A network signal operation monitoring method

Abstract

This invention proposes a method for monitoring network signal operation. By deploying a centralized management service in a cloud computing environment, it performs threshold judgments on aggregated signal data, dynamically acquires additional cloud resources to support monitoring, and simultaneously constructs a cloud-based signal monitoring dashboard to update remote signals in real time, identify abnormal patterns, and integrate them into the network monitoring system. For anomalies related to resource scheduling, it obtains optimized paths, enhances dashboard functionality, and ultimately adjusts management services based on communication feedback data. This method achieves efficient aggregation of signal data, accurate identification of anomalies, and intelligent resource scheduling, significantly improving the reliability and response speed of cross-regional communication monitoring and providing stable support for multi-regional network operation.

Description

Technical Field

[0001] This invention relates to a method for monitoring network signal operation. Background Technology

[0002] Stable network signal operation is crucial for all industries, especially in communications, logistics, and smart device management, where signal quality directly impacts business efficiency and user experience. Current network signal monitoring methods often reveal significant shortcomings when facing large-scale, cross-regional business demands. Existing technologies struggle to adapt to differences in network environments across regions, lacking the ability to flexibly allocate resources, resulting in incomplete monitoring coverage. This is particularly true during periods of resource scarcity or sudden traffic spikes, where monitoring effectiveness is greatly reduced, making real-time monitoring of signal status difficult and consequently affecting the timeliness and accuracy of business decisions. In complex network environments, network signals are distributed across different regions, with data sources scattered and in varying formats, making it difficult to establish a unified management perspective. This leads to uneven resource allocation; without a unified perspective, it's impossible to dynamically adjust monitoring resources according to actual needs. For example, when signal anomalies are frequent in certain areas, resources cannot be concentrated in those areas in a timely manner, resulting in monitoring blind spots or wasted resources.

[0003] Therefore, how to integrate scattered signal data into a unified view in a cross-regional network environment, and on this basis, realize flexible scheduling of monitoring resources, has become a key issue in ensuring business continuity and improving monitoring efficiency. Summary of the Invention

[0004] This invention proposes a network signal operation monitoring method, which solves the problems of the complexity of communication signal data in cross-regional network operation and the monitoring needs of cross-regional operation in the prior art. It effectively aggregates communication signal data from multiple regions, monitors abnormal patterns in real time, and optimizes cloud resource scheduling to ensure the stability of monitoring communication.

[0005] The technical solution of this invention is implemented as follows:

[0006] A method for monitoring network signal operation includes the following steps: S1 obtains communication signal data from the operation of multi-regional networks, forms business logic associations through cloud resource scheduling, and obtains aggregated communication signal data; S2, Deploy centralized management services for the aggregated communication signal data in a cloud computing environment. If the aggregated communication signal data exceeds a preset business threshold, acquire additional cloud resources to support remote communication monitoring. S3, Based on the centralized management service, determine the communication monitoring indicators required for cross-regional operation from the aggregated communication signal data, and construct the initial structure of the cloud-based signal monitoring dashboard; S4 obtains real-time updates of remote communication signals from the monitoring dashboard of the initial structure, identifies communication anomaly patterns in multi-region operation, and integrates into the network monitoring system of the cloud computing platform. S5. In the network monitoring system, if the communication anomaly mode is related to cloud resource scheduling, then the resource optimization path is obtained from the cloud computing environment to obtain an enhanced monitoring dashboard. S6. Obtain cross-regional operation communication feedback data from the enhanced monitoring dashboard, and determine the adjustment path of centralized management services through data aggregation.

[0007] This invention deploys a centralized management service in a cloud computing environment, performs threshold judgments on aggregated signal data, dynamically acquires additional cloud resources to support monitoring, and simultaneously constructs a cloud-based signal monitoring dashboard to update remote signals in real time, identify abnormal patterns, and integrate them into the network monitoring system. For anomalies related to resource scheduling, it obtains optimized paths, enhances dashboard functionality, and ultimately adjusts management services based on communication feedback data. This method achieves efficient aggregation of signal data, accurate identification of anomalies, and intelligent resource scheduling, significantly improving the reliability and response speed of cross-regional communication monitoring and providing stable support for multi-regional network operation. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating the monitoring method of the present invention. Detailed Implementation

[0010] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0011] like Figure 1 The method for monitoring network signal operation, as shown, includes the following steps:

[0012] S1 acquires communication signal data from the operation of multi-regional networks, forms business logic associations through cloud resource scheduling, and obtains aggregated communication signal data.

