; for the IP segment 6, 1 network system corresponding to IP is MOBILE, and 157 network systems corresponding to IP are WIFI.
It should be understood that the above examples are only examples listed for better understanding of the technical solution of the present embodiment, and are not the only limitation of the present embodiment.
(3) And selecting network modes with the number of the IPs meeting preset conditions as preset network modes corresponding to the IP sections.
Specifically, the above-mentioned condition meeting the preset condition can be classified into the following two cases in practical application:
case 1: the two network systems of MOBILE and WIFI both correspond to the number of IPs, and the meeting of the preset condition may be that the number of IPs is greater than a certain preset threshold, or the network system with the largest number of IPs is selected as the preset network system corresponding to the IP segment.
Case 2: only one of the two network systems, MOBILE and WIFI, corresponds to the number of IPs, and the meeting of the preset condition may be selecting the network system corresponding to the number of IPs as the preset network system corresponding to the IP segment.
(4) And establishing a corresponding relation between the IP section and the preset network system to obtain a mapping table of the IP section and the network system.
In order to facilitate understanding, in this embodiment, the network system satisfying the preset condition is set to select the network system with the largest number of IPs as the preset network system corresponding to the IP segment, and based on table 1, the mapping table of the finally obtained IP segment and network system is shown in table 2.
Table 2IP segment and network mapping table
IP section Presetting network system
IP section 1 MOBILE
IP section 2 MOBILE
IP section 3 MOBILE
IP section 4 WIFI
IP section 5 WIFI
IP section 6 WIFI
In addition, it should be noted that, in practical application, a manner of combining table 1 and table 2 into one table, such as the style shown in table 3, may be used in constructing the mapping table of the IP segment and the network system.
Table 3IP segment and network mapping table
IP section IP number of MOBILE IP quantity of WIFI Presetting network system
IP section 1 83 2 MOBILE
IP section 2 101 7 MOBILE
IP section 3 91 6 MOBILE
IP section 4 2 151 WIFI
IP section 5 1 169 WIFI
IP section 6 1 157 WIFI
It should be understood that the above examples are only examples listed for better understanding of the technical solution of the present embodiment, and are not the only limitation of the present embodiment.
And step 103, taking the searched preset network system as a target network system.
Step 104, selecting a transmission strategy from preset transmission strategies as a target transmission strategy according to the target network system, so as to execute a Transmission Control Protocol (TCP) transmission service based on the target transmission strategy.
It should be understood that, compared with the RTT of the network system of the MOBILE (in particular, the embodiment refers to 4G) type, the RTT of the network system of the WIFI type is stable, and the RTT value is usually smaller, and the transformation is not large. Therefore, aiming at the jamming rate index, when the target network system is WIFI, the selected target transmission strategy can be used for timely detecting retransmission when packet loss occurs, so that jamming is reduced; and for the MOBILE which is unstable in RTT and easy to deteriorate, the MOBILE is not detected and retransmitted in time and is easy to be blocked when the packet is lost, and the RTT deterioration needs to be controlled as much as possible on the selected target transmission strategy so as to reduce the influence on the transmission efficiency and further improve the transmission quality.
The above-mentioned target transmission policy adapted to different target network systems may be specifically preset by a technician according to actual situations, which is not limited in this embodiment.
According to the method for selecting the transmission strategy, which is provided by the embodiment, the IP section and the network system mapping table are constructed based on the principle that the IP section and the network system from the same base station are corresponding, before the transmission strategy is selected, the preset network system corresponding to the IP section information provided by the client is searched in the preset IP section and the network system mapping table, and then the searched network system is used as the target type of the network for TCP service transmission with the client for providing the IP section information, namely the target network system, the accuracy of the determined target network system is effectively ensured, and finally the adaptive target transmission strategy is selected in a targeted manner according to the actually determined target network system, so that the transmission strategy according to which the TCP transmission service is transmitted can consider the difference of different network systems, thereby avoiding the influence of different network systems on the transmission quality, and further effectively promoting the improvement of the overall transmission quality of the TCP transmission layer.
A second embodiment of the invention relates to a method of selecting a transmission strategy. The second embodiment is further improved based on the first embodiment, and the main improvements are that: and when the preset network system corresponding to the acquired IP section information is not found in the preset IP section and network system mapping table, analyzing and processing the acquired characteristic information of the TCP transmission layer by utilizing a preset network system determining model, so as to determine a target network system.
As shown in fig. 2, the method for selecting a transmission policy according to the second embodiment includes the following steps:
step 201, obtaining IP segment information of a client.
It is to be noted that step 201 in this embodiment is substantially the same as step 101 in the first embodiment, and will not be described here.
Step 202, judging whether a preset network system corresponding to the IP segment information is found in a preset mapping table of the IP segment and the network system.
Specifically, if a preset network system corresponding to the IP segment information is found in a preset IP segment and network system mapping table, step 204 is directly executed; otherwise, step 203 is performed.
Step 203, obtaining characteristic information of a TCP transmission layer, analyzing and processing the characteristic information by using a preset network system determining model, determining a network system corresponding to the characteristic information, and taking the determined network system group as the target network system.
Specifically, the feature information acquired in this embodiment may be from a TCP connection or a TCP request.
