Road network performance prediction method and device, electronic equipment, storage medium and computer program product

By building network diagrams and feature aggregation processing, using time series and abnormal prediction models, the problem of inefficient supervision of network equipment is solved, the network performance is predicted and fault prevention is achieved, the troubleshooting process is simplified, and the detection accuracy is improved. efficiency.

CN119094371APending Publication Date: 2024-12-06JIANGSU TRAFFIC CONTROL DIGITAL TRANSPORTATION RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411227484.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the prior art, the supervision of network equipment relies on manual remote login inspection, which is inefficient and difficult to quickly and accurately detect a large number of network equipment on highways. The troubleshooting process is cumbersome, and the accuracy and efficiency are difficult to ensure.

Method used

By building a network diagram, the network performance data in the historical time period is obtained, feature aggregation is performed, and the time series prediction model and abnormal prediction model are used to predict future network performance, prevent failures in advance, and optimize network regulation.

Benefits of technology

It realizes advance prediction of network performance, improves fault prevention efficiency, simplifies the troubleshooting process, and improves the accuracy and efficiency of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119094371A_ABST
    Figure CN119094371A_ABST
Patent Text Reader

Abstract

The invention provides a road network performance prediction method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: constructing a corresponding network graph by taking network nodes in a road network to be detected as graph nodes; a plurality of groups of network performance data in a historical time period are obtained, each group of network performance data comprises network performance data of each network node in the road network to be tested corresponding to one historical time node, and the historical time period comprises a plurality of historical time nodes; performing feature aggregation processing on the network performance data of each graph node in the network graph for each historical time node to obtain an aggregation feature corresponding to at least one network node; and predicting the predicted network performance of at least one network node in the road network to be measured in the future time period based on the at least one aggregation feature corresponding to each historical time node.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to network technology, and in particular to a method, device, electronic device, storage medium and computer program product for predicting road network performance. Background Art

[0002] Currently, the supervision of network equipment is carried out through manual remote logging into each network device to troubleshoot problems. The disadvantage of this primitive inspection method is that it is inefficient and the fault is not checked until after the problem occurs, making it difficult to achieve rapid and accurate detection of a large number of network devices on highways. On the other hand, after manual detection of the cause of the fault, the result is recorded in a document and reported for repair. The overall process is cumbersome, and accuracy and work efficiency are difficult to guarantee. Summary of the invention

[0003] The embodiments of the present application provide a road network performance prediction method, device, electronic device and computer-readable storage medium, which can predict network performance in advance, thereby preventing failures and improving efficiency.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The present application provides a method for predicting road network performance, including:

[0006] Taking the network nodes in the road network to be tested as graph nodes, the corresponding network graph is constructed;

[0007] Respectively obtain multiple groups of network performance data in historical time periods, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes;

[0008] For each of the historical time nodes, feature aggregation processing is performed on the network performance data of each graph node in the network graph to obtain an aggregate feature corresponding to at least one network node;

[0009] Based on at least one aggregate feature corresponding to each historical time node, a predicted network performance of at least one network node in the road network to be tested in a future time period is predicted.

[0010] In the above solution, the predicting of the network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregate feature corresponding to each historical time node includes:

[0011] Using a time series prediction model, based on at least one aggregation feature corresponding to each historical time node, predict the predicted aggregation feature of at least one network node corresponding to multiple future time nodes in a future time period;

[0012] The predicted aggregated features are determined as predicted network performance of the corresponding network node at the corresponding future time node.

[0013] In the above scheme, the method further comprises:

[0014] Analyzing a network performance change trend of at least one network node according to the predicted network performance of at least one network node in the road network to be tested in a future time period;

[0015] Based on the network performance change trend, network adjustment is performed on the road network to be tested.

[0016] In the above solution, the at least one network node includes all network nodes in the road network to be tested, or the at least one network node includes at least one target network node, and the target network node is determined by:

[0017] Determine node characteristics of each graph node in the network graph respectively;

[0018] Determine a graph node whose node characteristics in the network graph reach a target threshold as a target graph node;

[0019] A network node corresponding to the target graph node is determined as the target network node.

