A 5G communication engineering communication state intelligent detection method and system

Abstract

This invention relates to the field of communication status detection technology, specifically to an intelligent method and system for detecting the communication status of 5G communication projects. It includes dividing the network transmission into segments and deploying multi-segment node detection probes; establishing a communication fault analysis model to calculate the fault status of each network element node. This invention achieves multi-channel, multi-interface, and comprehensive detection of the communication status of 5G communication projects by dividing the network transmission into segments and deploying multi-segment node detection probes. It collects network communication status data from different locations across multiple segments, and simultaneously obtains parameter data relationships between different nodes through the established communication fault analysis model. It utilizes parameter values ​​fed back from probes in key deployment nodes to classify event types and match parameter value trends, and, in conjunction with a node status calculation function, calculates the corresponding fault score in real time. This allows for real-time fault prediction of the current faulty node from multiple perspectives, avoiding the limitations of prediction based on single-node data feedback and ensuring prediction effectiveness.

Description

Technical Field

[0001] This invention relates to the field of communication status detection technology, and more specifically, to a method and system for intelligent detection of communication status in 5G communication engineering. Background Technology

[0002] In the current era of 5G communication networks evolving towards ultra-dense networking, cloud-native architecture, and diversified services, real-time and accurate detection of network communication status has become a core cornerstone for ensuring user experience, achieving network autonomy, and fulfilling service level agreements. Traditional and current mainstream detection methods, especially those combining active probes and passive data collection, often suffer from non-linear, indirect, and lagging interactions between nodes in complex service-oriented architectures. For example, an increase in packet loss rate at an edge UPF (User Plane Function) could be caused by a routing policy change at another non-directly connected node in the transport network or by signaling overload on the core network control plane. While a basic framework for network observability has been established, a fundamental methodological limitation becomes increasingly apparent when dealing with the inherent complexities of 5G networks. This leads to the following problems with existing 5G communication engineering communication status detection methods:

[0003] First, the false alarm and false negative rates are high: static thresholds cannot detect dynamic changes in the overall network load. For example, when the entire network undergoes a large-scale service migration, multiple node indicators may simultaneously exhibit "abnormal" fluctuations, but this is normal operation rather than a fault, and traditional methods are prone to generating widespread false alarms. Conversely, a slowly deteriorating, latent fault manifested through slight degradation of multiple adjacent nodes (such as slowly increasing interference) may be missed because it does not trigger the threshold of a single node.

[0004] Secondly, when alarms are generated, the system can only list all nodes with abnormal metrics, but cannot reveal the causal or strong correlation between these anomalies. Operations personnel face an "alarm storm," requiring extensive experience to manually analyze the topology and logs to deduce the initial source of the fault, which is inefficient and highly dependent on expert experience.

[0005] To address the aforementioned issues, there is an urgent need for an intelligent detection method for the communication status of 5G communication engineering that performs correlation analysis on node parameters. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for intelligent detection of communication status in 5G communication engineering, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, one of the objectives of this invention is to provide an intelligent detection method for the communication status of 5G communication engineering, comprising the following steps:

[0008] S1. Collect the communication routes of 5G communication projects, divide the network transmission segments, and deploy multi-segment node detection probes;

[0009] S2. Set the detection event feedback time point and collect events from the detection probes in different sections at regular intervals;

[0010] S3. Perform phased processing based on the event status;

[0011] The collected event types are categorized and classified.

[0012] Perform node association and direction binding on event parameter values;

[0013] S4. Establish a communication fault analysis model ;

[0014] in, Represents a set of nodes. Indicating network transmission segments Each network element node;

[0015] This represents the set of network element node failure trends. This indicates the failure trend of Z network element nodes;

[0016] Denotes the set of edges. express The connection relationship between adjacent network element nodes;

[0017] Represents a set of compatible pathways. express Fault propagation paths of different network element nodes;

[0018] The node state calculation function combines the node set, the network element node fault trend set, the edge set, and the compatible path set to calculate the fault state of each network element node.

[0019] S5. Based on the upload event status of different probes, combined with the communication fault analysis model. Output the network communication status prediction results.

[0020] As a further improvement to this technical solution, the network transmission segments divided in S1 include a terminal segment, an access segment, a wireless segment, a core network segment, and a service segment.