In addition, the characteristic information of the TCP layer may include information such as a quadruple, URL, server operator, maximum packet length (Maximum Segment Size, MSS), time period required for TCP to establish a connection (hereinafter referred to as "connection establishment Time period est"), time period sst from completion of establishing a connection to receipt of a secure socket protocol (Secure Sockets Layer, SSL) handshake packet, time period set from receipt of an SSL handshake packet to completion of SSL handshake, time period reqt from completion of establishment or completion of SSL handshake to receipt of a request, initial Round Trip Time (RTT), initial reception window of a client, etc.
When the network type determining model is obtained through training, the training test and comparison show that est, sst, set, reqt and initial RTT of different areas are related to area coverage, the prediction accuracy of the area can reach 95% by a single area and the model trained by the features, but the prediction accuracy is unstable when the model is applied to other areas. Therefore, considering generalization of the network format determination model, in this embodiment, the training feature value selects MSS and client initial receiving window sizes that are independent of regional coverage.
That is, in this embodiment, the obtained characteristic information mainly includes MSS and a client initial reception window size.
Furthermore, it is worth mentioning that, since in practical applications, TCP connections exist for both long and short connections. For the case of long connection, only the first TCP request will carry the above feature information, so in order to avoid the influence of repeated statistics caused by multiple requests of a single client IP, the obtained feature information is specifically the feature information in the initial stage of packet sending.
Further, it should be understood that, since the target network system is determined by the preset network system determination model based on the acquired feature information in this case, in order to ensure the accuracy of the determined target network system, the network system determination model described in the present embodiment is obtained based on training including the feature information of the same type.
In order to facilitate understanding of the calendar of the network type determination model, a specific training manner is provided in this embodiment, which is specifically as follows:
(1) And acquiring characteristic information of a TCP transmission layer corresponding to the known network system and a network system class mark of the known network system to obtain a training sample.
Specifically, the characteristic information of the TCP transport layer corresponding to the known network system acquired here also needs to include at least the maximum packet length and the initial receiving window size of the client.
In addition, the network type identifier is essentially identification information for identifying the type of the known network type. In this embodiment, WIFI is used to identify the wireless network type, and MOBILE is used to identify the MOBILE network type. That is, the network type is either WIFI or MOBILE.
It should be understood that the above examples are only examples listed for better understanding of the technical solution of the present embodiment, and are not the only limitation of the present embodiment.
The above-mentioned obtaining the characteristic information of the TCP transmission layer corresponding to the known network system specifically includes obtaining the maximum segment length and the initial receiving window size of the client received by the TCP transmission layer during the period from the start of establishing the connection to the start of sending the packet (i.e., the initial stage of sending the packet), and then using the received maximum segment length and the initial receiving window size of the client as the characteristic information of the TCP transmission layer corresponding to the known network system.
Further, since in practical application, long connection in TCP connection only carries the above characteristic information when first requested by TCP, all subsequent requests output "-". Therefore, in order to avoid being affected by the IP of the single client, the obtained characteristic information is specifically the maximum segment length carried in the first TCP request received by the TCP transmission layer and the initial receiving window size of the client during the period from the start of connection establishment to the start of packet sending of the obtained TCP.
Furthermore, it should be noted that, since in practical applications, the characteristic information of the TCP transport layer may be refined to various granularities (dimensions of characteristic acquisition), such as the request and connection described above, in addition to being processed to granularity of the machine. However, in general, the network system of the same connection is fixed, so in this embodiment, in order to ensure that the acquired feature information is a request or a connection, the feature information of the TCP transport layer is acquired at the granularity of the request or the connection.
In addition, regarding the above-mentioned network type class mark for acquiring the known network type, in this embodiment, the log or URL reported by the client is specifically acquired, and then acquired from the log or URL.
Further, the operation of acquiring the network type class mark from the log or the URL is specifically:
firstly, analyzing the log or the URL to obtain an analysis result; and then judging whether the analysis result comprises network system information.
Correspondingly, if the network type information is included, acquiring the network type class mark of the known network type from the network type information; otherwise, a test environment is built, packet capturing identification is carried out based on the built test environment, and then the known network system is marked manually according to the information of the packet capturing identification, namely the network system is divided into WIFI class or MOBILE class through judgment of technicians.
It should be noted that, in this embodiment, whether the network type class mark can be obtained is determined by judging whether the analysis result includes the network type information, because the network type information generally includes at least identification information, such as WIFI or MOBILE, for identifying the network to which the network type belongs.
Furthermore, it should be understood that in practical applications, in order to ensure accuracy of the network type determination model obtained by training, the training samples required for training need to be sufficient. Therefore, when the number of the obtained feature information and the network type class labels is large, in order to ensure the usability of the training samples, the feature information and the network type class labels corresponding to each other need to be used as one training sample, i.e. each training sample consists of the feature information and the network type class labels corresponding to each other.
(2) And constructing a network training model according to a preset machine learning algorithm.
Specifically, when the number of features in the obtained feature information is relatively small, a simple discriminant algorithm may be used to construct a network training model, such as decision tree, logistic regression, naive bayes, support vector machine SVM, and the like, which are not listed here.