[0020] In the above scheme, the method further comprises:

[0021] By utilizing the abnormal prediction model and based on the predicted network performance, abnormal prediction is performed on the corresponding network nodes to obtain corresponding prediction results.

[0022] In the above scheme, the method further comprises:

[0023] Obtain abnormal network performance characteristics;

[0024] Determining a similarity between the predicted network performance and the abnormal network performance characteristics;

[0025] If the similarity reaches a similarity threshold, it is determined that an abnormality occurs in the network node corresponding to the predicted network performance at a corresponding future time node.

[0026] The present application provides a road network performance prediction device, including:

[0027] A construction module is used to construct a corresponding network graph using the network nodes in the road network to be tested as graph nodes;

[0028] An acquisition module, used to respectively obtain multiple groups of network performance data in a historical time period, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes;

[0029] An aggregation processing module, used for performing feature aggregation processing on the network performance data of each graph node in the network graph for each of the historical time nodes, to obtain an aggregation feature corresponding to at least one network node;

[0030] The prediction module is used to predict the predicted network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregation feature corresponding to each historical time node.

[0031] An embodiment of the present application provides an electronic device, including:

[0032] A memory for storing executable instructions;

[0033] The processor is used to implement the road network performance prediction method provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0034] An embodiment of the present application provides a computer-readable storage medium storing executable instructions for causing a processor to execute and implement the road network performance prediction method provided in the embodiment of the present application.

[0035] An embodiment of the present application provides a computer program product storing a computer program for implementing the road network performance prediction method provided in the embodiment of the present application when executed by a processor.

[0036] The embodiment of the present application constructs a corresponding network graph by taking the network nodes in the road network to be tested as graph nodes and obtains multiple groups of network performance data in historical time periods respectively, and then performs feature aggregation processing on the network performance data of each graph node in the network graph for each historical time node respectively, to obtain an aggregate feature corresponding to at least one network node, and predicts the predicted network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregate feature corresponding to each historical time node, so that the network performance can be predicted in advance, thereby preventing failures and improving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is an optional structural diagram of the road network performance prediction system 100 provided in the embodiment of the present application;

[0038] Figure 2 is an optional structural diagram of an electronic device 200 provided in an embodiment of the present application;

[0039] Figure 3 It is an optional flow chart of the road network performance prediction method provided in the embodiment of the present application;

[0040] Figure 4is an optional topological structure diagram of the road network to be tested provided in an embodiment of the present application;

[0041] Figure 5 is an optional schematic diagram of a road network to be tested provided in an embodiment of the present application;

[0042] Figure 6 It is an optional schematic diagram of the network diagram provided in the embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0044] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0045] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0047] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0048] 1) Zabbix SerVer, an open source distributed monitoring system.

[0049] First, the road network performance prediction system provided by the embodiment of the present application is described. Figure 1 , Figure 1It is an optional structural diagram of the road network performance prediction system 100 provided in the embodiment of the present application. In order to support a road network performance prediction application, the performance monitoring device 101 is connected to the road network to be tested 103 through the network 102. In some embodiments, the performance monitoring device 101 can be a terminal or a server. Among them, the terminal can be a laptop, a tablet computer, a desktop computer and a smart phone, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network) services, and big data and artificial intelligence platforms. The network 102 can be a wide area network or a local area network, or a combination of the two. The performance monitoring device 101 and the road network to be tested 103 can be directly or indirectly connected by wired or wireless communication, which is not limited in the embodiment of the present application.

[0050] Next, the electronic device provided in the embodiment of the present application for implementing the above-mentioned road network performance prediction method is described, see Figure 2 , Figure 2 is an optional structural diagram of an electronic device 200 provided in an embodiment of the present application. In practical applications, the electronic device 200 can be implemented as Figure 1 The performance monitoring device 101 in the embodiment of the present application is described below. The electronic device for implementing the road network performance prediction method of the embodiment of the present application is described below.