[0021] As a further improvement to this technical solution, the method for deploying multi-segment node detection probes in S1 includes the following steps:

[0022] S1.1. Based on the segmentation results, mark the devices in each segment with serial numbers and obtain the connection status between adjacent devices;

[0023] S1.2 Locate the key deployment nodes in each section and deploy the detection probes according to the task type of the key deployment nodes;

[0024] S1.3 Locate the key deployment nodes corresponding to each group of data transmission routes based on the network data transmission routes.

[0025] As a further improvement to this technical solution, the deployment method of the key deployment node in S1.3 is fault-compatible deployment.

[0026] As a further improvement to this technical solution, the method for performing node association and directional binding on event parameter values ​​in S3 includes the following steps:

[0027] S3.1 Classify the events reported by the probes deployed in each key deployment node by type;

[0028] S3.2 Match fault data of faulty equipment under faulty conditions;

[0029] S3.3 Collect fault data to show the trend of event parameter values ​​and the range of parameter value changes in the device;

[0030] S3.4. Bind the faulty equipment, the fault data display equipment, the trend of event parameter values, and the range of parameter value changes to establish a node association trend database.

[0031] As a further improvement to this technical solution, the calculation method of the node state calculation function in S4 includes the following steps:

[0032] S4.1 Define the numerical range of regular event parameters for each key deployment node and establish a set of regular numerical ranges. ;

[0033] S4.2 Collect the event parameter values ​​of probe detection for each key deployment node according to the set detection event feedback time point;

[0034] S4.3, through node set Identify the current critical deployment node sequence number, in conjunction with a standard numerical range set. Perform numerical mapping;

[0035] Critical deployment nodes whose detected event parameter values ​​are within the normal event parameter value range are marked as normal critical deployment nodes;

[0036] Critical deployment nodes whose detected event parameter values ​​exceed the normal range are marked as abnormal critical deployment nodes;

[0037] S4.4, Associative Edge Set Locate the transmission route of the currently abnormal critical deployment node and obtain the connection status between the abnormal critical deployment node and the corresponding adjacent network element node;

[0038] S4.5, Set of compatible pathways Locate the fault propagation path of the currently abnormal critical deployment node and obtain the faulty nodes associated with the abnormal critical deployment node;

[0039] S4.6. Combine the event parameter values ​​of the abnormal critical deployment nodes corresponding to the faulty nodes at the same time point with the network element node fault trend set. Perform mapping matching and mark it as a fault event parameter;

[0040] S4.7 Obtain the corresponding fault event parameter values. Collect the conventional parameter values ​​of the fault event parameters at the previous time point. By combining the historical numerical parameter variation range, a fraction of the unit change is calculated for each event parameter. planning;

[0041] S4.8 Calculate the fault score for the fault event parameter values ​​at different time points. ;

[0042] S4.9, Obtain the fault score from the parameter values ​​of each fault event. The average value is used as the real-time fault score in the final output.

[0043] As a further improvement to this technical solution, the fault score of the fault event parameter value in S4.7 is... The calculation algorithm is as follows:

[0044] ;

[0045] in The initial fault score, For units of change, fractions The values ​​are the parameters for the fault event. These are standard parameter values.

[0046] As a further improvement to this technical solution, the unit change fraction in S4.7 It is negatively correlated with the magnitude of the change in the event parameter value.

[0047] As a further improvement to this technical solution, the network communication status prediction result output in S5 includes event type, fault device number, fault data manifestation device number, and fault event parameter value. And real-time fault scores.

[0048] The second objective of this invention is to provide a system for implementing an intelligent detection method for the communication status of 5G communication engineering, including a multi-segment probe deployment model, an event type processing module, a communication fault analysis model, and a result output module;

[0049] The multi-segment probe deployment model is used to collect communication routes of 5G communication projects, divide network transmission segments, deploy multi-segment node detection probes, test and detect different types of devices through the CPU core module, and configure multiple test channels to adapt to the connection methods of different devices, including 5G test channels, WI-Fi test channels and Ethernet test channels.

[0050] The event type processing module is used to classify the events reported by probes deployed in each key deployment node, and to perform node association trend binding on the event parameter values. It binds faulty devices, fault data display devices, event parameter value change trends, and parameter value change ranges to establish a node association trend database.

[0051] The communication fault analysis model is used to calculate the fault status of each network element node by combining the node set, the network element node fault trend set, the edge set, and the compatible path set.

