Data security transmission method and system based on computer network

Abstract

The present invention relates to the field of digital information transmission technology, and in particular to a data security transmission method and system based on a computer network, the method comprising: obtaining network data of network nodes at different times in a target network; calculating the congestion degree of each network node at different times according to the network indicators of each network node; determining the predicted congestion degree of the current network node at a future time according to the congestion degree of the current network node at different times, a first network congestion degree change curve, and a second network congestion degree change curve of other network nodes at different historical times; determining the importance of the current network node according to the flow data of the current network node at the current time; determining the target compression method of the data to be transmitted of the current network node according to the predicted congestion degree and importance; and compressing the data to be transmitted and transmitting it using the target compression method. In this way, the present invention improves the security and reliability of data transmission.

Description

Technical Field

[0001] The present invention relates to the technical field of digital information transmission, and in particular to a computer network-based data security transmission method and system. Background Art

[0002] With the continuous development of computer networks, data transmission has higher and higher requirements for speed and reliability. At present, the industry often adopts efficient transmission protocols to optimize data transmission speed and reliability. As users pay more and more attention to data transmission security, encryption technology and security protocols are used to protect the confidentiality and integrity of data transmission.

[0003] In the scenario of campus network, the campus network generally limits the bandwidth resources during the use of the network, the network equipment performance of the campus network is poor, and the number of users of the campus network is large. When the network is in peak use, a large number of users transmit and access data at the same time, resulting in tight bandwidth resources of the network, causing network congestion, high packet loss rate, and low security and reliability of data transmission. Summary of the invention

[0004] In order to solve the technical problem of low security and reliability of data transmission, the purpose of the present invention is to provide a data security transmission method and system based on a computer network. The technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a computer network-based data security transmission method, comprising: obtaining network data of network nodes in a target network at different times, the network data including network indicators and traffic data; calculating the congestion degree of each network node at different times according to the network indicators of each network node; determining the predicted congestion degree of the current network node at a future time according to the congestion degree of the current network node at different times, a first network congestion degree change curve of the current network node at different historical times, and a second network congestion degree change curve of other network nodes at different historical times; determining the importance of the current network node according to the traffic data of the current network node at the current time; determining a target compression method for data to be transmitted of the current network node according to the predicted congestion degree and importance; and compressing the data to be transmitted using the target compression method and then transmitting it.

[0006] Optionally, obtain network data of network nodes in the target network at different times, the network data including network indicators and traffic data; calculate the congestion level of each network node at different times according to the network indicators of each network node; determine the predicted congestion level of the current network node at a future time according to the congestion level of the current network node at different times, a first network congestion level change curve of the current network node at different historical times, and a second network congestion level change curve of other network nodes at different historical times; determine the importance of the current network node according to the traffic data of the current network node at the current time; determine the target compression method of the data to be transmitted of the current network node according to the predicted congestion level and importance; and compress the data to be transmitted using the target compression method before transmitting it.

[0007] Optionally, determining the predicted congestion level of the current network node at a future moment according to the congestion level of the current network node at different moments, a first network congestion level change curve of the current network node at different historical moments, and a second network congestion level change curve of other network nodes at different historical moments includes: determining a growth trend of the congestion level of the network node at the current moment by using the congestion level at each moment; obtaining a first network congestion level change curve of the current network node at different historical moments and a second network congestion level change curve of other network nodes at different historical moments; determining a correlation between the current network node and the other network nodes according to a distance between the current network node and the other network nodes and a similarity between the first network congestion level change curve and the second network congestion level change curve; and determining a correlation between the first network congestion level change curve and the second network congestion level change curve. The method comprises the following steps: intercepting a curve of a first network congestion change curve to obtain a plurality of first curve segments; intercepting a curve of a second network congestion change curve to obtain a plurality of second curve segments; determining a sample distance between the first curve segment and the second curve segment based on the correlation between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion degree of the current network node at the current moment, and the growth trend of the congestion degree of other network nodes at the current moment; clustering the first curve segments and the second curve segments based on the sample distance to obtain a plurality of cluster centers; determining a predicted congestion degree of the current network node at a future moment according to the congestion degree of the current network node at different moments, the sample distance between each first curve segment and each cluster center, and the maximum congestion degree in the curve segment corresponding to each cluster center.

[0008] Optionally, using the congestion levels at each moment to determine the growth trend of the congestion level of the network node at the current moment includes: performing standardized weight conversion on the moment to obtain a conversion value; determining the rate of change of the congestion level at the current moment based on the congestion level at the current moment and the congestion levels at adjacent moments adjacent to the current moment; determining the growth trend of the congestion level of the network node at the current moment based on the conversion value and the rate of change of the congestion level at the current moment.