(3) And carrying out iterative training on the network type training model by using the training sample until a preset iteration termination condition is met, so as to obtain the network type determining model.
It should be understood that, since the feature information in the training samples corresponds to the network type class label, that is, the network type class label in each training sample is used to identify the feature information in the training sample, and the feature information and the network type class label are both from the known network type. Therefore, after the training samples are sequentially input into the network system training model, the network system is obtained as an output result after analysis processing of the network system training model, and the network system determination model can be obtained after continuous iterative training until the preset iteration termination condition is met.
It should be understood that, in practical application, the iterative training of the model may not necessarily ensure that each training sample of the training model of the network system is input, and the network system output after the analysis and the processing of the training model of the network system is the same as the corresponding known network system. Moreover, if the network system obtained by all training samples is the same as the known network system, the model overfitting can be caused. Therefore, in order to avoid the above-mentioned problem, in this embodiment, iteration termination conditions are preset specifically, that is, when the preset iteration termination conditions are satisfied, the iteration training is stopped, and then the network system training model of the card is used as the network system determining model that is finally required.
In practical applications, the above-mentioned iteration termination condition may be set by those skilled in the art by selecting different algorithms according to needs, for example, when the machine algorithm used to train the network system determination model is a decision tree algorithm, the preset iteration termination condition may be set according to the purity of the leaf nodes.
In addition, it should be noted that, in practical application, in order to ensure accuracy of the network type determination model obtained by training, before the training sample is used to perform iterative training on the network type training model, the training sample may be divided into a training set and a testing set at random, that is, a part of data in the training sample is used as training data, and another part is used as testing data.
Accordingly, the training process essentially comprises the steps of performing iterative training on the network system training model by using training data, testing the current network system training model based on the divided test data before the current network system training model is used as a network system determining model after the training is finished, and considering that the training of the current network system training model is finished and the current network system training model can be used as the network system determining model when any piece of test data is input and the output result is the network system corresponding to the input test data.
It should be understood that the above examples are only examples listed for better understanding of the technical solution of the present embodiment, and are not the only limitation of the present embodiment. In practical application, a person skilled in the art can also adopt a ten-fold cross-validation method to validate whether the network type training model trained by the training sample can be used as the network type determining model.
The network type determining model obtained through training in the mode can achieve more than 80% of accuracy and recall rate under the condition of considering model generalization (only adopting MSS and initial receiving window size of a client as characteristic information). If the number of the models or the less regions are not considered in the practical application, the characteristic information such as est, sst, set, reqt and initial RTT is introduced when the network system determination model is trained, and the accuracy and recall rate of the network system determination model for different regions can be improved to 95%.
In addition, it should be noted that, in practical application, in order to ensure that after the subsequent IP segment information of the client is received, a corresponding preset network system can be found in the IP segment and network system mapping table, after the target network system is determined by using the preset network system determining model, a corresponding relationship between the IP segment information and the network system determined by using the network system determining model can be established, and the established corresponding relationship is added into the IP segment and network system mapping table, so that the information recorded in the IP segment and network system mapping table can be richer, and more network systems suitable for different clients are covered.
And 204, taking the searched preset network system as a target network system.
Step 205, selecting a transmission strategy from preset transmission strategies as a target transmission strategy according to the target network system, so as to execute a Transmission Control Protocol (TCP) transmission service based on the target transmission strategy.
It is to be noted that, in this embodiment, step 204 and step 205 are substantially the same as step 103 and step 104 in the first embodiment, and will not be described here.
Therefore, in the transmission policy selection method provided in this embodiment, when the preset network system corresponding to the IP segment information provided by the client is not found in the preset IP segment and network system mapping table, the characteristic information of the TCP transmission layer is analyzed and processed by the network system determination model obtained based on the pre-training, so as to determine the network system, thereby making up the deficiency of the IP segment and the network system mapping table.
It should be understood that the above steps of the methods are divided, for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they include the same logic relationship, which is within the protection scope of the present patent; it is within the scope of this patent to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.
A third embodiment of the present invention relates to a transmission policy selection device, as shown in fig. 3, including: an acquisition module 301, a search module 302 and a selection module 303.
The acquiring module 301 is configured to acquire IP segment information of a client; a determining module 302, configured to search a preset network system corresponding to the IP segment information in a preset IP segment and network system mapping table, and take the searched preset network system as a target network system; and a selecting module 303, configured to select, according to the target network format, a transmission policy from preset transmission policies as a target transmission policy, so as to execute a transmission control protocol TCP transmission service based on the target transmission policy.