[0013] Obtain raw communication signal data and extract signal features, obtain the cloud resource pool load status corresponding to the signal features, and determine the topological mapping relationship between the carrying signal features and the computing resources.

[0014] A business logic association matrix is ​​constructed, and the traffic distribution pattern in the business logic association matrix is ​​identified. If the traffic distribution pattern conforms to the preset logical link rules, a cloud resource scheduling instruction is generated, and the signal features are aggregated to the aggregation node to obtain aggregated communication signal data.

[0015] First, acquire raw communication signal data, such as radio frequency signal waveform data collected in a base station environment, and then extract signal features, such as amplitude, frequency, and phase parameters. In the process of extracting signal features, Fourier transform can be used to perform frequency domain analysis on the raw signal data. Specifically, the acquired time-domain signal sequence is input into a fast Fourier transform algorithm, and the dominant frequency components are identified by calculating the spectral distribution of the signal. Amplitude features are obtained through peak detection, frequency features are determined based on spectral line positions, and phase features are estimated through the arctangent function, thereby obtaining signal features in vector representation. This feature extraction not only reduces data redundancy but also improves the efficiency of subsequent processing, reduces computational overhead in high-load networks, and thus optimizes the overall system performance.

[0016] Next, the load status of the cloud resource pool corresponding to the signal characteristics is obtained, such as by monitoring the CPU utilization and memory usage of the cloud server, thereby determining the topological mapping relationship between the signal characteristics and the computing resources. This topological mapping relationship can be constructed using a graph theory model, where nodes represent signal characteristics and computing resources, and edges represent allocation correspondences. High-frequency signal characteristics are mapped to low-load GPU resource nodes, and the optimal correspondence is calculated using a minimum path algorithm, thus forming a directed graph representation of the mapping structure.

[0017] Next, based on the aforementioned topology mapping, a business logic association matrix is ​​constructed. This matrix is ​​a two-dimensional array where rows represent signal characteristics, columns represent resource nodes, and element values ​​are association strengths. Matrix multiplication is used to identify traffic distribution patterns. During matrix construction, it is first initialized as a zero matrix, and then values ​​are filled according to the mapping relationship. For example, the strength value is calculated based on load status and feature complexity; for instance, strength = reciprocal of load * feature dimension. Principal component analysis is then used to identify patterns in the matrix, such as clustering distribution patterns, indicating that traffic tends to converge on certain resource clusters. If the traffic distribution pattern conforms to preset logical link rules, such as patterns showing balanced traffic and no circular dependencies, a cloud resource scheduling instruction is generated. This instruction aggregates the signal characteristics to the central server of the aggregation node, obtaining aggregated communication signal data.

[0018] S2, deploy a centralized management service in a cloud computing environment for the aggregated communication signal data. If the aggregated communication signal data exceeds a preset business threshold, additional cloud resources are obtained to support remote communication monitoring.

[0019] The signal payload characteristics in the aggregated communication signal data are obtained and mapped to the pre-deployed centralized management service node. The resource occupancy ratio is determined based on the signal payload characteristics carried by the centralized management service node. If the ratio exceeds the preset business threshold, the elastic instance size is determined based on the identified resource gap.

[0020] Additional cloud resources are acquired by scaling up elastic instances and mounted to a virtual cluster. The additional cloud resources are used to build a monitoring link to synchronize the aggregated communication signal data and obtain a load image. Remote communication monitoring tasks are executed based on the remote signaling data in the load image, thereby achieving centralized management and resource expansion of the aggregated communication signal data.

[0021] Signal payload features are extracted from the aggregated communication signal data. In the network environment, signal payload features include packet size, transmission protocol type, and priority markers. These features are obtained by parsing the data frame structure and then mapped to pre-deployed centralized management service nodes. This mapping process uses a key-value pair storage method, where the key is the feature identifier and the value is the node address. High-priority load features are mapped to the main service node to ensure real-time processing. The resource occupancy ratio is determined based on the signal payload features carried by the centralized management service node. For example, the CPU utilization and bandwidth consumption of the monitoring node are monitored. If the ratio exceeds a preset business threshold of 80%, a resource gap is identified. The resource gap is determined by calculating the difference between the current occupancy and the threshold. For example, gap = threshold - current ratio. Then, the elastic instance size is estimated based on the gap size. For example, if the gap is 20%, two instances are added to dynamically adjust the resource configuration.