[0009] Optionally, determining the correlation between the current network node and the other network nodes based on the distance between the current network node and the other network nodes and the similarity between the first network congestion level change curve and the second network congestion level change curve includes: translating the second network congestion level change curve by multiple units in sequence to obtain a third network congestion level change curve; determining the maximum value among the similarities between the first network congestion level change curve and each third network congestion level change curve; and determining the product of the maximum value and the distance as the correlation between the current network node and the other network nodes.

[0010] Optionally, intercepting the first network congestion level change curve to obtain multiple first curve segments includes: determining a first target time point at which the congestion level is greater than a preset threshold from the first network congestion level change curve; intercepting a curve segment with a length of a preset length before the first target time point from the first network congestion level change curve as a first curve segment; intercepting the second network congestion level change curve to obtain multiple second curve segments includes: determining a second target time point at which the congestion level is greater than a preset threshold from the second network congestion level change curve; intercepting a curve segment with a length of a preset length before the second target time point from the second network congestion level change curve as a second curve segment.

[0011] Optionally, in order to determine the sample distance between the first curve segment and the second curve segment based on the correlation between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion level of the current network node at the current moment, and the growth trend of the congestion level of other network nodes at the current moment, the sample distance between the first curve segment and the second curve segment includes: calculating the absolute value of the first difference between the growth trend of the congestion level of the current network node at the current moment and the growth trend of the congestion level of other network nodes at the current moment; calculating the second product between the inverse of the correlation, the DTW distance and the absolute value of the first difference; and normalizing the second product to obtain the sample distance between the first curve segment and the second curve segment.

[0012] Optionally, determining the predicted congestion level of the current network node at a future moment based on the congestion level of the current network node at different moments, the sample distances between each first curve segment and each cluster center, and the maximum congestion level in the curve segment corresponding to each cluster center includes: determining the congestion level of the current network node at the current moment; calculating the first ratios between each maximum congestion level and each sample distance, and averaging the first ratios to obtain an average ratio; normalizing the average ratio to obtain a normalized ratio; and determining that the third product of the congestion level of the current network node at the current moment, the predetermined value, and the normalized ratio is the predicted congestion level of the current network node at the future moment.

[0013] Optionally, determining the importance of the current network node based on the traffic data of the current network node at the current moment includes: determining the number of types of traffic information in the traffic data, the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment, and the importance of each type of traffic information; calculating the fourth product between the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment and the importance of each type of traffic information; and averaging each fourth product to obtain the importance of the current network node.

[0014] In a second aspect, an embodiment of the present invention provides a computer network-based data security transmission system, comprising: a processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; and the processor is used to execute the program stored in the memory to implement the steps of the computer network-based data security transmission method mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: firstly, network data of network nodes in a target network at different times are obtained, the network data including network indicators and flow data; then, the congestion degree of each network node at different times is calculated according to the network indicators of each network node; secondly, the predicted congestion degree of the current network node at a future time is determined according to the congestion degree of the current network node at different times, the first network congestion degree change curve of the current network node at different historical times and the second network congestion degree change curve of other network nodes at different historical times; then, the importance of the current network node is determined according to the flow data of the current network node at the current time; and the target compression method of the data to be transmitted of the current network node is determined according to the predicted congestion degree and the importance; finally, the data to be transmitted is compressed and transmitted according to the target compression method.

[0016] In this way, the embodiment of the present invention can predict the congestion degree of the network node at a future time according to the network data of the network node at different times in the target network, and determine the target compression mode of the data to be transmitted of the current network node according to the predicted congestion degree at a future time and the importance of the network node of the current network, and compress the data to be transmitted according to the target compression mode before transmission. In this way, congestion in the target network is avoided, the data packet loss rate is reduced, and the security and reliability of data transmission are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a computer network-based data security transmission method provided by one embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the module composition of a computer network-based data security transmission system provided by one embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the structure of a computer network-based data security transmission system provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a data security transmission method and system based on a computer network proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0022] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0023] The following is a detailed description of a computer network-based data security transmission method and system provided by the present invention in conjunction with the accompanying drawings.

[0024] Embodiment 1:

[0025] See also Figure 1 , which shows a flow chart of a data security transmission method based on a computer network provided by an embodiment of the present invention, including:

[0026] S101, obtaining network data of network nodes in a target network at different times.

[0027] Among them, network data includes network indicators and traffic data.

