Network state analysis method and device, electronic device, and storage medium
By generating network state images and using convolutional neural networks for analysis, the problem of the inability to comprehensively measure the state of communication networks in existing technologies is solved, thereby improving communication efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA UNITED NETWORK COMM GRP CO LTD
- Filing Date
- 2023-04-18
- Publication Date
- 2026-07-21
AI Technical Summary
Existing technologies cannot fully measure the network status of communication networks, resulting in low communication efficiency.
By processing network information in a time sequence, a network state image is generated, and the image is analyzed using a target convolutional neural network to obtain network situation information, including normal state, abnormal state, and fault information.
It enables comprehensive status measurement of the communication network, improving the efficiency and accuracy of communication between communication devices.
Smart Images
Figure CN116389291B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, specifically to a network potential analysis method and apparatus, electronic equipment, and storage medium. Background Technology
[0002] Currently, situational awareness of communication networks typically employs data analysis to examine data generated by network devices and links to determine whether each device is functioning correctly. However, this method cannot comprehensively assess the network status, thus reducing communication efficiency. Summary of the Invention
[0003] To this end, this application provides a network potential analysis method and apparatus, electronic device, and storage medium to solve the problem of how to comprehensively measure the network potential of a communication network, thereby improving the communication efficiency between various devices in the communication network.
[0004] To achieve the above objectives, the first aspect of this application provides a network situation analysis method, the method comprising: processing collected network information based on time sequence to obtain a network state image, wherein the network information includes at least one of network topology information, network element state information, link state information and network management interface state information; and inputting the network state image into a target convolutional neural network for analysis to obtain network situation information.
[0005] In some optional implementations, network situation information includes at least one of: normal status information, abnormal status information, and fault information;
[0006] The abnormal status information includes at least one of the following: abnormal information of network element devices, abnormal information of links, and abnormal information of network management devices;
[0007] The fault information includes at least one of the following: network element equipment fault information, link fault information, and network management equipment fault information.
[0008] In some optional implementations, the acquired network information is processed based on time sequence to obtain a network state image, including:
[0009] The network element status information, link status information, and network management interface status information are formatted respectively to obtain formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information.
[0010] Based on the generation time of the network information itself, the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information are spliced together to obtain spliced information; the spliced information is then processed into a graphical representation to generate a network status image.
[0011] In some optional implementations, the network topology information includes at least one of the following: the number of network element devices, the number of network management devices, link information between different network element devices, and interface information between the network management device and each network element device.
[0012] In some optional implementations, the network element status information includes at least one of attribute information, configuration information, performance information, and alarm information; wherein, the attribute information includes at least one of equipment manufacturer information, network access time, and network element region information; and the performance information includes load and / or latency information during network element operation.
[0013] Link status information includes: link input and output information, link capacity information, and load information. Link capacity information includes at least one of maximum bandwidth, minimum latency, and maximum utilization. Load information includes at least one of actual bandwidth, bandwidth utilization, packet loss rate, and latency information.
[0014] The network management interface status information includes at least one of the following: network management configuration information, network management performance information, and network management alarm information. Among them, the network management performance information includes the load information and / or latency information of the network management device during operation, and the network management alarm information includes the interface alarm information between the network management device and each network element device.
[0015] In some optional implementations, before inputting the network state image into the target convolutional neural network for analysis to obtain network situation information, the following steps are also included:
[0016] The initial convolutional neural network is trained based on the training data to obtain the target convolutional neural network;
[0017] The training data is generated by annotating multiple images carrying network information. The training data includes multiple sample images, which are temporally continuous.
[0018] The output data of the target convolutional neural network includes network situation information corresponding to the time information in the sample image.
[0019] In some optional implementations, the correspondence between the sample image at the first time point and the first network potential information is used as the basis for judging the accuracy of the network potential information, and the correspondence between the sample image at the first time point and the second network potential information is used as the basis for predicting the accuracy of the network potential information.
[0020] The first network potential information is obtained by inputting the sample image collected at the first time point into the target convolutional neural network for analysis;
[0021] The second network potential information is obtained by inputting the sample image collected at the next time step after the first time point into the target convolutional neural network for analysis.
[0022] To achieve the above objectives, a second aspect of this application provides a network situation analysis device, comprising: a processing module configured to process collected network information based on time sequence to obtain a network situation image, wherein the network information includes at least one of network topology information, network element status information, link status information, and network management interface status information; and an analysis module configured to input the network situation image into a target convolutional neural network for analysis to obtain network situation information.