[0052] The result output module is based on the upload event status of different probes, in conjunction with a communication fault analysis model. Output the network communication status prediction results.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] This intelligent detection method and system for 5G communication engineering communication status divides the network transmission area and deploys multi-segment node detection probes to achieve multi-channel, multi-interface, and comprehensive detection of the communication status of 5G communication engineering. It collects network communication status data from different locations in multiple segments, and obtains parameter data relationships between different nodes through an established communication fault analysis model. It uses the parameter values ​​fed back by probes in key deployment nodes to classify event types and match parameter value trends. Combined with the node status calculation function, it calculates the corresponding fault score in real time, and performs real-time fault prediction of the current fault node from multiple perspectives, avoiding the limitations of prediction based on single node data feedback and ensuring prediction effectiveness. Attached Figure Description

[0055] Figure 1This is a diagram illustrating the overall method steps of the present invention;

[0056] Figure 2 This is a schematic diagram simulating the network transmission segmentation of the present invention;

[0057] Figure 3 This is a step diagram of the multi-segment node detection probe deployment method of the present invention;

[0058] Figure 4 This is a flowchart illustrating the steps of the method for binding node associations to event parameter values ​​according to the present invention.

[0059] Figure 5 This is a diagram illustrating the calculation steps of the node state calculation function of the present invention.

[0060] Figure 6 This is a block diagram of the overall system structure of the present invention. Detailed Implementation

[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] Please see Figure 1 As shown, one of the objectives of this invention is to provide an intelligent detection method for the communication status of 5G communication engineering, comprising the following steps:

[0063] S1. Collect the communication routes of 5G communication projects, divide the network transmission segments, and deploy multi-segment node detection probes;

[0064] S2. Set the detection event feedback time point and collect events from the detection probes in different sections at regular intervals;

[0065] S3. Perform phased processing based on the event status;

[0066] The collected event types are categorized and classified.

[0067] Perform node association and direction binding on event parameter values;

[0068] S4. Establish a communication fault analysis model ;

[0069] in, Represents a set of nodes. Indicating network transmission segments Each network element node;

[0070] This represents the set of network element node failure trends. This indicates the failure trend of Z network element nodes;

[0071] Denotes the set of edges. express The connection relationship between adjacent network element nodes;

[0072] Represents a set of compatible pathways. express Fault propagation paths of different network element nodes;

[0073] The node state calculation function combines the node set, the network element node fault trend set, the edge set, and the compatible path set to calculate the fault state of each network element node.

[0074] S5. Based on the upload event status of different probes, combined with the communication fault analysis model. Output the network communication status prediction results.

[0075] The details are as follows:

[0076] First, this solution detects the communication status of 5G communication projects through test probes. These probes have a built-in CPU core module, integrating CPU, memory, and ROM. Multiple test channels (5G, Wi-Fi, and Ethernet) are configured to accommodate testing at different locations. Since the communication routes of 5G communication projects involve different communication devices and software, and the connection statuses between these devices vary, a single test probe cannot perform comprehensive testing of the entire communication route. Distributed testing is required based on the communication route. Therefore, appropriate locations are selected for test probe deployment to ensure that the deployed test probes can comprehensively test the entire communication route of the 5G communication project.

[0077] like Figure 2 As shown, this solution divides network transmission segments by collecting the communication routes of 5G communication projects. This is because a complete communication route generally includes client terminals, AR, routers, CPEs, 5G base stations, user plane network function equipment, and server nodes, such as... Figure 2 As shown, the network transmission segment is divided into terminal segment, access segment, wireless segment, core network segment and service segment according to the service path and node distribution. Each segment consists of multiple similar node devices. The operating status of each node and the transmission quality between nodes are key factors affecting the service quality of the communication route in 5G communication engineering.

[0078] Furthermore, after completing the segmentation, multi-segment node detection probes are deployed based on the segmentation results, such as... Figure 3 As shown, the specific deployment method is as follows:

[0079] First, based on the segmentation results, devices in each segment are numbered, the connection status between adjacent devices is obtained, and key deployment nodes in each segment are located. Detection probes are deployed according to the task type of the key deployment nodes. For example, in the terminal segment, the key deployment node is the user terminal, using an embedded SDK or lightweight software probe. For the access segment, the key deployment node is the enterprise AR (access router) or customer front-end equipment (CPE), using hardware probes for detection and deployment. The transmission routes in each segment are then divided based on the network data transmission method; that is, different segments include multiple sets of data transmission routes. For example, in the access segment… In this system, multiple enterprise ARs and customer front-end devices (CPEs) are deployed, and different enterprise ARs with different serial numbers are connected to different customer front-end devices (CPEs). Therefore, there are multiple network data transmission routes. It is necessary to locate the key deployment nodes corresponding to each group of data transmission routes. The deployment method of the key deployment nodes is fault-compatible deployment, that is, faults between connected devices in the same group of data transmission routes can propagate to each other, and the corresponding fault data can be detected and displayed in the connected devices. In this case, the connected devices share the same detection probe. The device that deploys the probe is marked as the detection device, and the device that is compatiblely connected to it is marked as the associated device.

[0080] After the probe deployment is completed, it is necessary to set the detection event feedback time points. The corresponding events include packet loss rate, one-way / two-way latency, throughput, bandwidth utilization, CP utilization, memory utilization, network card packet error rate, and routing table status. Events are collected periodically by the detection probes of different segments. That is, at regular intervals, event information is fed back through the probes corresponding to the key deployment nodes to obtain the current network communication status of the key deployment nodes.

[0081] like Figure 4As shown, due to the diverse types of events acquired, and the different parameter values ​​corresponding to different event types mapping different fault states, it is necessary to process the event states in stages. The first step is to classify the events reported by probes deployed in each key deployment node. Simultaneously, since changes in event parameter values ​​collected from different key deployment nodes may be caused by faults in other compatible connected devices, this solution requires node-related trend binding of event parameter values ​​during the event state processing process to obtain faulty devices and devices exhibiting fault data, in conjunction with historical fault detection data. For example, when a probe in a router collects its packet loss rate data, the following may occur: The faulty device is a base station or server with compatible connection. The cause of the fault may be the inability to receive data streams from the enterprise intranet or the interruption of all connections with the enterprise's IP segment. The base station or server is the faulty device, and the router is the corresponding faulty data display device. Finally, the trend of event parameter values ​​of the faulty data display device is collected. That is, when a fault occurs, the event parameter values ​​of the corresponding faulty data display device decrease, increase, or remain unchanged. These are all corresponding event parameter value change trends. The faulty device, the faulty data display device, the event parameter value change trend, and the parameter value change range are bound together to establish a node association trend database, which serves as a reference for subsequent fault prediction.

[0082] Furthermore, to facilitate subsequent communication status monitoring, this solution establishes a communication fault analysis model. Predictive processing is performed, where Represents a set of nodes. Indicating network transmission segments Each network element node;

[0083] This represents the set of network element node failure trends. express The fault trends of individual network element nodes are derived from a node association trend database. It represents the fault trend of different network element nodes, that is, the fault data reflecting the fault status of faulty equipment, specifically including the parameter value change trend and the value change range.

[0084] Denotes the set of edges. express The connection relationship between adjacent network element nodes, whether they are currently connected, and whether their corresponding data transmission channels are open, where the detection node is the key deployment node for deploying the corresponding probe;

[0085] Represents a set of compatible pathways. express The fault propagation path of different network element nodes, wherein the fault propagation path consists of multiple faulty devices and fault data display devices.

[0086] The function representing the node state calculation, such as Figure 5 As shown, the specific calculation method is as follows:

[0087] First, define the numerical range of regular event parameters for each key deployment node, and establish a set of regular numerical ranges. Based on the set detection event feedback time points, the event parameter values ​​of probe detection on each key deployment node are collected, and the data is processed through the node set. Identify the current critical deployment node sequence number, in conjunction with a standard numerical range set. Numerical mapping is performed, marking critical deployment nodes whose detected event parameter values ​​are within the normal range as normal critical deployment nodes, and marking critical deployment nodes whose detected event parameter values ​​exceed the normal range as abnormal critical deployment nodes, combined with the edge set. The system locates the transmission route of the currently abnormal critical deployment node and obtains the connection status between the abnormal critical deployment node and its corresponding adjacent network element nodes. Since there are multiple nodes on different transmission routes, in order to further narrow down the scope of fault prediction, it is necessary to use a compatible path set. Locate the fault propagation path of the currently abnormal critical deployment node and obtain the faulty nodes (faulty devices) associated with the abnormal critical deployment node.