[0028] Specifically, the target network may be a campus network, etc. Traffic data includes, but is not limited to, the type of traffic, the mode of traffic, and the magnitude of traffic. The type of traffic includes, but is not limited to, text, image, video, and audio, etc. The mode of traffic includes, but is not limited to, real-time traffic mode and batch data transmission mode, etc. The magnitude of traffic includes, but is not limited to, the amount of evaluation data and the rate of change of data, etc. Network indicators include, but are not limited to, the bandwidth utilization of network nodes, the packet loss rate of network nodes, the average delay of the target network where the network nodes are located, and the queue length of network nodes, etc.

[0029] Furthermore, when monitoring network data of network nodes in the target network, Wireshark may be selected as a network monitoring tool.

[0030] S102, calculating the congestion degree of each network node at different times according to the network index of each network node.

[0031] Specifically, for the network indicators of each network node, bandwidth utilization can be used as a key indicator to measure the network performance of the target network. By monitoring bandwidth utilization, it is possible to find out whether there are excess or insufficient resources. Secondly, for a single network node, an increase in the packet loss rate of the network node may mean that there is a bottleneck or configuration problem in the network part to which the network node is connected, or it may be that the network node itself has insufficient processing capacity. Therefore, the packet loss rate can be used to indirectly reflect the congestion of the current network node. When the network is congested, the data packets may need to queue on the network device for processing, which will increase the queuing delay and thus increase the overall network delay. Therefore, the congestion of the nodes in the current network can be reflected by the delay of the target network. When calculating the delay of the network node, the delay of a single data packet can be calculated first, and then the average delay of the target network where the current network node is located can be expressed based on the average delay time of the data packets in the previous three minutes. Finally, the queue length of the network node can also be used as a network indicator of the target network. The longer the queue length of the network node, the higher the congestion length of the current network node.

[0032] Furthermore, when calculating the congestion degree of each network node at different times based on the network indicators of the above-mentioned network nodes, as an optional embodiment of the present invention, the bandwidth utilization, packet loss rate, average delay and queue length of the current network node are first determined from the network data of the network node; then the first product between the bandwidth utilization, packet loss rate, average delay and queue length is calculated; finally, the first product is normalized to obtain the congestion degree of the network node at different times.

[0033] Specifically, the following formula can be used to calculate the congestion level of network nodes at different times:

[0034]

[0035] In the above formula, Indicates The congestion level of a network node at a certain moment. Indicates The bandwidth utilization of a network node at a certain moment. Indicates The packet loss rate of each network node. Indicates The average latency of the network where the network nodes are located. Indicates The queue length of a network node at a certain moment. Represents the normalization function, which is used to Perform normalization.

[0036] Furthermore, according to the method described in the above embodiment of the present invention, the congestion degree of the network node is calculated once every 10 seconds as a time point, and the congestion degree is reflected in the coordinate system and connected with a smooth curve to obtain a network congestion degree change curve.

[0037] S103, determining the predicted congestion level of the current network node at a future time according to the congestion level of the current network node at different times, the first network congestion level change curve of the current network node at different historical times, and the second network congestion level change curves of other network nodes at different historical times.

[0038] Specifically, in an embodiment of the present invention, the congestion level of an unknown network node is predicted according to the known congestion level of the network node. When predicting the predicted congestion level of a network node at a certain moment in the future, as an optional embodiment of the present invention, firstly, the congestion level at each moment is used to determine the growth trend of the congestion level of the network node at the current moment; obtain the first network congestion level change curve of the current network node at different historical moments and the second network congestion level change curve of other network nodes at different historical moments; determine the correlation between the current network node and the other network nodes based on the distance between the current network node and the other network nodes and the similarity between the first network congestion level change curve and the second network congestion level change curve; perform curve interception on the first network congestion level change curve to obtain multiple first curve segments; and perform curve segmentation on the second network congestion level change curve. The change curve is intercepted to obtain multiple second curve segments; the sample distance between the first curve segment and the second curve segment is determined based on the correlation between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion level of the current network node at the current moment, and the growth trend of the congestion level of other network nodes at the current moment; the first curve segments and the second curve segments are clustered based on the sample distance to obtain multiple cluster centers; according to the congestion level of the current network node at different moments, the sample distance between each first curve segment and each cluster center, and the maximum congestion level in the curve segment corresponding to each cluster center, the predicted congestion level of the current network node at a future moment is determined.

[0039] Among them, when determining the growth trend of the congestion level of the network node at the current moment in an embodiment of the present invention, as an optional embodiment of the present invention, the moment is subjected to a standardized weight transformation to obtain a transformation value; based on the congestion level at the current moment and the congestion level at adjacent moments adjacent to the current moment, the congestion level change rate at the current moment is determined; based on the transformation value and the congestion level change rate at the current moment, the growth trend of the congestion level of the network node at the current moment is determined.