[0022] In a preferred embodiment, the determination process involves statistical analysis. A sliding window method is used to accumulate occupancy data over a certain period, calculate the average proportion, and compare it with a threshold. If the threshold is exceeded, a scale calculation is triggered. The scale formula is based on a linear ratio, such as scale = gap / instance capacity, where the instance capacity is preset to 10% of the resource unit. This obtains accurate expansion requirements, and elastic response avoids overload, achieving efficient load balancing in business operations. Additional cloud resources are acquired through elastic instance scaling and mounted to the virtual cluster. Virtual machine instances of the appropriate scale are requested from the cloud provider's resource pool and mounted to the existing cluster via API. These additional resources are used to build a monitoring link, deploying a proxy service to synchronize aggregated communication signal data and generate a load image, which includes a copy of real-time signaling data. Finally, remote communication monitoring tasks are performed based on the remote signaling data in the load image, such as analyzing latency indicators and packet loss rates in the signaling. This achieves centralized management and resource expansion of the aggregated data, thereby improving network stability.

[0023] S3. Based on the centralized management service, determine the communication monitoring indicators required for cross-regional operation from the aggregated communication signal data, and construct the initial structure of the cloud-based signal monitoring dashboard.

[0024] The regional identifier and signal transmission delay are extracted from the aggregated communication signal data and input into the centralized management service. The service determines the business throughput in cross-regional operation and determines communication monitoring indicators based on the correlation between the business throughput and node load status.

[0025] A monitoring dimension mapping is performed on the communication monitoring indicators to obtain a monitoring dimension set. The monitoring dimension set is then matched with a preset dashboard layout template. The dashboard layout template carries the real-time data stream, thus constructing the initial structure of a cloud-based signal monitoring dashboard.

[0026] Geographic identifiers and signal transmission delays are extracted from the aggregated communication signal data. Geographic identifiers can be obtained by parsing location metadata in the data packets, such as base station codes or GPS coordinates, to identify the signal source area. Signal transmission delays are obtained by calculating the time difference between sending and receiving data packets, for example, by using timestamp comparison methods to determine the end-to-end delay value. The regional identifier and the signal transmission delay are input to the centralized management service, which is a software platform deployed in a cloud computing environment for processing and analyzing input data. It determines the business throughput in cross-regional operations through a built-in algorithm. The service first maps the regional identifier to an operational area model, which divides network traffic based on geographical partitions. Then, it calculates the average throughput by combining the signal transmission delay. This process involves aggregating the delay values ​​of multiple data streams and applying a weighted average formula, where weights are allocated according to regional traffic density, thus deriving the overall business throughput, such as the amount of data transmitted per second, to reflect cross-regional communication efficiency. Next, communication monitoring indicators are determined based on the correlation between business throughput and node load status. This correlation is established through a preset mapping table, for example, associating high throughput with node CPU utilization; if the throughput exceeds a threshold, it indicates excessive load.

[0027] The process involves performing monitoring dimension mapping on communication monitoring metrics to obtain a monitoring dimension set. Specifically, this includes decomposing metrics into dimensions such as latency and packet loss, and assigning each metric to a corresponding set using a mapping function. For example, dimension data can be stored using key-value pairs to form a comprehensive monitoring set. Then, the monitoring dimension set is matched with a preset dashboard layout template. The dashboard layout template carries the real-time data stream, constructing the initial structure of a cloud-based signal monitoring dashboard. For example, the template predefines chart component layouts, and the dimension data in the set is bound to the components to display the real-time data stream, thereby achieving efficient communication monitoring.

[0028] S4 acquires real-time updates of remote communication signals from the monitoring dashboard of the initial structure, identifies abnormal communication patterns in multi-region operation, and integrates into the network monitoring system of the cloud computing platform.

[0029] Real-time update data of remote communication is extracted from the monitoring dashboard of the initial structure. Based on the real-time update data, the data flow characteristics in multi-region operation are identified to obtain multi-region data flow sequences and perform node status mapping. The node status classification result is obtained by classifying the sequence after node status mapping.

[0030] If the node status classification result exceeds the preset alarm threshold, traffic fluctuation features are extracted from the node status classification result to determine the communication anomaly mode in multi-region operation.

[0031] Obtain the cloud computing platform interface protocol corresponding to the communication anomaly mode, perform protocol conversion on the communication anomaly mode to obtain standard format anomaly mode data, and generate network monitoring synchronization instructions based on the standard format anomaly mode data to integrate into the network monitoring system of the cloud computing platform.