[0023] To achieve the above objectives, in a third aspect, this application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the above-described network potential analysis method.
[0024] To achieve the above objectives, in a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described network potential analysis method.
[0025] The network situation analysis method, apparatus, electronic device, and storage medium in this application process collected network information in a time sequence to obtain a network situation image. The network information includes at least one of network topology information, network element status information, link status information, and network management interface status information. This clarifies different dimensions of information in the communication network, facilitating a clear and intuitive understanding of the network situation through the network situation image. The network situation image is then input into a target convolutional neural network for analysis, enabling the recognition of the network situation and obtaining network situation information. The convolutional neural network is fully utilized for image recognition of the network situation image, improving information recognition efficiency and comprehensively measuring the network situation in the communication network, thereby improving communication efficiency based on accurate network situation information. Attached Figure Description
[0026] The accompanying drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the detailed description of exemplary embodiments with reference to the accompanying drawings, in which:
[0027] Figure 1 This is a flowchart illustrating a network potential analysis method provided in an embodiment of this application.
[0028] Figure 2 This is a schematic diagram of a network topology image provided in an embodiment of this application.
[0029] Figure 3 This is a schematic diagram of a graphical network element status image provided in an embodiment of this application.
[0030] Figure 4 This is a schematic diagram of a link status image provided in an embodiment of this application.
[0031] Figure 5 This is a schematic diagram of a network management interface status image provided in an embodiment of this application.
[0032] Figure 6 This is a schematic diagram of a network status image provided in an embodiment of this application.
[0033] Figure 7 This is a block diagram of a network potential analysis device provided in an embodiment of this application.
[0034] Figure 8 This is a block diagram of a network potential analysis system provided in an embodiment of this application.
[0035] Figure 9 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0036] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the application. Those skilled in the art can implement this application without requiring some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0037] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0038] The first aspect of this application provides a method for network potential analysis. Figure 1 This is a flowchart illustrating a network potential analysis method provided in an embodiment of this application. This network potential analysis method can be applied to a network potential analysis device. Figure 1 As shown, the network potential analysis method includes, but is not limited to, the following steps.
[0039] Step S101: Process the collected network information based on time sequence to obtain a network status image.
[0040] The network information includes at least one of the following: network topology information, network element status information, link status information, and network management interface status information.
[0041] Step S102: Input the network state image into the target convolutional neural network for analysis to obtain network situation information.
[0042] The network status information includes at least one of the following: normal status information, abnormal status information, and fault information. Abnormal status information includes at least one of the following: network element device abnormality information, link abnormality information, and network management device abnormality information; fault information includes at least one of the following: network element device fault information, link fault information, and network management device fault information.
[0043] By using a target convolutional neural network to analyze network state images, the analysis of the operational status of various devices in a communication network can be accelerated based on image processing, and the accuracy of network situation analysis can be improved. Furthermore, the network situation information output by the target convolutional neural network can be used to evaluate the overall operation of the communication network, comprehensively measure the network state, and improve communication efficiency based on accurate network situation information.
[0044] In this embodiment, network status images are obtained by processing the collected network information based on time sequence. The network information includes at least one of network topology information, network element status information, link status information, and network management interface status information. This clarifies different dimensions of information in the communication network, making it easy to intuitively understand the network status through the network status image. The network status image is then input into a target convolutional neural network for analysis to achieve network situational awareness and obtain network situational information. The convolutional neural network is fully utilized for image recognition of the network status image to improve information recognition efficiency and comprehensively measure the network status in the communication network, thereby improving communication efficiency based on accurate network situational information.
[0045] In some optional implementations, the process of processing the collected network information based on time sequence to obtain a network state image in step S101 can be implemented in the following way:
[0046] The network element status information, link status information, and network management interface status information are formatted separately to obtain formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information. Based on the generation time of the network information itself, the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information are spliced together to obtain spliced information. The spliced information is then image-processed to obtain a spliced image. The spliced image is then labeled to generate a network status image.
[0047] Among them, formatting different information can be done by organizing information into a specific format according to the required format of various information, so as to meet the usage needs of different information.
[0048] Furthermore, screenshots can be used to visualize the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information, respectively, so as to convert the formatted network topology information into a network topology image, the formatted network element status information into a network element status image, the formatted link status information into a link status image, and the formatted network management interface status information into a network management interface status image, etc.