[0040] Specifically, the embodiment of the present invention may use the following formula to calculate the growth trend of the congestion degree of the network node at the current moment:

[0041]

[0042] In the above formula, Indicates The growth trend of the congestion level of each network node at the current moment. Indicates that the a-th time point The converted value after the standardized weight transformation. Indicates The congestion level change rate at a point in time. In the above formula, the farther a network node is from the current time, the smaller the contribution of the tangent slope of the network node to the growth trend of the congestion level of the network node.

[0043] Furthermore, the occurrence of network congestion may be associated with fixed activities, such as the school's regular course selection schedule leading to network congestion, or the cafeteria having too many people during the students' get out of class break, which leads to heavy traffic on some network nodes. It is necessary to compare the previous congestion change curve with the currently known congestion change curve. When there are similar changes in network congestion levels, it can be inferred that the current congestion change in the future is similar to the historical data, thereby determining the correlation between network nodes and further accurately judging the change trend of the network congestion level at the current moment. Considering that the impact between different network nodes may be lagging, it is necessary to translate one of the network congestion change curves and calculate its similarity. For example, when students attend an event at a venue, they enter in order of their seats. On the side where the existing students enter, the traffic of the network nodes in the campus network may increase first. After the students on the other side enter, the traffic of the network nodes on the other side of the campus network increases in a similar pattern. However, there is a certain time delay between the changes of the two. Directly comparing the similarity between the two may not produce ideal data. However, the changes of the two in practice are highly correlated. Therefore, it is necessary to shift the network congestion change curve left and right and find the most appropriate time point to compare the similarity of the network congestion change curve.

[0044] Furthermore, when determining the correlation between the current network node and other network nodes, as an optional embodiment of the present invention, the second network congestion level change curve is first translated by multiple units in sequence to obtain a third network congestion level change curve; then the maximum value of the similarities between the first network congestion level change curve and each third network congestion level change curve is determined; finally, the product of the maximum value and the distance is determined as the correlation between the current network node and other network nodes.

[0045] Specifically, when calculating the correlation between network nodes, when the congestion levels of two network nodes change more similarly and the distance between them in the campus network is closer, it is considered that the correlation between the two network nodes is higher. Taking the target network as a campus network as an example, the following formula is used to calculate the correlation in the embodiment of the present invention:

[0046]

[0047] In the above formula, Indicates the campus network The network node and The relationship between network nodes. Indicates the campus network The network congestion degree change curve of the network node is The network congestion degree curve of network nodes is shifted Similarity after units. Indicates the need for translation The upper limit of units, Indicates the need for translation The lower limit of units. Indicates the campus network The network node and The distance between network nodes.

[0048] Furthermore, the network congestion degree change curves of different network nodes are intercepted in the above manner, and the distances between the intercepted network congestion degree change curves are measured in combination with the correlation between different network nodes. When intercepting the first network congestion degree change curve, as an optional embodiment of the present invention, a first target time point at which the congestion degree is greater than a preset threshold is determined from the first network congestion degree change curve; a curve segment with a length of a preset length before the first target time point is intercepted from the first network congestion degree change curve as the first curve segment; when intercepting the second network congestion degree change curve, as an optional embodiment of the present invention, a second target time point at which the congestion degree is greater than a preset threshold is determined from the second network congestion degree change curve; a curve segment with a length of a preset length before the second target time point is intercepted from the second network congestion degree change curve as the second curve segment.

[0049] Specifically, the preset threshold and the preset length can be determined according to actual conditions. Specifically, the preset threshold is 0.8 and the preset length is 10, which are not limited in the embodiment of the present invention. As the first target time point and the second target time point, the network congestion level in the network congestion level change curve is intercepted to be greater than the preset threshold The length before the first target time point or before the second target time point is The curve of network congestion level changing over time.

[0050] Furthermore, when determining the sample distance between the first curve segment and the second curve segment, as an optional embodiment of the present invention, the absolute value of the first difference between the growth trend of the congestion level of the current network node at the current moment and the growth trend of the congestion level of other network nodes at the current moment is calculated; the second product of the inverse of the correlation, the DTW distance and the absolute value of the first difference is calculated; the second product is normalized to obtain the sample distance between the first curve segment and the second curve segment.