[0051] Figure 2 The electronic device 200 shown includes: at least one processor 201, a memory 205, at least one network interface 202 and a user interface 203. The various components in the electronic device 200 are coupled together via a bus system 204. It is understood that the bus system 204 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 204 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 204 is not described in detail. Figure 2 Various buses are labeled as bus system 204 .

[0052] The processor 201 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0053] The user interface 203 includes one or more output devices 2031 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 203 also includes one or more input devices 2032, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0054] The memory 205 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 205 may optionally include one or more storage devices that are physically remote from the processor 201.

[0055] The memory 205 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 205 described in the embodiment of the present application is intended to include any suitable type of memory.

[0056] In some embodiments, the memory 205 can store data to support various operations. Examples of these data include programs, modules, and data structures or subsets or supersets thereof. In the embodiment of the present application, the memory 205 stores an operating system 2051, a network communication module 2052, a presentation module 2053, an input processing module 2054, and a road network performance prediction device 2055; specifically,

[0057] Operating system 2051, including system programs for processing various basic system services and performing hardware-related tasks, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0058] A network communication module 2052, for reaching other computing devices via one or more (wired or wireless) network interfaces 202, exemplary network interfaces 202 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB);

[0059] a presentation module 2053 for enabling presentation of information (e.g., a user interface for operating peripherals and displaying content and information) via one or more output devices 2031 (e.g., a display screen, a speaker, etc.) associated with the user interface 203;

[0060] The input processing module 2054 is used to detect one or more user inputs or interactions from one of the one or more input devices 2032 and translate the detected inputs or interactions.

[0061] In some embodiments, the road network performance prediction device provided in the embodiments of the present application can be implemented in software. Figure 2 The road network performance prediction device 2055 stored in the memory 205 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: a construction module 20551, an acquisition module 20552, an aggregation processing module 20553 and a prediction module 20554. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0062] In other embodiments, the road network performance prediction device provided in the embodiments of the present application can be implemented in hardware. As an example, the road network performance prediction device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the road network performance prediction method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0063] The road network performance prediction method provided in the embodiment of the present application will be explained in combination with the exemplary application and implementation of the terminal provided in the embodiment of the present application.

[0064] See also Figure 3 , Figure 3 is an optional flow chart of the road network performance prediction method provided in the embodiment of the present application, which will be combined with Figure 3 The steps shown are explained.

[0065] Step 301, using the network nodes in the road network to be tested as graph nodes, constructing a corresponding network graph;

[0066] Step 302, respectively obtaining multiple groups of network performance data in a historical time period, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes;

[0067] Step 303, for each of the historical time nodes, perform feature aggregation processing on the network performance data of each graph node in the network graph to obtain an aggregate feature corresponding to at least one network node;

[0068] Step 304: predicting the predicted network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregated feature corresponding to each historical time node.

[0069] In actual implementation, the road network to be tested includes network nodes set up in the roads within the scope of the test area. Here, the road can be a highway. The network node is a network system set up at a toll station, a section center and / or a service area on the highway. Here, the network system includes at least one network device, and the network device can be a switch, a router, an optical box, a customer premise equipment (CPE), a firewall, a service terminal and a server, etc. Figure 4 , Figure 4 It is an optional topological structure diagram of the road network to be tested provided by the embodiment of the present application. Here, the road network includes 7 network nodes, namely network nodes 401~407. Among them, network node 401 is located at the toll station, which includes network devices such as business computer 4011 and switch 4012. Network nodes 403 and 404 are located on the server. Among them, network node 403 includes network devices such as switch 4031, POS machine 4032, retail equipment 4033, refueling equipment 40334, monitoring equipment 4035 and business office equipment 4036. Network nodes 405~407 can be a service platform located in the center of the road section. Among them, network node 405 is an XX system platform, which includes network devices such as a first firewall, a border router, a second firewall, vxnet, XX host, OA application host and XX system host.