[0049] Based on the chronological order of the generation of each network information, network topology images, network element status images, link status images, and network management interface status images corresponding to the same point in time can be stitched together to obtain a more complete network status image that can characterize the operation of the communication network.
[0050] Alternatively, the above images can be obtained using an information snapshot method.
[0051] It should be noted that obtaining the network status image can be achieved by first splicing together the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information to obtain spliced information; then, the spliced information is processed into an image to generate the network status image.
[0052] Alternatively, the formatted network topology information can be converted into a network topology image, the formatted network element status information into a network element status image, the formatted link status information into a link status image, and the formatted network management interface status information into a network management interface status image. Then, the network topology image, network element status image, link status image, and network management interface status information can be spliced together to generate a network status image.
[0053] The above-described methods for acquiring images are merely illustrative examples. Specific settings can be made according to actual needs. Other undescribed methods for acquiring images are also within the scope of protection of this application and will not be elaborated upon here.
[0054] In some specific implementations, the stitched information is processed into an image to obtain a stitched image. This can involve converting the stitched information into a picture and then processing and / or modifying the picture. For example, image processing software can be used to adjust the color, cut out the image, composite it, modify the brightness and contrast, modify the saturation and color, add special effects, edit, and repair the image.
[0055] Furthermore, the images transformed from the stitched information can be analyzed, processed, and refined to create stitched images that meet user needs. These stitched images can be stored digitally.
[0056] In some optional implementations, the network topology information includes at least one of the following: the number of network element devices, the number of network management devices, link information between different network element devices, and interface information between the network management device and each network element device.
[0057] For example, Figure 2 This is a schematic diagram of a network topology image provided in an embodiment of this application. Figure 2 As shown, based on time information (e.g., year X month X day X hour X minute X second, where X is a positive integer), the communication connection information between the network management device and multiple network element devices (e.g., network element 1, network element 2, network element 3, ..., network element m) through network management interface-1, network management interface-2, ..., network management interface-n is determined. Here, n and m are both integers greater than or equal to 1.
[0058] Specifically, network element 1 and network element 2 are connected via link 1-2; network element 2 and network element 3 are connected via link 2-3; network element 1 and network element 3 are connected via link 1-3; network element 1 and network element m are connected via link 1-m; network element 2 and network element m are connected via link 2-m; and network element 3 and network element m are connected via link 3-m.
[0059] Based on the graphical display method, the network topology information is presented intuitively and clearly, which facilitates the subsequent analysis of network potential information.
[0060] In some optional implementations, the network element status information includes at least one of attribute information, configuration information, performance information, and alarm information; wherein, the attribute information includes at least one of equipment manufacturer information, network access time, and network element region information; and the performance information includes load and / or latency information of the network element equipment during operation.
[0061] For example, Figure 3 This is a schematic diagram of a network element status image provided in an embodiment of this application. For example... Figure 3 As shown, according to Figure 2 The network topology image shown can further obtain network element information, and display the network element information of each network element in a graphical way, which facilitates accurate analysis of network element information based on graphical processing.
[0062] Among them, the network element information corresponding to network element 1 includes configuration information (e.g., parameter 1, parameter 2, etc.), performance information (e.g., load information, latency information, etc.), and alarm information (e.g., device alarm 1, device alarm 2, etc.). The network element information corresponding to network elements 2 and 3 both include configuration information, performance information, and alarm information, only the values corresponding to each piece of information are different; the network element information corresponding to other network elements is as follows: Figure 3 As shown, it will not be elaborated further here.
[0063] It should be noted that network elements of the same type have the same network element information. For example, if network elements 1 to m are all terminals, then the network element information for each network element includes configuration information, performance information, and alarm information. However, the operating status of different network elements may differ at the same time. Therefore, the values in the above information may vary. This allows us to determine which network element may be abnormal or malfunctioning based on thresholds, enabling timely troubleshooting of network elements and improving communication efficiency between network elements.
[0064] In some optional implementations, the link status information includes: link input and output information, link capacity information, and load information. The link capacity information includes at least one of maximum bandwidth, minimum latency, and maximum utilization. The load information includes at least one of actual bandwidth, bandwidth utilization, packet loss rate, and latency information.
[0065] For example, Figure 4 This is a schematic diagram of a link status image provided in an embodiment of this application. Figure 4 As shown, according to Figure 2 The network topology image shown can further obtain link status information and display the link status information of each link in a graphical way, which facilitates accurate analysis of link status information based on graphical processing.