[0051] Specifically, the embodiment of the present invention takes the current network node as For example, other network nodes are Taking as an example, the calculation formula of the sample distance between the first curve segment and the second curve segment is explained. The sample distance between the first curve segment and the second curve segment can be calculated using the following formula:

[0052]

[0053] In the above formula, Indicates The first curve segment intercepted and the The sample distance between the intercepted second curve segments. Indicates The first curve segment intercepted is located in the network nodes and The second curve segment intercepted is located in the The relationship between network nodes. Indicates The first curve segment intercepted and the The DTW distance between the intercepted second curve segments. Indicates The growth trend of the congestion level of each network node at the current moment. Indicates The growth trend of the congestion level of each network node at the current moment. Represents the normalization function, which is used to Normalize.

[0054] Furthermore, when clustering the first curve segments and the second curve segments based on the sample distance, a k-shape clustering algorithm may be used to cluster the intercepted first curve segments and the second curve segments, and obtain cluster centers of different clusters.

[0055] Furthermore, when determining the maximum congestion degree in the curve segment corresponding to each cluster center, the final sample distances between the intercepted first curve segment and the second curve segment and each cluster center are first calculated, and the final sample distances of each first curve segment are arranged from small to large, and the top five cluster centers with the smallest final sample distances are found. The network congestion degree curve where the first curve segment is located is compared with the first cluster center. The final sample distance between cluster centers is recorded as , and the first On the network congestion curve corresponding to the cluster centers, the maximum congestion degree is recorded as .

[0056] Furthermore, combined with the similarity between the current network congestion curve and historical data, the smaller the final sample distance between a cluster center and the current network congestion curve, the greater the reference value of the data of the cluster center for the current prediction; the greater the similarity, the larger the maximum value of the network congestion curve, which indicates that the congestion level of the current network node at the next moment is likely to increase.

[0057] Furthermore, when determining the predicted congestion level of the current network node at a future moment, as an optional embodiment of the present invention, the congestion level of the current network node at the current moment is first determined; then the first ratio between each maximum congestion level and each sample distance is calculated, and the first ratios are averaged to obtain an average ratio; the average ratio is then normalized to obtain a normalized ratio; finally, the third product of the congestion level of the current network node at the current moment, the predetermined value and the normalized ratio is determined as the predicted congestion level of the current network node at the future moment.

[0058] Specifically, the preset value can be set according to the actual situation. In the embodiment of the present invention, the value is 2. Taking a network node as an example, the following formula can be used to calculate the predicted congestion level of the current network node at a future time:

[0059]

[0060] In the above formula, Indicates The congestion level of a network node at the next time point is the predicted congestion level of the current network node at the future moment. Indicates The congestion level of a network node at the current moment. Indicates The length before the network node is The first curve segment and the The final sample distance between cluster centers. Indicates Cluster centers. Indicates The maximum congestion level in the network congestion level curve corresponding to the cluster center. Represents the normalization function, which is used to Perform normalization.

[0061] Furthermore, after obtaining the congestion level at the next time point, the congestion level at the next time point is regarded as a known quantity, and the congestion level within the subsequent 10 minutes is predicted, and the prediction result is refreshed every 10 seconds.

[0062] S104: Determine the importance of the current network node according to the traffic data of the current network node at the current moment.

[0063] Specifically, when the congestion level of a network node is high, reducing the compression ratio will improve the data processing efficiency, while the data packet will also increase and the data transmission efficiency will be reduced, so it is necessary to select a suitable compression ratio. When determining a suitable compression ratio, the embodiment of the present invention can determine the target compression method of the data to be transmitted of the current network node according to the predicted congestion level, the current congestion level and the importance of the network node.

[0064] Furthermore, when determining the importance of a network node, as an optional embodiment of the present invention, first determine the number of types of traffic information in the traffic data, the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment, and the importance of each type of traffic information; then calculate the fourth product between the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment and the importance of each type of traffic information; finally, average the fourth products to obtain the importance of the current network node.

[0065] Specifically, the processing volume ratio of each type of traffic information in the traffic data at the current moment can be the ratio of a certain type of traffic information to the total traffic information of all types in the traffic data at the current moment. The importance of a certain type of traffic information can be predefined, such as predefining that the importance of video and audio is equally important, and the importance of text and images is second. In the embodiment of the present invention, the following formula can be used to calculate the importance of the current network node:

[0066]

[0067] In the above formula, Indicates The importance of a network node. Indicates The number of types of traffic information that a network node is exposed to. Indicates The type of traffic information that a network node is exposed to The processing volume ratio of traffic information of this category. Indicates The type of traffic information that a network node is exposed to Importance of class traffic information.

[0068] S105, determining a target compression method for data to be transmitted of the current network node according to the predicted congestion degree and importance.