[0070] In actual implementation, the network nodes in the road network to be tested are used as graph nodes to construct a corresponding network graph. Here, the connection relationship between each graph node in the graph network corresponds to the connection relationship between the network nodes in the road network to be tested in the road. Figure 5 and Figure 6 , Figure 5 is an optional schematic diagram of a road network to be tested provided in an embodiment of the present application. Figure 6is an optional schematic diagram of a network diagram provided in an embodiment of the present application. Here, the road network to be tested includes 10 network nodes, namely network nodes 501 to 510. There are sections of corresponding lengths between the network nodes. For example, there is a 38km section between network node 501 and network node 502. Figure 5 The network graph includes 10 graph nodes, namely, graph nodes A to J. Here, the edges of the network graph have corresponding weights, and the weight of each edge is positively correlated with the length of the corresponding road section. For example, the weight of the edge between node A and node B is w1, and the weight between node C and node D is w2, then w1 / w2=38 / 32.

[0071] In actual implementation, multiple groups of network performance data in the historical time period are obtained respectively. Here, the historical time period includes multiple historical time nodes, and each group of network performance data includes the network performance data of each network node in the road network to be tested corresponding to a historical time node. Here, the network performance data may include at least one of the following: network traffic, bandwidth utilization, delay and packet loss rate. In the embodiment of the present application, the Zabbix Server can collect network device data in the form of SNMP, ZabbixAgent, Ping, and port monitoring. Specifically, the Ping and SNMP protocols are used to monitor whether the network device is online and obtain valid data, including the device serial number (SN, Serial Number), device name, device port, interface receiving traffic, interface sending traffic, receiving traffic, sending traffic, and sending and receiving time. After the network device traffic, performance indicators, connection and other data are collected, the original data needs to be cleaned and formatted, including special processing of abnormal data, traffic unit conversion, data not obtained messages and other multi-dimensional data processing. Specifically, through mean filtering, each data point is replaced with the average value of the data points in its surrounding neighborhood to smooth the data and remove noise to improve data quality. The data is then stored in a distributed big data storage system, and when needed, the corresponding data is directly obtained from the distributed big data storage system.

[0072] In actual implementation, feature aggregation processing is performed on the network performance data of each graph node in the network diagram for each historical time node, and an aggregate feature corresponding to at least one network node is obtained. It should be understood that when the feature aggregation processing is performed, the aggregation is performed based on the connection relationship between the nodes in the network diagram. Exemplarily, for graph node E, aggregation processing can be performed from the outside to the inside based on the graph nodes in the network diagram that have a direct or indirect connection relationship with graph node E, to obtain the aggregate feature corresponding to graph node E. Next, based on at least one aggregate feature corresponding to each historical time node, the predicted network performance of at least one network node in the road network to be tested in the future time period is predicted.

[0073] In an embodiment of the present application, by taking the network nodes in the road network to be tested as graph nodes, constructing a corresponding network graph and obtaining multiple groups of network performance data in the historical time period respectively, and then performing feature aggregation processing on the network performance data of each graph node in the network graph for each historical time node respectively, obtaining the aggregation feature corresponding to at least one network node, and predicting the predicted network performance of at least one network node in the road network to be tested in the future time period based on at least one aggregation feature corresponding to each historical time node, the network performance can be predicted in advance, thereby preventing failures and improving efficiency. In some embodiments, the prediction of the network performance of at least one network node in the road network to be tested in the future time period based on at least one aggregation feature corresponding to each historical time node includes: using a time series prediction model, based on at least one aggregation feature corresponding to each historical time node, predicting the predicted aggregation feature of at least one network node corresponding to multiple future time nodes in the future time period; determining the predicted aggregation feature as the predicted network performance of the corresponding network node at the corresponding future time node.

[0074] In actual implementation, the time series prediction model can be an autoregressive moving average model (ARMA), which is used to describe the autocorrelation structure and moving average structure of time series data. The ARMA model is shown in formula (1):

[0075]

[0076] Among them, X t is the observed value at time point t, ∈ t is the white noise error term, p and q represent the orders of autoregression and moving average, respectively.

[0077] In the embodiment of the present application, the time series prediction model can be obtained by pre-training. Specifically, at least one sample aggregation feature corresponding to a sample time node within a sample time period can be obtained, a training sample can be constructed based on the sample time node and the sample aggregation feature, and the time series prediction model can be trained by the training sample to obtain a trained time series prediction model.