[0088] Since multiple faulty nodes may exist at the same time, and the corresponding faulty node needs to provide feedback through the event parameter values ​​of one or more abnormal critical deployment nodes, the faulty node verification process requires combining the event parameter values ​​of the abnormal critical deployment nodes corresponding to the faulty node at the same time with the network element node fault trend set. Perform mapping and matching, mark as fault event parameters, and obtain the corresponding fault event parameter values. Collect the conventional parameter values ​​of the fault event parameters at the previous time point. By combining the historical numerical parameter variation range, a fraction of the unit change is calculated for each event parameter. Planning, and the magnitude and unit change fraction of the event parameter values. There is a negative correlation, meaning that the larger the magnitude of the change in the event parameter value, the greater the corresponding unit change in the fraction. The smaller the value, the higher the fault score for calculating the fault event parameter values ​​at different time points. The specific algorithm is as follows:

[0089] ;

[0090] in The initial fault score is the fault score that, since different fault events may induce multiple fault event parameter values. The situation has changed; therefore, in this solution, the failure score of the final failure node is taken as the failure score of each failure event parameter value. The average value is used as the real-time fault score in the final output.

[0091] After completing the real-time fault score calculation, based on the uploaded event status of different probes, and in conjunction with the communication fault analysis model... The network communication status prediction results are output, including event type, faulty device number, faulty data manifestation device number, and fault event parameter value. The system also includes real-time fault scores, which are then bound together to build a network communication status output model that outputs network communication status information in real time.

[0092] This invention achieves comprehensive multi-channel, multi-interface detection of 5G communication status by dividing network transmission segments and deploying multi-segment node detection probes. It collects network communication status data from different locations across multiple segments. Simultaneously, it establishes a communication fault analysis model incorporating node sets, network element node fault trend sets, edge sets, and compatible path sets to obtain parameter data relationships between different nodes. Using parameter values ​​fed back from probes in key deployment nodes, it classifies event types and matches parameter value trends. Combined with node status calculation functions, it calculates corresponding fault scores in real time, enabling comprehensive and multi-angle real-time fault prediction of current faulty nodes. This avoids the limitations of prediction based on single-node data feedback and ensures accurate prediction results.

[0093] Please see Figure 6 As shown, the second objective of this invention is to provide a system for implementing an intelligent detection method for the communication status of 5G communication engineering, including a multi-segment probe deployment model, an event type processing module, a communication fault analysis model, and a result output module;

[0094] The multi-segment probe deployment model is used to collect communication routes of 5G communication projects, divide network transmission segments, and deploy multi-segment node detection probes. It tests and probes different types of devices through the CPU core module and configures multiple test channels to adapt to the connection methods of different devices, including 5G test channels, WI-Fi test channels and Ethernet test channels; the 5G test channel includes 5G module 0 and 5G module 1.

[0095] The event type processing module is used to classify the events reported by probes deployed in each key deployment node, and to bind the event parameter values ​​to the node association trend. It binds the faulty device, the fault data display device, the event parameter value change trend and the parameter value change range, and establishes a node association trend database.

[0096] The communication fault analysis model is used to calculate the fault status of each network element node by combining the node set, the network element node fault trend set, the edge set, and the compatible path set.

[0097] The results output module, based on the upload event status of different probes, in conjunction with the communication fault analysis model, Output the network communication status prediction results.

[0098] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent detection of communication status in 5G communication engineering, characterized in that: Includes the following steps: S1. Collect the communication routes of 5G communication projects, divide the network transmission segments, and deploy multi-segment node detection probes; S2. Set the detection event feedback time point and collect events from the detection probes in different sections at regular intervals; S3. Perform phased processing based on the event status; The collected event types are categorized and classified. Perform node association and direction binding on event parameter values; S4. Establish a communication fault analysis model ; in, Represents a set of nodes. Indicating network transmission segments Each network element node; This represents the set of network element node failure trends. This indicates the failure trend of Z network element nodes; Denotes the set of edges. express The connection relationship between adjacent network element nodes; Represents a set of compatible pathways. express Fault propagation paths of different network element nodes; The node state calculation function combines the node set, the network element node fault trend set, the edge set, and the compatible path set to calculate the fault state of each network element node. S5. Based on the upload event status of different probes, combined with the communication fault analysis model. Output the network communication status prediction results; The calculation method for the node state calculation function in S4 includes the following steps: S4.1 Define the numerical range of regular event parameters for each key deployment node and establish a set of regular numerical ranges. ; S4.2 Collect the event parameter values ​​of probe detection for each key deployment node according to the set detection event feedback time point; S4.3, through node set Identify the current critical deployment node sequence number, in conjunction with a standard numerical range set. Perform numerical mapping; Critical deployment nodes whose detected event parameter values ​​are within the normal event parameter value range are marked as normal critical deployment nodes; Critical deployment nodes whose detected event parameter values ​​exceed the normal range are marked as abnormal critical deployment nodes; S4.4, Associative Edge Set Locate the transmission route of the currently abnormal critical deployment node and obtain the connection status between the abnormal critical deployment node and the corresponding adjacent network element node; S4.5, Set of compatible pathways Locate the fault propagation path of the currently abnormal critical deployment node and obtain the faulty nodes associated with the abnormal critical deployment node; S4.