[0069] Specifically, in the embodiment of the present invention, the network congestion degree is graded, and the network congestion degree is divided into 1 to 10 levels with a span of 0.1. When the level of congestion is higher, a compression method with a lower compression rate can be selected, that is, a certain range of compression rates are pre-assigned to different levels of compression. When determining the target compression method of the data to be transmitted, first determine at which level the predicted congestion level is, and then try the corresponding compression rate in the level according to the importance of the current network node, wherein the higher the importance, the lower the compression rate. Thus, the target compression method of the data to be transmitted of the current network node is determined.

[0070] S106, compressing the data to be transmitted using a target compression method and then transmitting it.

[0071] Specifically, the target compression method is used to compress the data to be transmitted before transmission.

[0072] Furthermore, after determining the congestion level at the current moment, the compression method can be determined according to the congestion level at the current moment and the importance of the data to be transmitted at the current moment, and the data to be transmitted at the current moment can be compressed and then transmitted.

[0073] The embodiment of the present invention can predict the congestion degree of the network node at a future time according to the network data of the network node at different times in the target network, and determine the target compression mode of the data to be transmitted of the current network node according to the predicted congestion degree at a future time and the importance of the network node of the current network, and compress the data to be transmitted according to the target compression mode before transmission. In this way, congestion in the target network is avoided, the data packet loss rate is reduced, and the security and reliability of data transmission are improved.

[0074] Embodiment 2:

[0075] Corresponding to the data security transmission method based on a computer network provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a data security transmission system based on a computer network, and the data security transmission system based on a computer network is used to execute the data security transmission method based on a computer network. Figure 2 A schematic diagram of the module composition of a computer network-based data security transmission system provided by an embodiment of the present invention is as follows: Figure 2As shown. The computer network-based data security transmission system 200 includes: an acquisition module 201, which is used to acquire network data of network nodes in the target network at different times, and the network data includes network indicators and flow data; a calculation module 202, which is used to calculate the congestion degree of each network node at different times according to the network indicators of each network node; a determination module 203, which is used to determine the predicted congestion degree of the current network node at a future time according to the congestion degree of the current network node at different times, the first network congestion degree change curve of the current network node at different historical times, and the second network congestion degree change curve of other network nodes at different historical times; the determination module 203 is also used to determine the importance of the current network node according to the flow data of the current network node at the current time; the determination module 203 is also used to determine the target compression method of the data to be transmitted of the current network node according to the predicted congestion degree and importance; and a transmission module 204, which is used to compress the data to be transmitted using the target compression method and then transmit it.

[0076] The embodiment of the present invention can predict the congestion degree of the network node at a future time according to the network data of the network node at different times in the target network, and determine the target compression mode of the data to be transmitted of the current network node according to the predicted congestion degree at a future time and the importance of the network node of the current network, and compress the data to be transmitted according to the target compression mode before transmission. In this way, congestion in the target network is avoided, the data packet loss rate is reduced, and the security and reliability of data transmission are improved.

[0077] Optionally, the calculation module 202 is also used to determine the bandwidth utilization, packet loss rate, average delay and queue length of the current network node from the network data of the network node; calculate the first product between the bandwidth utilization, packet loss rate, average delay and queue length; normalize the first product to obtain the congestion degree of the network node at different times.

[0078] Optionally, the determination module 203 is also used to determine the growth trend of the congestion level of the network node at the current moment by using the congestion level at each moment; obtain the first network congestion level change curve of the current network node at different historical moments and the second network congestion level change curve of other network nodes at different historical moments; determine the correlation between the current network node and the other network nodes according to the distance between the current network node and the other network nodes and the similarity between the first network congestion level change curve and the second network congestion level change curve; perform curve interception on the first network congestion level change curve to obtain multiple first curve segments; perform curve interception on the second network congestion level change curve to obtain to multiple second curve segments; determine the sample distance between the first curve segment and the second curve segment based on the correlation between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion level of the current network node at the current moment, and the growth trend of the congestion level of other network nodes at the current moment; cluster the first curve segments and the second curve segments based on the sample distance to obtain multiple cluster centers; determine the predicted congestion level of the current network node at a future moment according to the congestion level of the current network node at different moments, the sample distance between each first curve segment and each cluster center, and the maximum congestion level in the curve segment corresponding to each cluster center.

[0079] Optionally, the determination module 203 is also used to perform standardized weight conversion on the time to obtain a conversion value; determine the rate of change of the congestion level at the current time according to the congestion level at the current time and the congestion level at adjacent times adjacent to the current time; determine the growth trend of the congestion level of the network node at the current time according to the conversion value and the rate of change of the congestion level at the current time.