[0078] In some embodiments, the method further includes: analyzing a network performance change trend of at least one network node in the road network to be tested based on the predicted network performance of at least one network node in the road network to be tested in a future time period; and performing network adjustments on the road network to be tested based on the network performance change trend.

[0079] In actual implementation, the network performance change trend of at least one network node is determined based on the predicted network performance of at least one network node in the future application period. Here, a corresponding network performance change graph can be generated according to the time sequence to characterize the network performance change trend. Based on the difference between the network performance change trend and the target change trend, network adjustment is performed on the road network to be tested. Here, the target change trend is a pre-set ideal trend for the normal operation of the road network. The network adjustment of the road network to be tested can make the network performance change trend close to the target change trend by adjusting the traffic, bandwidth, etc. of each network device. Specifically, the difference between the network performance change trend and the target change trend can be made less than or equal to the difference threshold.

[0080] In some embodiments, the at least one network node includes all network nodes in the road network to be tested, or the at least one network node includes at least one target network node, and the target network node is determined by: determining the node characteristics of each graph node in the network graph respectively; determining the graph node whose node characteristics in the network graph reach the target threshold as the target graph node; and determining the network node corresponding to the target graph node as the target network node.

[0081] In actual implementation, at least one network node in step 303 may include all network nodes in the road network to be tested, or may include at least one target network node. Here, the target network node is selected from multiple graph nodes in the network graph. Specifically, the node features of each graph node in the network graph can be determined respectively, and the graph node whose node features in the network graph reach the target threshold is determined as the target graph node, and the network node corresponding to the target graph node is determined as the target network node. Here, the node feature includes at least one of the following: degree, betweenness centrality and proximity centrality. In the embodiment of the present application, the higher the degree value of the graph node, the greater the traffic flow of the graph node, the greater the betweenness centrality of the graph node, the more important the hub node, and the greater the proximity centrality of the graph node. The graph node is more critical for the flow distribution point. In the embodiment of the present application, the target threshold corresponds to the node feature, that is, if the node feature includes the degree, the target threshold includes the degree threshold, if the node feature includes the betweenness centrality, the target threshold includes the betweenness centrality threshold, and if the node feature includes the proximity centrality, the target threshold includes the proximity centrality threshold. It should be understood that if the node features include multiple types, then the multiple node features of the graph node are determined separately and compared with the corresponding target thresholds respectively. As long as one of the node features reaches the corresponding target threshold, the graph node is determined to be the target graph node. Exemplarily, if the node features include degree, betweenness centrality and closeness centrality, the degree, betweenness centrality and closeness centrality of graph node A are calculated respectively to obtain the corresponding degree value A, betweenness centrality A and closeness centrality A. If one of the degree value A, betweenness centrality A and closeness centrality A reaches the corresponding target threshold, then graph node A is determined to be the target graph node. For example: if the degree value A does not reach the degree threshold, the betweenness centrality A does not reach the betweenness centrality threshold, and the closeness centrality A reaches the closeness centrality threshold, then graph node A is determined to be the target graph node.

[0082] Next, the network node corresponding to the target graph node is determined as the target network node. The important target network nodes are selected by node features, and feature aggregation and corresponding performance prediction are performed on the target network nodes, which reduces processing tasks and saves computing resources.

[0083] In some embodiments, the method further includes: utilizing an abnormality prediction model to perform abnormality prediction on corresponding network nodes based on the predicted network performance to obtain corresponding prediction results.

[0084] In actual implementation, the anomaly prediction model can be a classification model. Specifically, the eigenvalues ​​of the linear combination can be passed to the logic function through the logistic regression model, the input can be mapped to a probability value between 0 and 1, and then the classification prediction can be performed according to the threshold, the network fault can be automatically diagnosed and classified, and the network anomaly can be detected by using the isolated forest anomaly monitoring algorithm, including network jitter, network interruption, abnormally high or low network, to quickly locate the cause of the fault. In some embodiments, the device logs and device event data of each network device can also be obtained in real time, and the anomaly prediction model can be used to identify anomalies based on the device logs and device event data to obtain anomaly identification results to achieve real-time network fault detection.