In addition, in another example, the searching module 302 is specifically configured to, when searching a preset network system corresponding to the IP segment information in the preset IP segment and network system mapping table, use the searched preset network system as a target network system;
in addition, in another example, the selecting device of the transmission policy further includes a network system determining module.
Specifically, the searching module 302 is specifically configured to, when searching a preset network system corresponding to the IP segment information in a preset IP segment and network system mapping table, use the searched preset network system as a target network system; when the preset network system corresponding to the IP segment information is not found, notifying an acquisition module 301 to acquire the characteristic information of the TCP transmission layer, notifying a network system determination module to analyze and process the characteristic information by utilizing a preset network system determination model, determining the network system corresponding to the characteristic information, and taking the determined network system group as the target network system.
In addition, in another example, the network system determining module is further configured to establish a correspondence between the IP segment information and the network system, and add the correspondence to the IP segment and network system mapping table.
In addition, in another example, the selecting device of the transmission policy further includes a mapping table construction module.
Specifically, the mapping table construction module is used for analyzing and processing sample characteristic information in a sample characteristic set by using the network type determining model, and determining a network type corresponding to each sample characteristic information, wherein the sample characteristic information is characteristic information of a TCP transmission layer provided by clients of different IPs in the same IP section collected in advance; counting the number of the IP corresponding to the determined different network systems; selecting network systems with the number of the IPs meeting preset conditions as preset network systems corresponding to the IP sections; and establishing a corresponding relation between the IP section and the preset network system to obtain a mapping table of the IP section and the network system.
In addition, in another example, the selection device of the transmission strategy further includes a network system determination model training module.
Specifically, a network system determination model training module is used for acquiring characteristic information of a TCP transmission layer corresponding to a known network system and a network system class mark of the known network system to obtain a training sample; constructing a network training model according to a preset machine learning algorithm; and carrying out iterative training on the network type training model by using the training sample until a preset iteration termination condition is met, so as to obtain the network type determining model.
In addition, in another example, the network system determining model training module is further configured to obtain a maximum packet length received by the TCP transport layer and an initial receiving window size of the client during a period from when the TCP establishes a connection to when the TCP starts to send a packet, so as to obtain feature information of the TCP transport layer corresponding to the known network system.
In addition, in another example, the network system determining model training module is further configured to obtain a maximum packet length carried in a first TCP request received by the TCP transport layer and an initial receiving window size of the client during a period from when the TCP establishes a connection to when the TCP starts to send a packet, so as to obtain feature information of the TCP transport layer corresponding to the known network system.
In addition, in another example, the network system determination model training module is further configured to obtain a log or URL reported by the client; and obtaining the network type class mark of the known network type from the log or the URL.
In addition, in another example, the network system determination model training module is further configured to parse the log or the URL to obtain a parsing result; and judging whether the analysis result comprises network system information.
Correspondingly, if the network type information is included, acquiring the network type class mark of the known network type from the network type information; otherwise, setting up a test environment, and manually marking the known network system based on the packet capturing identification of the test environment to obtain a network system class mark of the known network system.
It is to be noted that this embodiment is an embodiment of the apparatus corresponding to the first or second embodiment, and this embodiment can be implemented in cooperation with the first or second embodiment. The related technical details mentioned in the first or second embodiment are still valid in this embodiment, and in order to reduce repetition, a detailed description is omitted here. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first or second embodiment.
It should be noted that, each module involved in this embodiment is a logic module, and in practical application, one logic unit may be one physical unit, or may be a part of one physical unit, or may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, units less closely related to solving the technical problem presented by the present invention are not introduced in the present embodiment, but it does not indicate that other units are not present in the present embodiment.
A fourth embodiment of the invention relates to a transmission policy selection device, as shown in fig. 4, comprising at least one processor 401; and a memory 402 communicatively coupled to the at least one processor 401; wherein the memory 402 stores instructions executable by the at least one processor 401, the instructions being executable by the at least one processor 401 to enable the at least one processor 401 to perform the method of selecting a transmission policy as described in the first or second embodiment.
Where the memory 402 and the processor 401 are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting the various circuits of the one or more processors 401 and the memory 402 together. The bus may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or may be a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 401 is transmitted over a wireless medium via an antenna, which further receives and transmits the data to the processor 401.
The processor 401 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 402 may be used to store data used by processor 401 in performing operations.
A fifth embodiment of the present application relates to a computer-readable storage medium storing a computer program. The selection method embodiment of the above-mentioned transmission strategy is implemented when the computer program is executed by the processor.
That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the application and that various changes in form and details may be made therein without departing from the spirit and scope of the application.