[0066] The link status information corresponding to link 1-2 includes: input and output information (1, 2), link capacity information (e.g., maximum bandwidth, minimum latency, and maximum utilization) and load information (e.g., actual bandwidth, bandwidth utilization, packet loss rate, and latency); the link status information corresponding to link 1-3 includes: input and output information (1, 3), link capacity information (e.g., maximum bandwidth, minimum latency, and maximum utilization) and load information (e.g., actual bandwidth, bandwidth utilization, packet loss rate, and latency); ...; the link status information corresponding to link 3-m includes: input and output information (3, m), link capacity information (e.g., maximum bandwidth, minimum latency, and maximum utilization) and load information (e.g., actual bandwidth, bandwidth utilization, packet loss rate, and latency).
[0067] It should be noted that different links have different operating parameters at the same time. Therefore, the values in the above link information are different. This allows us to determine which link may be abnormal or faulty based on thresholds, and to promptly investigate abnormal links, improve the effectiveness of communication links, and ensure normal communication between various network elements.
[0068] In some optional implementations, the network management interface status information includes at least one of the following: network management configuration information, network management performance information, and network management alarm information. The network management performance information includes load information and / or latency information during the operation of the network management device, and the network management alarm information includes interface alarm information between the network management device and various network element devices.
[0069] For example, Figure 5 This is a schematic diagram of a network management interface status image provided in an embodiment of this application. Figure 5 As shown, according to Figure 2 The network topology image shown can further obtain the interface status information between the network management device and other network elements, and display the status information of each network management interface in a graphical way, which facilitates accurate analysis of the status information of each network management interface based on the graphical processing method.
[0070] Among them, network management interface-1 includes network management configuration information (e.g., parameters), network management performance information (e.g., load information, latency information, etc. when the network management device is running), and network management alarm information (e.g., interface alarm information between the network management device and various network element devices); network management interface-2 includes network management configuration information (e.g., parameters), network management performance information (e.g., load information, latency information, etc. when the network management device is running), and network management alarm information (e.g., interface alarm information between the network management device and various network element devices); ...; network management interface-n includes network management configuration information (e.g., parameters), network management performance information (e.g., load information, latency information, etc. when the network management device is running), and network management alarm information (e.g., interface alarm information between the network management device and various network element devices).
[0071] By visualizing the parameter values of different network management interfaces, it is possible to obtain... Figure 5 The network management interface status image shown provides a clear and intuitive display of the network management interface status information, thereby improving the efficiency of processing this information.
[0072] For example, Figure 6 This is a schematic diagram of a network status image provided in an embodiment of this application. Figure 6 As shown, the network state image represents the state at the same time (e.g., all are X year X month X day X hour X minute X second). Figure 2 Network topology image in Figure 3 Network element status images, Figure 4 Link status images in, and Figure 5 The network management interface status images are stitched together to obtain a stitched image, which is then annotated to generate a... Figure 6 The network status image shown.
[0073] based on Figure 6 The network status image shown can comprehensively measure information such as the status of each network element, network management device, and link between devices in the communication network, which facilitates the overall analysis of the communication network.
[0074] In some optional implementations, before performing step S102 of inputting the network state image into the target convolutional neural network for analysis to obtain network situation information, the method further includes: training the initial convolutional neural network based on training data to obtain the target convolutional neural network.
[0075] The training data is generated by annotating multiple images carrying network information. The training data includes multiple sample images, which are temporally continuous. The output data of the target convolutional neural network includes network situation information corresponding to the temporal information in the sample images.
[0076] Among them, the annotation of images carrying network information is to annotate the network status of the images by combining information such as fault reports from operation and maintenance personnel and expert experience, so that the annotated images can clearly reflect the status of each network element device (or network management device, or links between devices, etc.).
[0077] For example, different status codes can be used to characterize whether each network element is working properly. For example, "0" indicates that the network element is working normally; "1" indicates that the network element is in an abnormal working state; and "2" indicates that the network element is in a fault state.
[0078] By using the different status codes included in the annotated image, the status of network element devices at different times can be clearly identified, which facilitates the statistical analysis of the real-time operation of the communication network.
[0079] Furthermore, by inputting multiple sample images into the initial convolutional neural network for training, a trained convolutional neural network is obtained, and when the trained convolutional neural network meets preset conditions, the target convolutional neural network can be obtained.