[0085] In some embodiments, the method further includes: obtaining abnormal network performance characteristics; determining the similarity between the predicted network performance and the abnormal network performance characteristics; if the similarity reaches a similarity threshold, determining that the network node corresponding to the predicted network performance has an abnormality at a corresponding future time node.

[0086] In actual implementation, the similarity between the predicted network performance and the abnormal network performance characteristics can be determined, and based on the similarity, it is determined whether the network node will be abnormal at the corresponding future time node. If the similarity reaches the similarity threshold, it is determined that the network node will be abnormal at the future time node, otherwise it will not be abnormal. Using similarity to judge abnormalities can improve judgment efficiency.

[0087] In some embodiments, data analysis can also be used to identify abnormal traffic and attack patterns in the network, and an abnormal monitoring model can be established. The Z-score method can be used to identify abnormal values ​​based on the deviation of data points from their mean values. If the data follows a normal distribution, abnormal network behavior can be identified. In some embodiments, data growth trends can also be analyzed to predict future capacity requirements for expansion. In some embodiments, the effect of abnormal prediction or abnormal detection can be improved by integrating learning models, adjusting thresholds, and dynamically adjusting algorithm parameters, etc., to establish a real-time monitoring system, capture new abnormal patterns in a timely manner, and continuously optimize the model to reduce false alarm rates and improve detection accuracy.

[0088] In some embodiments, a GIS map is used to indicate the road network map to be tested. The location information of all network nodes is marked on the map according to the coordinate information. By clicking on the corresponding point information, all current information, including alarms, resources, response time, traffic, etc., is displayed. Different colors are presented according to the degree of equipment failure to identify the faulty equipment. Furthermore, core resource information such as the total number of resources, resource distribution, operating conditions, and abnormal alarms can also be displayed for the network operation and maintenance center and the command and dispatch center, so that administrators and operation and maintenance personnel can intuitively understand the operation of the network and take timely action. In addition, the status and location of network failures, events, and alarms can also be displayed to help administrators quickly locate and solve problems.

[0089] The following is a description of an exemplary structure of the road network performance prediction device 2055 provided in the embodiment of the present application implemented as a software module. In some embodiments, Figure 2 As shown, the software modules stored in the road network performance prediction device 2055 of the memory 205 may include:

[0090] A construction module 20551 is used to construct a corresponding network graph using network nodes in the road network to be tested as graph nodes;

[0091] The acquisition module 20552 is used to respectively obtain multiple groups of network performance data in a historical time period, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes;

[0092] Aggregation processing module 20553, used for performing feature aggregation processing on the network performance data of each graph node in the network graph for each of the historical time nodes, to obtain an aggregate feature corresponding to at least one network node;

[0093] The prediction module 20554 is used to predict the predicted network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregation feature corresponding to each historical time node.

[0094] In some embodiments, the prediction module 20554 is also used to use a time series prediction model to predict the predicted aggregate feature of at least one network node corresponding to multiple future time nodes in a future time period based on at least one aggregate feature corresponding to each historical time node; and determine the predicted aggregate feature as the predicted network performance of the corresponding network node at the corresponding future time node.

[0095] In some embodiments, the device also includes: an adjustment module, which is used to analyze the network performance change trend of at least one network node in the road network to be tested according to the predicted network performance of at least one network node in the road network to be tested in a future time period; and perform network adjustment on the road network to be tested based on the network performance change trend.

[0096] In some embodiments, the at least one network node includes all network nodes in the road network to be tested, or the at least one network node includes at least one target network node, and the target network node is determined by: determining the node characteristics of each graph node in the network graph respectively; determining the graph node whose node characteristics in the network graph reach the target threshold as the target graph node; and determining the network node corresponding to the target graph node as the target network node.

[0097] In some embodiments, the device further includes: an abnormality prediction module, which is used to use an abnormality prediction model to perform abnormality prediction on corresponding network nodes based on the predicted network performance to obtain corresponding prediction results.