[0032] Real-time updated data from remote communications is extracted from the initial monitoring dashboard. This data includes indicators such as signal strength and transmission rate. Based on this data, the data flow characteristics in multi-region operation are identified to obtain multi-region data flow sequences. Real-time updated data can be extracted from the dashboard, including packet routing paths and timing information. The process of identifying data flow characteristics involves analyzing the jump patterns of packets between different regions, such as the flow path from one node to another. By tracking changes in IP addresses and timestamp sequences of packets, multi-region data flow sequences are obtained. These sequences record the starting region, intermediate jump nodes, and ending region of each data flow, as well as the corresponding flow duration. For example, the sequence format is [Region A - Node 1 - Duration 10ms, Region B - Node 2 - Duration 15ms]. This sequence is formed by aggregating information from multiple data flows. The specific analysis process includes first filtering noise in real-time data, such as discarding invalid packets, and then using a sequence modeling algorithm to connect feature points into a chain. The algorithm is based on temporal association rules to match data points with adjacent timestamps. If the temporal difference between two data points is less than a preset threshold, such as 5ms, they are considered as part of the same flow chain, thus constructing a complete sequence. In the process, a regional mapping table can also be introduced to convert IP addresses into geographical labels to ensure that the sequence reflects the real cross-regional flow dynamics.

[0033] Node status mapping is performed using multi-region data flow sequences. The mapped sequences are then classified to obtain node status classification results. For example, the mapping process uses state vectors to represent node load and correlates the duration of the sequence with node CPU utilization. If the node status classification result exceeds a preset alarm threshold, such as a load rate exceeding 80%, traffic fluctuation features are extracted from the results to determine abnormal communication patterns in multi-region operation. Feature extraction includes calculating traffic peak-to-valley differences and identifying anomalies such as sudden congestion using a fluctuation analysis model. The corresponding cloud computing platform interface protocol for the abnormal communication pattern is obtained, and the anomaly pattern is converted using the protocol to obtain standard format data. Based on this data, network monitoring synchronization instructions are generated and integrated into the system. For example, the protocol conversion uses JSON format standardization to achieve real-time anomaly synchronization.

[0034] S5. In the network monitoring system, if the communication anomaly mode is related to cloud resource scheduling, then the resource optimization path is obtained from the cloud computing environment to obtain an enhanced monitoring dashboard.

[0035] Extract scheduling correlation features from communication anomaly patterns, match the scheduling correlation features with preset cloud resource scheduling logs, and determine the degree of correlation between the communication anomaly patterns and cloud resource scheduling.

[0036] If the correlation exceeds the preset scheduling correlation threshold, the distribution pattern of virtual node load data on the time axis is obtained according to the scheduling correlation characteristics, redundant computing links are searched in the cloud computing environment and topology weight is calculated to obtain the resource optimization path.

[0037] The resource optimization path is mapped to the visualization layer of the network monitoring system. The data dimensions of the monitoring dashboard in the initial structure are expanded through the visualization layer to obtain an enhanced monitoring dashboard.

[0038] Scheduling correlation features are extracted from communication anomaly patterns, including sudden latency peaks. Feature extraction involves parsing timestamps and resource ID sequences in the patterns, converting them into vector form, and then matching these features with preset cloud resource scheduling logs. These logs record virtual machine migration events and CPU allocation history. The degree of correlation is determined by calculating the cosine similarity between the feature vector and the log entry. For example, the similarity formula is based on the vector inner product divided by the modulus; a result of 0.85 indicates a high correlation. Continuing based on the above correlation, if the correlation exceeds a preset threshold (e.g., 0.7), the distribution pattern of virtual node load data on the time axis is obtained according to the scheduling correlation features. The node IDs extracted from the features are used to query the load database. The distribution pattern is obtained through time series analysis, using a sliding window algorithm to scan the 24-hour load curve and calculate the average load rate and variance for each time period. For example, during peak periods, the load rate rises from 50% to 90%, exhibiting periodic fluctuations. The detailed process involves: first, aggregating load data points and sorting them by time axis; then, applying Fourier transform to identify frequency components to avoid noise interference and ensure the pattern reflects the true dynamics. This method uses multi-node data fusion to form a comprehensive time distribution view.