[0080] Specifically, the correspondence between the sample image at the first time point and the first network potential information is used as the basis for judging the accuracy of the network potential information, and the correspondence between the sample image at the first time point and the second network potential information is used as the basis for predicting the accuracy of the network potential information.
[0081] It should be noted that the first time point is a preset time point. By using the correspondence between the sample image at the first time point and the first network potential information as the basis for judging the accuracy of the network potential information, the trend of the network potential corresponding to the first time point can be clearly defined, so that the obtained target convolutional neural network can meet the user's needs, that is, it can predict the network potential information corresponding to the expected time point.
[0082] The first network potential information is obtained by inputting the sample image collected at the first time point into the target convolutional neural network for analysis; the second network potential information is obtained by inputting the sample image collected at the next time point of the first time point into the target convolutional neural network for analysis.
[0083] A second aspect of this application provides a network potential analysis device. Figure 7 This is a block diagram of a network potential analysis device provided in an embodiment of this application.
[0084] like Figure 7 As shown, the network potential analysis device 700 includes, but is not limited to, the following modules.
[0085] The processing module 701 is configured to process the collected network information based on time sequence to obtain a network status image, wherein the network information includes at least one of network topology information, network element status information, link status information and network management interface status information.
[0086] The analysis module 702 is configured to input the network state image into the target convolutional neural network for analysis to obtain network situation information.
[0087] It should be noted that the network potential analysis device 700 can implement any of the network potential analysis methods in this application.
[0088] In some optional implementations, network status information includes at least one of normal status information, abnormal status information, and fault information; wherein, abnormal status information includes at least one of network element device abnormal information, link abnormal information, and network management device abnormal information; and fault information includes at least one of network element device fault information, link fault information, and network management device fault information.
[0089] In some optional implementations, the processing module 701 is specifically used to: format the network element status information, link status information, and network management interface status information respectively to obtain formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information; splice the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information according to the generation time of the network information itself to obtain spliced information; and perform image processing on the spliced information to generate a network status image.
[0090] In some optional implementations, the network topology information includes at least one of the following: the number of network element devices, the number of network management devices, link information between different network element devices, and interface information between the network management device and each network element device.
[0091] In some optional implementations, the network element status information includes at least one of the following: attribute information, configuration information, performance information, and alarm information; wherein, the attribute information includes at least one of the following: equipment manufacturer information, network access time, and network element region information; the performance information includes: load and / or latency information of the network element device during operation; the link status information includes: input and output information of the link, link capacity information, and load information, wherein the link capacity information includes at least one of the following: maximum bandwidth, minimum latency, and maximum utilization; the load information includes at least one of the following: actual bandwidth, bandwidth utilization, packet loss rate, and latency information; the network management interface status information includes at least one of the following: network management configuration information, network management performance information, and network management alarm information, wherein the network management performance information includes load and / or latency information of the network management device during operation, and the network management alarm information includes interface alarm information between the network management device and each network element device.
[0092] In some alternative implementations, the network potential analysis apparatus 700 further includes a training module (not shown) configured to train an initial convolutional neural network based on training data to obtain a target convolutional neural network.
[0093] The training data is generated by annotating multiple images carrying network information. The training data includes multiple sample images, which are temporally continuous. The output data of the target convolutional neural network includes network situation information corresponding to the temporal information in the sample images.
[0094] In some optional implementations, the correspondence between the sample image at the first time point and the first network potential information is used as the basis for judging the accuracy of the network potential information, and the correspondence between the sample image at the first time point and the second network potential information is used as the basis for judging the accuracy of the prediction of the network potential information.
[0095] The first network potential information is obtained by inputting the sample image collected at the first time point into the target convolutional neural network for analysis; the second network potential information is obtained by inputting the sample image collected at the next time point of the first time point into the target convolutional neural network for analysis.
[0096] In this embodiment, the processing module processes the collected network information in chronological order to obtain a network status image. The network information includes at least one of network topology information, network element status information, link status information, and network management interface status information. This clearly defines different dimensions of information in the communication network, making it easy to intuitively understand the network status through the network status image. The analysis module inputs the network status image into a target convolutional neural network for analysis, enabling the understanding of the network situation and obtaining network situation information. By fully utilizing the convolutional neural network to perform image recognition on the network status image, the efficiency of information recognition is improved, and the network status in the communication network is comprehensively measured, so as to improve communication efficiency based on accurate network situation information.