[0080] Optionally, the determination module 203 is also used to translate the second network congestion level change curve by multiple units in sequence to obtain a third network congestion level change curve; determine the maximum value of the similarities between the first network congestion level change curve and each third network congestion level change curve; and determine the product of the maximum value and the distance as the correlation between the current network node and other network nodes.

[0081] Optionally, the determination module 203 is further used to determine a first target time point at which the congestion level is greater than a preset threshold from the first network congestion level change curve; intercept a curve segment with a length of a preset length before the first target time point from the first network congestion level change curve as a first curve segment; intercept the second network congestion level change curve to obtain multiple second curve segments, including: determining a second target time point at which the congestion level is greater than a preset threshold from the second network congestion level change curve; intercepting a curve segment with a length of a preset length before the second target time point from the second network congestion level change curve as a second curve segment.

[0082] Optionally, the determination module 203 is also used to calculate the absolute value of the first difference between the growth trend of the congestion level of the current network node at the current moment and the growth trend of the congestion level of other network nodes at the current moment; calculate the second product between the inverse of the correlation, the DTW distance and the absolute value of the first difference; normalize the second product to obtain the sample distance between the first curve segment and the second curve segment.

[0083] Optionally, the determination module 203 is also used to determine the congestion level of the current network node at the current moment; calculate the first ratio between each maximum congestion level and each sample distance, and average the first ratios to obtain an average ratio; normalize the average ratio to obtain a normalized ratio; determine that the third product of the congestion level of the current network node at the current moment, the predetermined value and the normalized ratio is the predicted congestion level of the current network node at the future moment.

[0084] Optionally, the determination module 203 is also used to determine the number of types of traffic information in the traffic data, the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment, and the importance of each type of traffic information; calculate the fourth product between the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment and the importance of each type of traffic information; and average each fourth product to obtain the importance of the current network node.

[0085] Embodiment three:

[0086] Corresponding to the data security transmission method based on a computer network provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a data security transmission system based on a computer network, and the data security transmission system based on a computer network is used to execute the data security transmission method based on a computer network. Figure 3 A schematic diagram of a computer network-based data security transmission system according to an embodiment of the present invention is shown in FIG. Figure 3The data security transmission system based on computer network may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302, the memory 302 is used to store computer programs that can be run on the processor 301, and the processor 301 is used to execute the program stored in the memory 302 to achieve the above Figure 1 The memory 302 may be a temporary storage or a permanent storage. The application stored in the memory 302 may include one or more modules (not shown in the figure), each of which may include a series of computer executable instructions in a computer network-based data security transmission system.

[0087] Furthermore, the processor 301 can be configured to communicate with the memory 302, and execute a series of computer executable instructions in the memory 302 on the computer network-based data security transmission system. The computer network-based data security transmission system can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, and one or more keyboards 306.

[0088] Specifically in this embodiment, the data security transmission system based on the computer network includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment are similar to those in the method embodiment, and have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0089] It should be noted that the computer network-based data security transmission system provided by the embodiment of the present invention and the computer network-based data security transmission method provided by the embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned computer network-based data security transmission method, and has the same or similar beneficial effects, and the repeated parts will not be repeated.

[0090] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A data security transmission method based on a computer network, characterized in that: The computer network-based data security transmission method comprises: Acquire network data of network nodes in the target network at different times, wherein the network data includes network indicators and flow data; Calculating the congestion degree of each of the network nodes at different times according to the network indicators of each of the network nodes; Determine the predicted congestion level of the current network node at a future time according to the congestion level of the current network node at different times, the first network congestion level change curve of the current network node at different historical times, and the second network congestion level change curve of other network nodes at different historical times; Determining the importance of the current network node according to the traffic data of the current network node at the current moment; Determining a target compression method for data to be transmitted of the current network node according to the predicted congestion level and the importance level; Using the target compression method to compress the data to be transmitted and then transmit it; Determining the predicted congestion level of the current network node at a future time according to the congestion level of the current network node at different times, the first network congestion level change curve of the current network node at different historical times, and the second network congestion level change curves of other network nodes at different historical times includes: Determine the growth trend of the congestion level of the network node at the current moment by using the congestion level at each of the moments; Obtain a first network congestion degree change curve of a current network node at different historical moments and a second network congestion degree change curve of other network nodes at different historical moments; Determining the correlation between the current network node and the other network nodes according to the distance between the current network node and the other network nodes and the similarity between the first network congestion degree change curve and the second network congestion degree change curve; Intercepting the first network congestion degree change curve to obtain a plurality of first curve segments; Intercepting the second network congestion degree change curve to obtain a plurality of second curve segments; Determine the sample distance between the first curve segment and the second curve segment based on the association between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion level of the current network node at the current moment, and the growth trend of the congestion level of the other network nodes at the current moment; Clustering each of the first curve segments and each of the second curve segments based on the sample distance to obtain a plurality of cluster centers; The predicted congestion degree of the current network node at a future time is determined according to the congestion degree of the current network node at different times, the sample distances between each of the first curve segments and each of the cluster centers, and the maximum congestion degree in the curve segments corresponding to each of the cluster centers.