[0039] Based on the distribution patterns, redundant computing links are searched in the cloud computing environment and topology weights are calculated to obtain resource optimization paths. The distribution patterns show that some links have uneven loads. The search process uses a graph traversal algorithm to scan all paths from the starting node and identify redundant links. The topology weight calculation involves assigning link costs, which are based on load variance and distance. For example, weight = load rate * distance factor. The optimized path selects the path with the lowest weight, such as the path from node A to C with a weight of 15 instead of 20.

[0040] Finally, the resource optimization path is mapped to the visualization layer of the network monitoring system. The data dimensions of the monitoring dashboard in the initial structure are expanded through the visualization layer. For example, the path data is converted into a heat map layer, and the expanded dimensions include the addition of a load trend chart, thus obtaining an enhanced monitoring dashboard.

[0041] S6. Obtain cross-regional operation communication feedback data from the enhanced monitoring dashboard, and determine the adjustment path of centralized management services through data aggregation.

[0042] The system acquires cross-regional operation communication feedback data from the enhanced monitoring dashboard, parses the message header information in the communication feedback data to identify node latency and traffic load and performs multi-dimensional spatial coordinate mapping, and performs data aggregation processing within a preset time window to generate a business response sequence.

[0043] Based on the analysis of the link quality differences between different regions according to the service response sequence, if the link quality is lower than the preset communication threshold, the resource quota distribution of the current centralized management service is retrieved, the redundancy of the centralized management service is calculated through the resource quota distribution, and the redundancy is matched with the execution efficiency of the real-time scheduling instructions to determine the adjustment path of the centralized management service.

[0044] Communication feedback data for cross-regional operations is obtained from an enhanced monitoring dashboard. The dashboard collects real-time feedback from nodes, including packet transmission records. Based on this data, the message header information in the communication feedback data is parsed to identify node latency and traffic load. The message header information typically includes fields such as timestamp, source address, and payload size. By reading the header structure byte by byte, for example, first extracting the 4-byte timestamp field to indicate the sending time, and then reading the 2-byte payload field to indicate the data size, the node latency is calculated, which is the difference between the receiving time and the sending time. For example, the latency from the Beijing node to the London node is 150 milliseconds. Traffic load is obtained by summing the packet size field in the header. For example, if 1000 packets are processed per second, and each packet is an average of 500 bytes, then the load rate is 500KB / s.

[0045] Multi-dimensional spatial coordinate mapping is performed on node latency and traffic load, and data aggregation is executed within a preset time window to generate a service response sequence. Specifically, spatial coordinate mapping converts latency and load into a three-dimensional coordinate system, for example, the x-axis represents geographical longitude, the y-axis represents latency value, and the z-axis represents load rate, visualizing the distribution of different nodes through a scatter plot. Then, within a preset time window such as 1 hour, data aggregation is performed, using an averaging method to aggregate all latency data within the window, calculating the mean and standard deviation to form a service response sequence. This sequence reflects the dynamics of service response, thereby connecting to the assessment of link quality.

[0046] Based on the analysis of business response sequences, the link quality differences between different regions are analyzed. If the link quality is lower than a preset communication threshold, the resource quota distribution of the current centralized management service is retrieved. Link quality is evaluated by a comprehensive score of latency and packet loss rate in the sequence, for example, score = (1 - latency / threshold) * (1 - load overload rate). If the score is lower than the threshold of 0.6, the database of the centralized management service is queried to obtain distribution information such as CPU quota of 50% and memory quota of 30%. The redundancy of the centralized management service is calculated through the resource quota distribution, and the redundancy is matched with the execution efficiency of real-time scheduling instructions. Redundancy = available quota / total quota. Then, the scheduling efficiency is matched to determine the path, such as increasing the quota of a certain node, thereby determining the adjustment path to achieve cross-regional management.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring network signal operation, characterized in that, Includes the following steps: S1 obtains communication signal data from the operation of multi-regional networks, forms business logic associations through cloud resource scheduling, and obtains aggregated communication signal data; S2, Deploy centralized management services for the aggregated communication signal data in a cloud computing environment. If the aggregated communication signal data exceeds a preset business threshold, acquire additional cloud resources to support remote communication monitoring. S3, Based on the centralized management service, determine the communication monitoring indicators required for cross-regional operation from the aggregated communication signal data, and construct the initial structure of the cloud-based signal monitoring dashboard; S4 obtains real-time updates of remote communication signals from the monitoring dashboard of the initial structure, identifies communication anomaly patterns in multi-region operation, and integrates into the network monitoring system of the cloud computing platform. S5. In the network monitoring system, if the communication anomaly mode is related to cloud resource scheduling, then the resource optimization path is obtained from the cloud computing environment to obtain an enhanced monitoring dashboard. S6. Obtain cross-regional operation communication feedback data from the enhanced monitoring dashboard, and determine the adjustment path of centralized management services through data aggregation.