6. Combine the event parameter values ​​of the abnormal critical deployment nodes corresponding to the faulty nodes at the same time point with the network element node fault trend set. Perform mapping matching and mark it as a fault event parameter; S4.7 Obtain the corresponding fault event parameter values. Collect the conventional parameter values ​​of the fault event parameters at the previous time point. By combining the historical numerical parameter variation range, a fraction of the unit change is calculated for each event parameter. planning; S4.8 Calculate the fault score for the fault event parameter values ​​at different time points. ; S4.9, Obtain the fault score from the parameter values ​​of each fault event. The average value is used as the final real-time fault score; The fault score of the fault event parameter values ​​in S4.7 The calculation algorithm is as follows: ； in The initial fault score, For units of change, fractions The values ​​are the parameters for the fault event. These are standard parameter values.

2. The intelligent detection method for communication status in 5G communication engineering according to claim 1, characterized in that: The network transmission segments divided in S1 include terminal segment, access segment, wireless segment, core network segment, and service segment.

3. The intelligent detection method for communication status in 5G communication engineering according to claim 2, characterized in that: The method for deploying multi-segment node detection probes in S1 includes the following steps: S1.

1. Based on the segmentation results, mark the devices in each segment with serial numbers and obtain the connection status between adjacent devices; S1.2 Locate the key deployment nodes in each section and deploy the detection probes according to the task type of the key deployment nodes; S1.3 Locate the key deployment nodes corresponding to each group of data transmission routes based on the network data transmission routes.

4. The intelligent detection method for communication status in 5G communication engineering according to claim 3, characterized in that: The critical deployment nodes in S1.3 are deployed using a fault-compatible deployment method.

5. The intelligent detection method for communication status in 5G communication engineering according to claim 1, characterized in that: The method for performing node association and directional binding of event parameter values ​​in S3 includes the following steps: S3.1 Classify the events reported by the probes deployed in each key deployment node by type; S3.2 Match fault data of faulty equipment under faulty conditions; S3.3 Collect fault data to show the trend of event parameter values ​​and the range of parameter value changes in the device; S3.

4. Bind the faulty equipment, the fault data display equipment, the trend of event parameter values, and the range of parameter value changes to establish a node association trend database.

6. The intelligent detection method for communication status in 5G communication engineering according to claim 1, characterized in that: The unit change fraction in S4.7 It is negatively correlated with the magnitude of the change in the event parameter value.

7. The intelligent detection method for communication status in 5G communication engineering according to claim 6, characterized in that: The network communication status prediction result output in S5 includes event type, fault device number, fault data manifestation device number, and fault event parameter value. And real-time fault scores.

8. A system for implementing the intelligent detection method for communication status in 5G communication engineering as described in claim 1, characterized in that: This includes a multi-segment probe deployment model, an event type processing module, a communication fault analysis model, and a result output module; The multi-segment probe deployment model is used to collect communication routes of 5G communication projects, divide network transmission segments, deploy multi-segment node detection probes, test and detect different types of devices through the CPU core module, and configure multiple test channels to adapt to the connection methods of different devices, including 5G test channels, WI-Fi test channels and Ethernet test channels. The event type processing module is used to classify the events reported by probes deployed in each key deployment node, and to perform node association trend binding on the event parameter values. It binds faulty devices, fault data display devices, event parameter value change trends, and parameter value change ranges to establish a node association trend database. The communication fault analysis model is used to calculate the fault status of each network element node by combining the node set, the network element node fault trend set, the edge set, and the compatible path set. The result output module is based on the upload event status of different probes, in conjunction with a communication fault analysis model. Output the network communication status prediction results.

Images