Claims (11)

1. A method for selecting a transmission strategy, comprising:
Acquiring IP section information of a client, wherein the IP section information is at least used for representing the size of a network scale;
searching a preset network system corresponding to the IP section information in a preset IP section and network system mapping table;
taking the searched preset network system as a target network system;
according to the target network system, selecting a transmission strategy from preset transmission strategies as a target transmission strategy, and executing Transmission Control Protocol (TCP) transmission service based on the target transmission strategy;
the construction of the IP section and the network mapping table comprises the following steps:
analyzing and processing sample characteristic information in a sample characteristic set by using a preset network system determining model, and determining a network system corresponding to each sample characteristic information, wherein the sample characteristic information is characteristic information of a TCP transmission layer provided by clients of different IPs in the same IP section collected in advance, and the network systems comprise a MOBILE network system and a WIFI network system;
counting the number of the IP corresponding to the determined different network systems;
if the MOBILE network system and the WIFI network system both correspond to the IP number, selecting the network system with the largest IP number as the preset network system corresponding to the IP section;
If one of the MOBILE network system and the WIFI network system corresponds to the IP number, selecting the network system corresponding to the IP number as a preset network system corresponding to the IP section;
and establishing a corresponding relation between the IP section and the preset network system to obtain a mapping table of the IP section and the network system.
2. The method for selecting a transmission policy according to claim 1, wherein after searching a preset network system corresponding to the IP segment information in the preset IP segment and network system mapping table, the method further comprises:
if a preset network system corresponding to the IP section information is found in a preset IP section and network system mapping table, executing the step of taking the found preset network system as a target network system;
otherwise, acquiring the characteristic information of the TCP transmission layer, analyzing and processing the characteristic information by using a preset network system determining model, determining a network system corresponding to the characteristic information, taking the determined network system as the target network system, and executing the step of selecting one transmission strategy from preset transmission strategies as a target transmission strategy according to the target network system.
3. The transmission policy selection method according to claim 2, wherein after the characteristic information is analyzed by using a preset network system determination model and the network system corresponding to the characteristic information is determined, the method further comprises:
and establishing a corresponding relation between the IP section information and the network system, and adding the corresponding relation into the mapping table of the IP section and the network system.
4. The method for selecting a transmission policy according to claim 2, wherein the training of the network type determination model includes:
acquiring characteristic information of a TCP transmission layer corresponding to a known network system and a network system class mark of the known network system to obtain a training sample;
constructing a network training model according to a preset machine learning algorithm;
and carrying out iterative training on the network type training model by using the training sample until a preset iteration termination condition is met, so as to obtain the network type determining model.
5. The method for selecting a transmission policy according to claim 4, wherein the obtaining the characteristic information of the TCP transport layer corresponding to the known network system includes:
And acquiring the maximum message segment length received by the TCP transmission layer and the initial receiving window size of the client during the period from the start of establishing the connection to the start of sending the packet, and obtaining the characteristic information of the TCP transmission layer corresponding to the known network system.
6. The method for selecting a transmission policy according to claim 5, wherein obtaining the maximum segment length received by the TCP transport layer and the initial receiving window size of the client during the period from the start of establishing the TCP connection to the start of sending the packet, obtaining the characteristic information of the TCP transport layer corresponding to the known network system, includes:
and acquiring the maximum message segment length carried in the first TCP request received by the TCP transmission layer and the initial receiving window size of the client during the period from the start of the connection establishment to the start of the packet sending, and obtaining the characteristic information of the TCP transmission layer corresponding to the known network system.
7. The method for selecting a transmission policy according to claim 4, wherein the obtaining the network type class label of the known network type includes:
acquiring a log or a URL reported by a client;
and obtaining the network type class mark of the known network type from the log or the URL.
8. The method for selecting a transmission policy according to claim 7, wherein said obtaining a network type class of the known network type from the log or the URL includes:
Analyzing the log or the URL to obtain an analysis result;
judging whether the analysis result comprises network system information or not;
and if the network type information is included, acquiring the network type class mark of the known network type from the network type information.
9. The transmission policy selection method according to claim 8, wherein after said determining whether the parsing result includes network system information, the method further comprises:
if the analysis result does not include the network system information, a testing environment is built, the known network system is marked manually based on the packet capturing identification of the testing environment, and the network system class mark of the known network system is obtained.
10. A transmission policy selection device, comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the transmission policy selection method of any one of claims 1 to 9.
11. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the transmission policy selection method according to any one of claims 1 to 9.
CN202010928114.8A 2020-09-07 2020-09-07 Transmission policy selection method, device and storage medium Active CN112217605B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010928114.8A CN112217605B (en) 2020-09-07 2020-09-07 Transmission policy selection method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010928114.8A CN112217605B (en) 2020-09-07 2020-09-07 Transmission policy selection method, device and storage medium