[0098] In some embodiments, the device also includes: an abnormal prediction module, used to obtain abnormal network performance characteristics; determine the similarity between the predicted network performance and the abnormal network performance characteristics; if the similarity reaches a similarity threshold, determine that the network node corresponding to the predicted network performance has an abnormality at a corresponding future time node.

[0099] It should be noted that the description of the device of the embodiment of the present application is similar to the description of the above-mentioned method embodiment, and has similar beneficial effects as the method embodiment, so it will not be repeated.

[0100] The embodiment of the present application provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the road network performance prediction method described in the embodiment of the present application.

[0101] An embodiment of the present application provides a computer-readable storage medium storing executable instructions, wherein executable instructions are stored. When the executable instructions are executed by a processor, the processor will execute the road network performance prediction method provided in the embodiment of the present application.

[0102] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or it may be various devices including one or any combination of the above memories.

[0103] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0104] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0105] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0106] In summary, the fault prediction efficiency can be improved through the embodiments of the present application.

[0107] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A road network performance prediction method, characterized in that: include: Taking the network nodes in the road network to be tested as graph nodes, the corresponding network graph is constructed; Respectively obtain multiple groups of network performance data in historical time periods, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes; For each of the historical time nodes, feature aggregation processing is performed on the network performance data of each graph node in the network graph to obtain an aggregate feature corresponding to at least one network node; Based on at least one aggregate feature corresponding to each historical time node, a predicted network performance of at least one network node in the road network to be tested in a future time period is predicted.

2. The method according to claim 1, characterized in that The predicting, based on at least one aggregate feature corresponding to each historical time node, the network performance of at least one network node in the road network to be tested in a future time period includes: Using a time series prediction model, based on at least one aggregation feature corresponding to each historical time node, predict the predicted aggregation feature of at least one network node corresponding to multiple future time nodes in a future time period; The predicted aggregated features are determined as predicted network performance of the corresponding network node at the corresponding future time node.

3. The method according to claim 1, characterized in that The method further comprises: Analyzing a network performance change trend of at least one network node according to the predicted network performance of at least one network node in the road network to be tested in a future time period; Based on the network performance change trend, network adjustment is performed on the road network to be tested.

4. The method according to claim 1, characterized in that: The at least one network node includes all network nodes in the road network to be tested, or the at least one network node includes at least one target network node, and the target network node is determined in the following manner: Determine node characteristics of each graph node in the network graph respectively; Determine a graph node whose node characteristics in the network graph reach a target threshold as a target graph node; A network node corresponding to the target graph node is determined as the target network node.

5. The method according to claim 1, characterized in that: The method further comprises: By utilizing the abnormal prediction model and based on the predicted network performance, abnormal prediction is performed on the corresponding network nodes to obtain corresponding prediction results.

6. The method according to claim 1, characterized in that The method further comprises: Obtain abnormal network performance characteristics; Determining a similarity between the predicted network performance and the abnormal network performance characteristics; If the similarity reaches a similarity threshold, it is determined that an abnormality occurs in the network node corresponding to the predicted network performance at a corresponding future time node.

7. A road network performance prediction device, characterized in that: include: A construction module is used to construct a corresponding network graph using the network nodes in the road network to be tested as graph nodes; An acquisition module, used to respectively obtain multiple groups of network performance data in a historical time period, each group of network performance data includes network performance data of each network node in the road network to be tested corresponding to a historical time node, and the historical time period includes multiple historical time nodes; An aggregation processing module, used for performing feature aggregation processing on the network performance data of each graph node in the network graph for each of the historical time nodes, to obtain an aggregation feature corresponding to at least one network node; The prediction module is used to predict the predicted network performance of at least one network node in the road network to be tested in a future time period based on at least one aggregation feature corresponding to each historical time node.

8. An electronic device, characterized in that: include: A memory for storing executable instructions; The processor is used to implement the road network performance prediction method described in any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to implement the road network performance prediction method described in any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that A computer program is stored, which is used to implement the road network performance prediction method described in any one of claims 1 to 6 when executed by a processor.