[0097] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problem proposed in this application; however, this does not mean that other units are absent from this embodiment.
[0098] A third aspect of this application provides a network potential analysis system. Figure 8 This is a block diagram of a network potential analysis system provided in an embodiment of this application.
[0099] like Figure 8 As shown, the network potential analysis system includes, but is not limited to, the following devices: a data preprocessing unit 810, a model training unit 820, and a model usage unit 830.
[0100] The data preprocessing unit 810 includes an information formatting processing module 811, an information image processing module 812, and an annotation module 813. The model usage unit 830 includes a cognition module 831 and a cognition result determination module 832.
[0101] The information formatting processing module 811 is used to receive network topology information, network element status information, link status information and network management interface status information, and to format the above-mentioned various types of information.
[0102] The information image processing module 812 is used to perform image processing on the formatted information, that is, to convert the formatted network topology information into a network topology image, the formatted network element status information into a network element status image, the formatted link status information into a link status image, and the formatted network management interface status information into a network management interface status image, etc.
[0103] Furthermore, the information image processing module 812 is also used to stitch together the network topology image, network element status image, link status image and network management interface status image corresponding to the same time point according to the chronological order of the generation time of each network information to obtain a stitched image.
[0104] The annotation module 813 is used to annotate the stitched image to obtain the annotated network state image.
[0105] The model training unit 820 is used to input the labeled network state image as training data into the initial three-dimensional convolutional neural network for training, and obtain a target convolutional neural network that meets the preset training conditions. This target convolutional neural network can accurately analyze the labeled network state image to obtain network potential information.
[0106] The training data includes multiple sample images, which are temporally continuous and carry network information. The output data of the target convolutional neural network includes network situation information corresponding to the temporal information in the sample images.
[0107] For example, the training data consists of network state images at y consecutive time points, namely, network state image k1, network state image k2, network state image k3, ..., network state image ky. Here, y is an integer greater than or equal to 1.
[0108] The aforementioned y network state images are used as a set of training data and input into the initial three-dimensional convolutional neural network for training until the trained convolutional neural network meets the preset training conditions, thereby obtaining the target convolutional neural network.
[0109] During training, the correspondence between the sample image at the first time point and the first network potential information can be used as the basis for judging the accuracy of the network potential information, and the correspondence between the sample image at the first time point and the second network potential information can be used as the basis for judging the accuracy of the prediction of the network potential information.
[0110] For example, the output of the trained convolutional neural network is y network potential information corresponding to y network state images, such as network potential information S1, network potential information S2, ..., network potential information Sy.
[0111] The first network potential information is obtained by inputting the sample image collected at the first time point into the target convolutional neural network for analysis; the second network potential information is obtained by inputting the sample image collected at the next time point of the first time point into the target convolutional neural network for analysis.
[0112] In other words, the correspondence between the network state image k1 and the network potential information S1 is used as the basis for judgment, and the correspondence between the network state image k1 and the network potential information S2 is used as the basis for the accuracy of the prediction of the network potential information.
[0113] The cognitive module 831 is used to analyze the image input by the information image processing module 812 using a target convolutional neural network, obtain the analysis result, and output the analysis result to the cognitive result determination module 832.
[0114] The cognitive result determination module 832 is used to judge the received analysis result and determine whether the analysis result meets the usage requirements of the network potential information of the communication network. If the usage requirements are met, the output network potential information is obtained.
[0115] It should be noted that the use of network status information involves evaluating and judging the working status of each device in the communication network and the links between them, in order to determine whether the device is working normally (or whether the device has any abnormalities or faults, etc.), thereby making a comprehensive assessment of the communication network.
[0116] In this embodiment, by formatting network topology information, network element status information, link status information, and network management interface status information, and then visualizing the formatted information to form images corresponding to different information, a trained target convolutional neural network can be used to classify the network status images, enabling the recognition of network situation information. This supports the judgment of the current communication network situation and the prediction of the network situation over a future period. Thus, a comprehensive assessment of the communication network is achieved, reducing equipment failure maintenance time and improving communication efficiency.
[0117] The fourth aspect of this application provides an electronic device and a computer-readable storage medium, both of which can be used to implement any of the network potential analysis methods in this application. The corresponding technical solutions and descriptions are described in the corresponding records in the method section and will not be repeated here.