2. The network signal operation monitoring method as described in claim 1, characterized in that, Step S1 is as follows: Obtain raw communication signal data and extract signal features, obtain the cloud resource pool load status corresponding to the signal features, and determine the topological mapping relationship between the carrying signal features and the computing resources. A business logic association matrix is ​​constructed, and the traffic distribution pattern in the business logic association matrix is ​​identified. If the traffic distribution pattern conforms to the preset logical link rules, a cloud resource scheduling instruction is generated, and the signal features are aggregated to the aggregation node to obtain aggregated communication signal data.

3. The network signal operation monitoring method as described in claim 1, characterized in that, Step S2 is as follows: The signal payload characteristics in the aggregated communication signal data are obtained and mapped to the pre-deployed centralized management service node. The resource occupancy ratio is determined based on the signal payload characteristics carried by the centralized management service node. If the ratio exceeds the preset business threshold, the elastic instance size is determined based on the identified resource gap. Additional cloud resources are acquired by scaling up elastic instances and mounted to a virtual cluster. The additional cloud resources are used to build a monitoring link to synchronize the aggregated communication signal data and obtain a load image. Remote communication monitoring tasks are executed based on the remote signaling data in the load image, thereby achieving centralized management and resource expansion of the aggregated communication signal data.

4. The network signal operation monitoring method as described in claim 1, characterized in that, Step S3 is as follows: The regional identifier and signal transmission delay are extracted from the aggregated communication signal data and input into the centralized management service. The service determines the business throughput in cross-regional operation and determines communication monitoring indicators based on the correlation between the business throughput and node load status. A monitoring dimension mapping is performed on the communication monitoring indicators to obtain a monitoring dimension set. The monitoring dimension set is then matched with a preset dashboard layout template. The dashboard layout template carries the real-time data stream, thus constructing the initial structure of a cloud-based signal monitoring dashboard.

5. The network signal operation monitoring method as described in claim 1, characterized in that, Step S4 is as follows: Real-time update data of remote communication is extracted from the monitoring dashboard of the initial structure. Based on the real-time update data, the data flow characteristics in multi-region operation are identified to obtain multi-region data flow sequences and perform node status mapping. The node status classification result is obtained by classifying the sequence after node status mapping. If the node status classification result exceeds the preset alarm threshold, traffic fluctuation features are extracted from the node status classification result to determine the communication anomaly mode in multi-region operation. Obtain the cloud computing platform interface protocol corresponding to the communication anomaly mode, perform protocol conversion on the communication anomaly mode to obtain standard format anomaly mode data, and generate network monitoring synchronization instructions based on the standard format anomaly mode data to integrate into the network monitoring system of the cloud computing platform.

6. The network signal operation monitoring method as described in claim 1, characterized in that, Step S5 is as follows: Extract scheduling correlation features from communication anomaly patterns, match the scheduling correlation features with preset cloud resource scheduling logs, and determine the degree of correlation between the communication anomaly patterns and cloud resource scheduling. If the correlation exceeds the preset scheduling correlation threshold, the distribution pattern of virtual node load data on the time axis is obtained according to the scheduling correlation characteristics, redundant computing links are searched in the cloud computing environment and topology weight is calculated to obtain the resource optimization path. The resource optimization path is mapped to the visualization layer of the network monitoring system. The data dimensions of the monitoring dashboard in the initial structure are expanded through the visualization layer to obtain an enhanced monitoring dashboard.

7. The network signal operation monitoring method as described in claim 1, characterized in that, Step S6 is as follows: The system acquires cross-regional operation communication feedback data from the enhanced monitoring dashboard, parses the message header information in the communication feedback data to identify node latency and traffic load and performs multi-dimensional spatial coordinate mapping, and performs data aggregation processing within a preset time window to generate a business response sequence. Based on the analysis of the link quality differences between different regions according to the service response sequence, if the link quality is lower than the preset communication threshold, the resource quota distribution of the current centralized management service is retrieved, the redundancy of the centralized management service is calculated through the resource quota distribution, and the redundancy is matched with the execution efficiency of the real-time scheduling instructions to determine the adjustment path of the centralized management service.

Images