2. The computer network-based data security transmission method according to claim 1, characterized in that: Calculating the congestion degree of each of the network nodes at different times according to the network indicators of each of the network nodes includes: Determine the bandwidth utilization, packet loss rate, average delay and queue length of the current network node from the network data of the network node; Calculating a first product among the bandwidth utilization, the packet loss rate, the average delay and the queue length; The first product is normalized to obtain the congestion degree of the network node at different times.

3. The computer network-based data security transmission method according to claim 1, characterized in that: Determining the growth trend of the congestion level of the network node at the current moment by using the congestion level at each moment includes: Performing a standardized weight conversion on the time to obtain a conversion value; Determine a rate of change of the congestion level at the current moment according to the congestion level at the current moment and the congestion level at an adjacent moment adjacent to the current moment; The growth trend of the congestion level of the network node at the current moment is determined according to the conversion value and the congestion level change rate at the current moment.

4. The computer network-based data security transmission method according to claim 1, characterized in that: The determining, according to the distance between the current network node and the other network nodes and the similarity between the first network congestion degree change curve and the second network congestion degree change curve, the association between the current network node and the other network nodes comprises: Shifting the second network congestion degree change curve by multiple units in sequence to obtain a third network congestion degree change curve; Determining a maximum value among similarities between the first network congestion level change curve and each of the third network congestion level change curves; The product of the maximum value and the distance is determined as the association between the current network node and the other network nodes.

5. The computer network-based data security transmission method according to claim 1, characterized in that: The intercepting of the first network congestion degree change curve to obtain a plurality of first curve segments comprises: Determining a first target time point at which the congestion level is greater than a preset threshold from the first network congestion level change curve; A curve segment having a preset length before the first target time point is intercepted from the first network congestion degree change curve as the first curve segment; The intercepting the second network congestion degree change curve to obtain a plurality of second curve segments comprises: Determining a second target time point at which the congestion level is greater than the preset threshold from the second network congestion level change curve; A curve segment having a preset length before the second target time point is intercepted from the second network congestion level change curve as the second curve segment.

6. The computer network-based data security transmission method according to claim 1, characterized in that: The determining of the sample distance between the first curve segment and the second curve segment based on the association between the first network node and the second network node, the DTW distance between the first curve segment and the second curve segment, the growth trend of the congestion level of the current network node at the current moment, and the growth trend of the congestion level of the other network nodes at the current moment comprises: Calculating an absolute value of a first difference between a growth trend of the congestion level of the current network node at a current moment and a growth trend of the congestion level of the other network nodes at a current moment; Calculating a second product of the inverse of the correlation, the DTW distance, and the absolute value of the first difference; The second product is normalized to obtain a sample distance between the first curve segment and the second curve segment.

7. The computer network-based data security transmission method according to claim 1, characterized in that: Determining the predicted congestion degree of the current network node at a future time according to the congestion degree of the current network node at different times, the sample distances between each of the first curve segments and each of the cluster centers, and the maximum congestion degree in the curve segments corresponding to each of the cluster centers includes: Determine the congestion level of the current network node at the current moment; Calculating a first ratio between each of the maximum congestion levels and each of the sample distances, and averaging each of the first ratios to obtain an average ratio; Normalizing the average ratio to obtain a normalized ratio; The third product of the congestion level of the current network node at the current moment, the predetermined value and the normalized ratio is determined as the predicted congestion level of the current network node at the future moment.

8. The computer network-based data security transmission method according to any one of claims 1 to 7, characterized in that: Determining the importance of the current network node according to the traffic data of the current network node at the current moment includes: Determine the number of types of traffic information in the traffic data, the proportion of each type of traffic information processed by the current network node in the traffic data at the current moment, and the importance of each type of traffic information; Calculate a fourth product between the proportion of the processing volume of each type of traffic information in the traffic data of the current network node at the current moment and the importance of each type of traffic information; An average of the fourth products is calculated to obtain the importance of the current network node.

9. A data security transmission system based on a computer network, characterized in that: The computer network-based data security transmission system includes: a processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; the processor is used to execute the program stored in the memory to implement the steps of the computer network-based data security transmission method as described in any one of claims 1-8.

Images