Publications (2)

Publication Number Publication Date
CN112217605A CN112217605A (en) 2021-01-12
CN112217605B true CN112217605B (en) 2023-10-20

Family

ID=74049090

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010928114.8A Active CN112217605B (en) 2020-09-07 2020-09-07 Transmission policy selection method, device and storage medium

Country Status (1)

Country Link
CN (1) CN112217605B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101399774A (en) * 2008-10-24 2009-04-01 华为技术有限公司 Processing method and system for packet data
CN102238204A (en) * 2010-04-23 2011-11-09 腾讯科技（深圳）有限公司 Network data acquisition method and system
CN103200622A (en) * 2012-01-09 2013-07-10 株式会社Ntt都科摩 Communication handling method, device and gateway equipment
CN104144462A (en) * 2013-05-06 2014-11-12 腾讯科技（深圳）有限公司 Mobile terminal network access way obtaining method and device and mobile terminal
CN104170353A (en) * 2013-12-27 2014-11-26 华为技术有限公司 TCP link configuring method, device and equipment
CN104303471A (en) * 2012-11-15 2015-01-21 僖迪网络科技株式会社 Method and apparatus for providing content by selecting data acceleration algorithm
CN105207949A (en) * 2014-06-12 2015-12-30 中国移动通信集团内蒙古有限公司 TCP optimization method and system, and SP server
WO2018076580A1 (en) * 2016-10-25 2018-05-03 网宿科技股份有限公司 Two-sided acceleration transmission method and system for wireless network
CN108040352A (en) * 2015-11-28 2018-05-15 广东欧珀移动通信有限公司 Method for processing business, device and mobile terminal under a kind of hybrid network standard
CN110138608A (en) * 2019-05-09 2019-08-16 网宿科技股份有限公司 The method and server of network service Service Quality Management
CN110831039A (en) * 2019-11-20 2020-02-21 北京连山科技股份有限公司 Data transmission method and transmission server in multi-path concurrent system
CN111314489A (en) * 2020-03-19 2020-06-19 腾讯科技（深圳）有限公司 Method, server and device for identifying type of access network
CN111416794A (en) * 2019-01-08 2020-07-14 华为技术有限公司 Data transmission method and electronic equipment