[0118] Figure 9 This is a block diagram of an electronic device provided in an embodiment of this application. (For example...) Figure 9 As shown, this application provides an electronic device, which includes: at least one processor 901; at least one memory 902; and one or more I / O interfaces 903 connected between the processor 901 and the memory 902; wherein the memory 902 stores one or more computer programs that can be executed by the at least one processor 901, and the one or more computer programs are executed by the at least one processor 901 to enable the at least one processor 901 to perform the above-described network potential analysis method.
[0119] This application also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor / processor core, implements the network potential analysis method described above. The computer-readable storage medium can be volatile or non-volatile.
[0120] This application also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the network potential analysis method described above.
[0121] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).
[0122] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.
[0123] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.
[0124] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state information from the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.
[0125] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.
[0126] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0127] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0128] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0130] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for general illustrative purposes only and should not be construed as limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this application as set forth by the appended claims.
Claims
1. A method for network potential analysis, characterized in that, The method includes: The network information collected is processed based on time sequence to obtain a network status image, wherein the network information includes at least one of network topology information, network element status information, link status information and network management interface status information. The network state image is input into the target convolutional neural network for analysis to obtain network situation information; The step of processing the collected network information based on time sequence to obtain a network status image includes: formatting the network element status information, link status information, and network management interface status information according to the required format to obtain formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information; splicing the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information according to the generation time of the network information itself to obtain spliced information; and performing image processing on the spliced information using a screenshot or information snapshot method to generate the network status image.
2. The method according to claim 1, characterized in that, The network situation information includes at least one of the following: normal status information, abnormal status information, and fault information; The abnormal status information includes at least one of the following: abnormal information of network element devices, abnormal information of links, and abnormal information of network management devices; The fault information includes at least one of the following: network element equipment fault information, link fault information, and network management equipment fault information.
3. The method according to any one of claims 1 to 2, characterized in that, The network topology information includes at least one of the following: the number of network element devices, the number of network management devices, link information between different network element devices, and interface information between the network management device and each of the network element devices.
4. The method according to claim 3, characterized in that, The network element status information includes at least one of the following: attribute information, configuration information, performance information, and alarm information; wherein, the attribute information includes at least one of the following: equipment manufacturer information, network access time, and network element region information; the performance information includes: load and / or latency information of the network element device during operation; The link status information includes: link input and output information, link capacity information, and load information. The link capacity information includes at least one of maximum bandwidth, minimum latency, and maximum utilization. The load information includes at least one of actual bandwidth, bandwidth utilization, packet loss rate, and latency information. The network management interface status information includes at least one of the following: network management configuration information, network management performance information, and network management alarm information. The network management performance information includes the load information and / or latency information of the network management device during operation, and the network management alarm information includes interface alarm information between the network management device and each of the network element devices.
5. The method according to claim 1, characterized in that, Before inputting the network state image into the target convolutional neural network for analysis to obtain network situation information, the method further includes: The initial convolutional neural network is trained based on the training data to obtain the target convolutional neural network; The training data is generated by annotating multiple images carrying network information. The training data includes multiple sample images, which are temporally continuous. The output data of the target convolutional neural network includes network situation information corresponding to the time information in the sample image.
6. The method according to claim 5, characterized in that, The correspondence between the sample image at the first time point and the first network potential information is used as the basis for judging the accuracy of the network potential information, and the correspondence between the sample image at the first time point and the second network potential information is used as the basis for predicting the accuracy of the network potential information. Wherein, the first network potential information is information obtained by inputting the sample image collected at the first time point into the target convolutional neural network for analysis; The second network potential information is obtained by inputting the sample image collected at the next moment after the first time point into the target convolutional neural network for analysis.
7. A network potential analysis device, characterized in that, include: The processing module is configured to process the collected network information in chronological order to obtain a network status image. The network information includes at least one of network topology information, network element status information, link status information, and network management interface status information. The chronological processing of the collected network information to obtain the network status image includes: formatting the network element status information, link status information, and network management interface status information according to a required format to obtain formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information; splicing the formatted network topology information, formatted network element status information, formatted link status information, and formatted network management interface status information according to the generation time of the network information itself to obtain spliced information; and image processing of the spliced information using a screenshot or information snapshot method to generate the network status image. The analysis module is configured to input the network state image into the target convolutional neural network for analysis to obtain network situation information.
8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the network potential analysis method as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the network potential analysis method as described in any one of claims 1-6.