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101399774A (en) * 2008-10-24 2009-04-01 华为技术有限公司 Processing method and system for packet data
CN102238204A (en) * 2010-04-23 2011-11-09 腾讯科技（深圳）有限公司 Network data acquisition method and system
CN103200622A (en) * 2012-01-09 2013-07-10 株式会社Ntt都科摩 Communication handling method, device and gateway equipment
CN104303471A (en) * 2012-11-15 2015-01-21 僖迪网络科技株式会社 Method and apparatus for providing content by selecting data acceleration algorithm
CN104144462A (en) * 2013-05-06 2014-11-12 腾讯科技（深圳）有限公司 Mobile terminal network access way obtaining method and device and mobile terminal
CN104170353A (en) * 2013-12-27 2014-11-26 华为技术有限公司 TCP link configuring method, device and equipment
CN105207949A (en) * 2014-06-12 2015-12-30 中国移动通信集团内蒙古有限公司 TCP optimization method and system, and SP server
CN108040352A (en) * 2015-11-28 2018-05-15 广东欧珀移动通信有限公司 Method for processing business, device and mobile terminal under a kind of hybrid network standard
WO2018076580A1 (en) * 2016-10-25 2018-05-03 网宿科技股份有限公司 Two-sided acceleration transmission method and system for wireless network
CN111416794A (en) * 2019-01-08 2020-07-14 华为技术有限公司 Data transmission method and electronic equipment
CN110138608A (en) * 2019-05-09 2019-08-16 网宿科技股份有限公司 The method and server of network service Service Quality Management
CN110831039A (en) * 2019-11-20 2020-02-21 北京连山科技股份有限公司 Data transmission method and transmission server in multi-path concurrent system
CN111314489A (en) * 2020-03-19 2020-06-19 腾讯科技（深圳）有限公司 Method, server and device for identifying type of access network

Also Published As

Publication number Publication date
CN112217605A (en) 2021-01-12

Similar Documents

Publication Publication Date Title
US10812358B2 (en) Performance-based content delivery
US11523288B2 (en) Data analysis apparatus, system, and method
US10027739B1 (en) Performance-based content delivery
CN101147380B (en) Method and apparatus for efficiently expanding a P2P network
CN106793007B (en) Interactive communication method and system of cloud and Bluetooth device and wireless router
CN104702592B (en) Stream media downloading method and device
CN113489619B (en) Network topology inference method and device based on time series analysis
US20230042747A1 (en) Message Processing Method and Device, Storage Medium, and Electronic Device
CN109819498A (en) A kind of smart machine, the automatic distribution method and system of smart machine
CN113965474A (en) Network quality evaluation method, electronic device and storage medium
WO2019224727A2 (en) Systems and methods for determining characteristics of devices on a network
CN110177384A (en) Cut-in method, device, wireless access point and readable storage medium storing program for executing
CN106900174A (en) The data transmission method of WLAN mesh network, apparatus and system
CN112491719A (en) Network node selection method, equipment and storage medium
KR100661006B1 (en) Home network device management system and method thereof
CN107809346A (en) The mark of route tracking node and associated equipment
CN108347360B (en) Network test data acquisition method and network server
CN112217605B (en) Transmission policy selection method, device and storage medium
CN115996203B (en) Network traffic domain division method, device, equipment and storage medium
CN109788075B (en) Private network system, data acquisition method and edge server
CN113783744A (en) Time delay measuring method and device, computer equipment and storage medium
CN113098787A (en) Flow processing method and equipment
JP2003037649A (en) Method for estimating contents distribution end time, recording medium and program
CN105052207B (en) Information query method, equipment and system
CN112637055B (en) Multi-link aggregation method, system and storage medium based on VPN tunnel

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant