Intelligent short message link efficient detection method and system

Abstract

The invention provides an intelligent short message link efficient detection method and system. According to the method, unmanned aerial vehicle cluster deployment is used for forming a dynamic communication topology, and the dynamic communication topology is used for monitoring the time delay mutation rate and the packet loss rate of a damaged short message link in real time and generating a state fluctuation sequence. When it is detected that the transmission time delay gradient exceeds an emergency communication threshold value, an abnormal marking mechanism is triggered, and abnormal association clusters and the space-time coupling relation of the abnormal association clusters are recognized by analyzing the data. Then, the information is bound with timestamps, and a block chain state change event is generated by using a multi-node parallel evidence storage technology; and adjusting the distribution density of the unmanned aerial vehicle according to a verification result, and generating a topology reconstruction factor so as to update a short message transmission path and optimize a communication network. According to the technical scheme provided by the invention, the stability and reliability of efficient detection of the short message link can be improved.

Description

Technical Field

[0001] This application relates to the technical field of efficient detection of short message links, and particularly to an intelligent method and system for efficiently detecting short message links. Background Art

[0002] When natural disasters or emergencies occur, communication infrastructure is often severely damaged, resulting in the interruption of traditional communication methods such as short message services or a sharp decline in performance. In such cases, ensuring the reliability, timeliness, and stability of emergency communication has become a key technical requirement. Especially in rescue operations, real-time access to on-site information is crucial for command and dispatch. Therefore, a communication solution that can respond quickly and adaptively adjust is needed, which can dynamically optimize the short message transmission path in a complex environment to minimize latency and data loss rate and ensure the effectiveness of emergency communication.

[0003] Currently, an advanced solution is to use satellite communication networks as a backup communication means. When it is found that the ground communication facilities are damaged, the satellite link is immediately switched to for data transmission. This solution forms a communication network with a wide coverage and not affected by ground disasters by deploying a series of low-orbit satellites globally, which can effectively provide stable short message services and ensure unobstructed communication even under extreme conditions. In addition, satellite communication also supports highly automated management and configuration, reducing the need for manual intervention and improving the overall system response speed and efficiency.

[0004] Although satellite communication systems provide effective backup options for emergency situations, they also have some limitations that cannot be ignored. First, the cost of satellite communication is relatively high, not only reflected in the initial construction investment, but also including daily operation and maintenance costs and usage tariffs, which is a significant burden for emergency response agencies with limited resources. Second, since satellite communication depends on specific spatial positions and orbital parameters, it may not provide the best service quality in some geographical regions or specific time windows, especially during periods of high-density user access, bandwidth bottlenecks may occur, affecting communication efficiency. Finally, the flexibility of satellite communication systems is poor, and it is difficult to quickly adjust resource allocation according to real-time changing environmental conditions, which to a certain extent limits its ability to respond to emergencies. Summary of the Invention

[0005] Embodiments of this application provide an intelligent method and system for efficiently detecting short message links to solve the problems of poor stability and reliability in detecting short message links in the prior art.

[0006] In a first aspect, embodiments of this application provide an intelligent method for efficiently detecting short message links, including: Form a dynamic communication topology by deploying a drone swarm to collect data on the delay mutation rate and packet loss rate of damaged SMS links in real time, generate an SMS link state fluctuation sequence, and trigger an SMS link anomaly flag when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold; Based on the SMS link state fluctuation sequence, perform SMS link state migration detection on the dynamic communication topology, identify abnormal correlation clusters of the transmission path, and form a spatio-temporal coupling relationship with the SMS link anomaly flag; Bind the time stamps to the abnormal correlation clusters and SMS link state migration features for multi-node parallel archiving, and generate a blockchain state change event containing the SMS link state fluctuation sequence; Adjust the distribution density of the drones according to the verification result of the blockchain state change event, generate an SMS link topology reconstruction factor, and form a closed-loop feedback with the spatio-temporal coupling relationship to update the topology correlation detection path of SMS transmission.

[0007] Optionally, the performing SMS link state migration detection on the dynamic communication topology based on the SMS link state fluctuation sequence, identifying abnormal correlation clusters of the transmission path, and forming a spatio-temporal coupling relationship with the SMS link anomaly flag includes: Generate a node aggregation path based on the SMS link state fluctuation sequence, dynamically adjust the aggregation weight according to the delay gradient and packet loss rate of adjacent nodes, and form a positive feedback association with the triggering condition of the SMS link anomaly flag; Perform SMS link state migration detection on the dynamic communication topology, and identify abnormal correlation clusters of the transmission path in the distribution characteristics of the node aggregation path and the SMS link state fluctuation sequence; Quantify the spatio-temporal coupling relationship of the abnormal correlation clusters into a spatio-temporal coupling coefficient, and the spatio-temporal coupling coefficient forms a cross-validation relationship with the aggregation weight of the node aggregation path; Based on the cross-validation relationship, correct the spatial distribution boundary of the abnormal correlation clusters, generate abnormal correlation cluster correction parameters, and feedback them to the dynamic spatial association analysis process of the SMS link state fluctuation sequence through the node aggregation path.

[0008] Optionally, the quantifying the spatio-temporal coupling relationship of the abnormal correlation clusters into a spatio-temporal coupling coefficient, and the spatio-temporal coupling coefficient forms a cross-validation relationship with the aggregation weight of the node aggregation path includes: Based on the three-dimensional coordinate distribution of drone nodes in the emergency area, generate a coverage density index by dividing geographical grid cells and counting the ratio of the number of active nodes to the grid volume; Statistically analyze the trigger frequency distribution of the abnormal marks of the SMS link according to a preset time window, generate an abnormal frequency histogram, and extract the duration of the peak interval in the abnormal frequency histogram as the abnormal time aggregation factor; Perform weighted fusion on the coverage density index and the abnormal time aggregation factor to generate an initial spatio-temporal coupling coefficient. At the same time, the weight of the coverage density index is dynamically adjusted according to the priority of the emergency area; Extract the weight distribution entropy value of the central area of the abnormal association cluster. Based on the difference degree between the weight distribution entropy value and the initial spatio-temporal coupling coefficient, quantify the spatio-temporal coupling relationship as the spatio-temporal coupling coefficient; Construct an aggregated weight-spatio-temporal coupling cross-validation matrix, generate a validation factor by comparing the correlation between the aggregated weight gradient change rate and the update amplitude of the spatio-temporal coupling coefficient element by element. When the validation factor is lower than the confidence threshold, trigger the reconstruction of the spatial distribution boundary of the abnormal association cluster.

[0009] Optionally, the triggering of the SMS link abnormal mark when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold includes: Analyze the SMS transmission delay gradient based on the difference between adjacent time windows in the SMS link state fluctuation sequence, and perform normalization processing through the cumulative mean of the delay change rate within the sliding window to generate a normalized SMS transmission delay gradient; Dynamically adjust the emergency communication threshold according to the historical distribution characteristics of the normalized SMS transmission delay gradient and the gradient change trend within the current window; When the normalized SMS transmission delay gradient exceeds the adjusted emergency communication threshold, combine the time length and the number of times exceeding the adjusted emergency communication threshold to generate an abnormal mark trigger condition; Use the normalized SMS transmission delay gradient, the adjusted emergency communication threshold, and the parameters corresponding to the abnormal mark trigger condition as associated parameters, and transfer them to the subsequent SMS link abnormal analysis module to trigger the SMS link abnormal mark.

[0010] Optionally, the formation of a dynamic communication topology by deploying a drone cluster to collect the delay mutation rate and packet loss rate data of the damaged SMS link in real time to generate an SMS link state fluctuation sequence includes: According to the spatial distribution of the damaged SMS link and the current channel quality, control the signal strength and interference level of each node in the drone cluster to generate dynamic weight parameters, and form a dynamic communication topology through iterative update of the drone cluster position; In the dynamic communication topology, collect the delay mutation rate and packet loss rate data of the damaged SMS link at a preset period. The packet loss rate data is appended with the packet loss rate variance within the acquisition time window as a fluctuation feature; Perform timestamp alignment and sliding window splicing on the data of the delay mutation rate and packet loss rate to generate a time-aligned acquisition data set, and perform weighted fusion on the acquisition data set based on the dynamic weight parameters to generate a short message link state fluctuation sequence.

[0011] Optionally, the performing timestamp alignment and sliding window splicing on the data of the delay mutation rate and packet loss rate to generate a time-aligned acquisition data set includes: Determine a reference time axis based on the clock synchronization protocol of each node in the UAV cluster, map the timestamps of the collected delay mutation rate and packet loss rate data to the reference time axis, and generate a timestamp mapping table; Perform linear interpolation filling on the delay mutation rate and packet loss rate data with missing timestamps according to the timestamp mapping table, and use the mean value of adjacent valid data points as the interpolation reference value to generate the interpolated delay mutation rate and packet loss rate data; Divide the interpolated delay mutation rate and packet loss rate data into multiple overlapping sliding windows, perform head and tail timestamp calibration and boundary data smoothing processing, and generate delay mutation rate segments and packet loss rate segments aligned within the window; Splice the delay mutation rate segments and packet loss rate segments in chronological order into a delay and packet loss joint data block with a unified time dimension, and extract the time coverage range and data density as window metadata to generate a time-aligned acquisition data set.

[0012] Optionally, the binding the abnormal association cluster and the short message link state migration feature with timestamps for multi-node parallel archiving to generate a blockchain state change event including the short message link state fluctuation sequence includes: Perform timestamp binding processing on the abnormal feature vector of the abnormal association cluster and the dynamic feature vector of the short message link state migration feature through a time window sliding alignment mechanism to generate an abnormal state joint feature vector group; Divide the abnormal state joint feature vector group into multiple parallel archiving sub-units according to the timestamp tags, perform hash archiving to generate an archiving hash chain, and perform cross-node cross-verification to construct an archiving topology structure; Extract the state encoding values of the short message link state migration features corresponding to each timestamp tag in the archiving topology structure, and perform fluctuation fitting on the state encoding values according to the state transition relationship in ascending order of timestamps to generate a short message link state fluctuation sequence; Perform event encapsulation binding on the short message link state fluctuation sequence and the archiving hash chain to generate a blockchain state change event including the short message link state fluctuation sequence.

[0013] In a second aspect, an embodiment of the present application provides an intelligent short message link efficient detection system, including: The acquisition module forms a dynamic communication topology by deploying a drone cluster to collect the data of the delay mutation rate and packet loss rate of the damaged SMS link in real time, generate an SMS link state fluctuation sequence, and trigger an SMS link anomaly mark when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold; The identification module performs SMS link state migration detection on the dynamic communication topology based on the SMS link state fluctuation sequence, identifies the abnormal correlation clusters of the transmission path, and forms a spatio-temporal coupling relationship with the SMS link anomaly mark; The generation module binds the time stamp to the abnormal correlation cluster and the SMS link state migration feature for multi-node parallel archiving, and generates a blockchain state change event including the SMS link state fluctuation sequence; The update module adjusts the distribution density of the drones according to the verification result of the blockchain state change event, generates an SMS link topology reconstruction factor, and forms a closed-loop feedback with the spatio-temporal coupling relationship to update the topology association detection path of SMS transmission.

[0014] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent SMS link efficient detection method as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements an intelligent SMS link efficient detection method as described in the first aspect.

[0016] In the embodiment of the present application, a dynamic communication topology is formed by deploying a drone cluster to collect the data of the delay mutation rate and packet loss rate of the damaged SMS link in real time, generate an SMS link state fluctuation sequence, and trigger an SMS link anomaly mark when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold; perform SMS link state migration detection on the dynamic communication topology based on the SMS link state fluctuation sequence, identify the abnormal correlation clusters of the transmission path, and form a spatio-temporal coupling relationship with the SMS link anomaly mark; bind the time stamp to the abnormal correlation cluster and the SMS link state migration feature for multi-node parallel archiving, and generate a blockchain state change event including the SMS link state fluctuation sequence; adjust the distribution density of the drones according to the verification result of the blockchain state change event, generate an SMS link topology reconstruction factor, and form a closed-loop feedback with the spatio-temporal coupling relationship to update the topology association detection path of SMS transmission.

[0017] The technical solution of the present application has the following beneficial effects: By deploying a drone cluster, this application can flexibly and quickly establish a temporary communication network, which is particularly suitable for emergency scenarios. This step can monitor the status changes of the SMS link in real time and detect potential problems in a timely manner. The mechanism for marking abnormal SMS links ensures that when the performance of the SMS link drops sharply, the system can quickly respond and mark the abnormal situation, providing an accurate basis for subsequent processing. By deeply analyzing the dynamic communication topology, the key factors affecting communication quality and their interrelationships are accurately identified, so as to achieve precise positioning and description of problems. Using blockchain technology to record abnormal information not only improves the security and immutability of data, but also facilitates multi-party verification and traceability, enhancing the transparency and trust of the system. Optimizing the drone layout based on the verification results further improves the quality of the SMS link, realizing an efficient communication network with fast learning and adaptation capabilities.

[0018] Furthermore, based on the sequence of fluctuations in the SMS link status, a node aggregation path is generated. By dynamically adjusting the aggregation weights and forming a positive feedback association with the abnormal marks, state migration detection is performed to identify abnormal association clusters and quantify their spatio-temporal coupling relationships. The spatial distribution boundary of the abnormal clusters is corrected through cross-verification and fed back to the dynamic spatial association analysis process. This process realizes the fine regulation and optimization of the SMS link status, effectively improving the accuracy and response speed of abnormal detection, while enhancing the stability and adaptive capabilities of the communication network.

[0019] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. Brief Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 Shows the flowchart of an intelligent and efficient SMS link detection method provided by this application; Figure 2 Shows the structural schematic diagram of an intelligent and efficient SMS link detection system provided by this application; Figure 3 Shows the structural schematic diagram of a computing device provided by this application. Detailed Embodiments

[0022] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application.

[0023] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0024] This application aims to use a drone swarm to build a dynamic communication network, monitor the delay mutation rate and packet loss rate of the SMS link in real time, generate a status fluctuation sequence and mark anomalies. Generate blockchain events through multi-node parallel evidence storage to ensure data security and traceability. Adjust the drone distribution density according to the verification results, optimize the SMS link, form a closed-loop feedback mechanism from detection to repair, achieve rapid response to environmental changes and self-optimization, improve the reliability and efficiency of SMS services in emergency communications, and provide a flexible and reliable solution.

[0025] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0026] Figure 1 The flowchart of an intelligent SMS link efficient detection method provided for the embodiments of this application is as Figure 1 shown, and this method includes: 101. Form a dynamic communication topology by deploying a drone swarm to collect the delay mutation rate and packet loss rate data of the damaged SMS link in real time, generate an SMS link status fluctuation sequence, and trigger an SMS link anomaly mark when the SMS transmission delay gradient in the SMS link status fluctuation sequence exceeds the emergency communication threshold; In this step, the dynamic communication topology is a temporary communication network structure formed by a drone swarm to support emergency communication.

[0027] The delay mutation rate refers to the rate of change of the delay of the damaged SMS link within a specific time window, and is used to describe the change of the delay during the SMS transmission process.

[0028] The variance of the packet loss rate within the additional acquisition time window of the packet loss rate data is used as a fluctuation feature to describe the proportion of lost data packets and their fluctuations during the data transmission process.

[0029] The short message link state fluctuation sequence is a time series generated based on the delay mutation rate and packet loss rate data, which is used to reflect the state change trend of the short message link.

[0030] The emergency communication threshold is a pre-set standard. When the short message transmission delay gradient exceeds this standard, the alarm mechanism is triggered.

[0031] The short message link anomaly flag is an identifier generated when the short message transmission delay gradient exceeds the emergency communication threshold, which is used to promptly discover and handle potential problems.

[0032] In the embodiments of the present application, first, a dynamic communication topology is formed by deploying a drone cluster to construct a temporary emergency communication network structure. The delay mutation rate and packet loss rate data of the damaged short message link within a specific time window are collected in real time, and the variance of the packet loss rate within the additional acquisition time window is used as a fluctuation feature. Secondly, a short message link state fluctuation sequence is generated based on the collected data, which can reflect the state change trend of the short message link, including the change of delay and the proportion of lost data packets and their fluctuations during the data transmission process. Finally, when analyzing the short message link state fluctuation sequence and finding that the short message transmission delay gradient exceeds the pre-set emergency communication threshold, the system will trigger the short message link anomaly flag to promptly discover and handle potential problems, ensuring the effectiveness and reliability of emergency communication. This process effectively utilizes the flexibility and real-time nature of the drone cluster and provides strong support for communication guarantee in emergency situations.

[0033] In a rescue scenario after a sudden earthquake, drones are quickly deployed over the disaster area to establish a temporary communication network. The real-time data acquisition module starts to work and collects various performance indicators of the short message links in the disaster area. After a period of data accumulation, the system identifies that the delay mutation rate of some link segments has increased significantly, and then triggers an anomaly flag, providing a clear direction for subsequent repair work.

[0034] 102. Based on the short message link state fluctuation sequence, perform short message link state migration detection on the dynamic communication topology, identify abnormal association clusters of the transmission path, and form a spatio-temporal coupling relationship with the short message link anomaly flag; In this step, the short message link state migration detection is an algorithm tool used to monitor the changes in the short message link state.

[0035] The abnormal association cluster refers to the key factors affecting communication quality, which are identified from the distribution characteristics of the node aggregation path and the short message link state fluctuation sequence through clustering analysis technology.

[0036] The spatio-temporal coupling relationship is a numerical value that quantifies the temporal and spatial distribution characteristics of abnormal correlation clusters and is used to evaluate the degree of their impact on the overall network.

[0037] Combining the short message link anomaly markers with the spatio-temporal coupling relationship forms a closed-loop feedback mechanism to achieve more accurate problem location and optimization measures.

[0038] In the embodiments of the present application, first, based on the short message link state fluctuation sequence, real-time monitoring is performed on each node in the dynamic communication topology to collect its state information. Then, time series analysis technology is applied to identify the change trend of the short message link state, and clustering algorithms are used to identify abnormal correlation clusters. Next, the identified abnormal correlation clusters are compared and analyzed with the existing short message link anomaly markers to determine the spatio-temporal coupling relationship between the two. Finally, all the information is integrated to generate a comprehensive report containing the spatio-temporal coupling relationship for guiding subsequent optimization measures.

[0039] Continuing with the above earthquake rescue scenario, after marking the abnormal link segments, the system further analyzes the specific situations of these segments, determines several key abnormal correlation clusters. By quantifying their spatio-temporal coupling relationship, the degree of impact of these clusters on the overall communication efficiency is clarified, thus providing a basis for optimizing resource allocation.

[0040] 103. Bind the time stamps to the abnormal correlation clusters and the short message link state migration characteristics for multi-node parallel evidence storage to generate a blockchain state change event containing the short message link state fluctuation sequence; In this step, binding the time stamp refers to the process of synchronizing the time information of the abnormal correlation clusters and the short message link state migration characteristics.

[0041] Multi-node parallel evidence storage is a technical means of using multiple nodes to store data simultaneously to ensure the reliability and anti-tampering ability of the data.

[0042] The blockchain state change event is an immutable record containing all relevant data and verification information for long-term storage and verification. This event encapsulates the short message link state fluctuation sequence and provides a complete data chain.

[0043] In the embodiments of the present application, first, the abnormal correlation clusters and the short message link state migration characteristics are bound to the corresponding time stamps to form a complete data packet. Then, hash evidence storage operations are performed in parallel on multiple nodes to ensure the authenticity and integrity of the data. Next, blockchain technology is used to encapsulate these data to create a new blockchain state change event. Through the consensus mechanism, this event is recognized and recorded by all nodes in the network. Finally, this event is added to the blockchain to form a permanent record to ensure the immutability of the data.

[0044] During earthquake rescue operations, all identified abnormal information is simultaneously recorded by multiple drone nodes, forming a series of blockchain events. This not only provides solid data support for current rescue operations but also accumulates valuable experience for future disaster responses.

[0045] 104. Adjust the distribution density of drones according to the verification result of the blockchain state change event, generate a short message link topology reconstruction factor, and form a closed-loop feedback with the spatio-temporal coupling relationship to update the topological association detection path of short message transmission.

[0046] In this step, the verification result of the blockchain state change event is confirmed by comparing the data consistency on different nodes.

[0047] The short message link topology reconstruction factor is a parameter generated by adjusting the drone distribution density based on the verification result, and is used to optimize the topology structure of the short message link.

[0048] The closed-loop feedback mechanism refers to combining the spatio-temporal coupling relationship with the short message link topology reconstruction factor to form a continuously optimized process.

[0049] Updating the topological association detection path of short message transmission is to adapt to new communication requirements and improve the overall communication performance.

[0050] In the embodiments of this application, first, extract the short message link state fluctuation sequences recorded by each node from the blockchain network, and count the number of times that the short message transmission delay gradient in the area where each drone node is located exceeds the emergency communication threshold, which is recorded as the abnormal frequency. For each abnormal association cluster, calculate the number of drone nodes covered by it and the fluctuation amplitude of the short message link state migration characteristics within the cluster to generate the cluster abnormal intensity.

[0051] Secondly, for the areas where the abnormal frequency is higher than the set value, increase the distribution density of drones in this area. The specific method is as follows: dispatch idle drones from the low-abnormal-frequency area to the high-abnormal-frequency area. If there are not enough idle drones, dynamically generate new drone nodes and add them to the high-abnormal-frequency area.

[0052] For the areas where the abnormal frequency is lower than the set value, reduce the distribution density of drones in this area. The specific method is as follows: mark some drones as standby status or dispatch them to other areas.

[0053] Furthermore, according to the adjusted drone distribution density, calculate the node coverage weight of each area. The weight value is the ratio of the number of drones in this area to the number of drones in the adjacent area. Combine the cluster abnormal intensity to generate a short message link topology reconstruction factor. This factor is a numerical value used to quantify the coverage ability of the current topology structure for the abnormal association cluster. The calculation formula is: Reconstruction factor = ∑(cluster abnormal intensity × node coverage weight) Finally, compare the SMS link topology reconstruction factor with the spatio-temporal coupling relationship: If the reconstruction factor is lower than the fluctuation amplitude of the abnormal correlation cluster recorded in the spatio-temporal coupling relationship, further increase the UAV distribution density in the high-abnormal frequency area. If the reconstruction factor is higher than the fluctuation amplitude of the abnormal correlation cluster recorded in the spatio-temporal coupling relationship, maintain the current UAV distribution density or slightly adjust the number of UAVs in the low-abnormal frequency area.

[0054] According to the latest UAV distribution density, recalculate the communication paths between nodes, and preferentially select the paths with high node coverage weights as the topological correlation detection paths for SMS transmission.

[0055] For example, in the rescue operation after an earthquake, based on the blockchain events recorded previously, the system automatically adjusted the UAV distribution density and optimized the topology of the SMS link. The new topology greatly improved the communication efficiency in the disaster area and ensured the smooth progress of the rescue work.

[0056] In summary, the accurate monitoring and real-time feedback of the damaged SMS link status are achieved through steps 101 to 104. This method not only improves the efficiency of data collection and analysis but also enhances the adaptability and stability of the system in emergency situations, providing strong technical support for dealing with emergencies. The whole process constructs an efficient, flexible, and reliable emergency communication guarantee system through precise data analysis, dynamic threshold adjustment, and effective anomaly marking mechanism, ensuring the timely transmission of key information and the smooth progress of rescue operations.

[0057] To further improve the monitoring and optimization of the SMS link status in the dynamic communication topology, the solution details the process of identifying the abnormal correlation cluster of the transmission path based on the SMS link status fluctuation sequence, and forms the spatio-temporal coupling relationship by aggregating node paths and dynamically adjusting the aggregation weight. By using clustering analysis technology and combining with the positive feedback mechanism, the sensitivity and response speed of the system to abnormal situations are improved, ensuring accurate positioning of the problem area.

[0058] In some embodiments, in step 102, the SMS link status migration detection is performed on the dynamic communication topology based on the SMS link status fluctuation sequence, the abnormal correlation cluster of the transmission path is identified, and the spatio-temporal coupling relationship is formed with the SMS link anomaly marking, including: 201. Generate a node aggregation path based on the SMS link status fluctuation sequence, dynamically adjust the aggregation weight according to the time delay gradient and packet loss rate of adjacent nodes, and form a positive feedback association with the trigger condition of the SMS link anomaly marking; In step 201, the node aggregation path is a set of paths generated based on the short message link state fluctuation sequence, which contains the delay gradient and packet loss rate information between adjacent nodes and is used to dynamically adjust the aggregation weight. The aggregation weight is a value calculated based on the delay gradient and packet loss rate of adjacent nodes and is used to reflect the connection strength between nodes. The triggering condition for the short message link anomaly flag is a preset standard, and when the short message link state exceeds this standard, the alarm mechanism is triggered. The positive feedback association refers to the interaction between the adjustment of the aggregation weight and the triggering condition of the anomaly flag to enhance the response speed to abnormal situations.

[0059] In the embodiment of this application, first, a node aggregation path is generated based on the short message link state fluctuation sequence. The time series analysis algorithm is used to calculate the delay gradient and packet loss rate between adjacent nodes, and the aggregation weight is dynamically adjusted accordingly. At the same time, these adjustments are combined with the triggering condition of the short message link anomaly flag to form a positive feedback association. Finally, this process enhances the sensitivity and response efficiency of the system to potential problems, ensuring the rapid discovery and handling of abnormal situations.

[0060] In practical applications, for example, first, the delay gradient and packet loss rate data of each drone node are extracted from the short message link state fluctuation sequence, and the data is divided into data blocks according to a time window (such as every 5 seconds).

[0061] For each data block, calculate the communication stability index between adjacent nodes: Delay gradient = current node delay - adjacent node delay Packet loss rate difference = current node packet loss rate - adjacent node packet loss rate If the delay gradient and packet loss rate difference between two nodes are both lower than the set threshold, a connection is established to form a node aggregation path (i.e., a set of stable communication paths).

[0062] Secondly, the initial aggregation weight = 1 / (delay gradient + packet loss rate difference + 1) (to avoid division by zero).

[0063] If the delay gradient or packet loss rate of a certain path exceeds the dynamic threshold (such as 2 times the historical average), its aggregation weight is reduced (such as multiplied by the attenuation coefficient 0.8).

[0064] If the delay gradient and packet loss rate of the path remain stable, the aggregation weight is gradually increased (such as multiplied by the enhancement coefficient 1.2).

[0065] Finally, when the aggregation weight of a certain path drops to the critical value (such as 0.3), the short message link anomaly flag is triggered.

[0066] After the anomaly flag is triggered, the aggregation weight of this path is forced to be reduced to 0, and a standby drone node is preferentially scheduled to replace this path.

[0067] The aggregation weight of the new node is initialized to a relatively high value (such as 0.8) to form positive feedback: abnormal marking trigger → weight adjustment → path optimization → reduction of subsequent abnormalities.

[0068] 202. Perform SMS link state migration detection on the dynamic communication topology, and identify the abnormal correlation clusters of the transmission path from the distribution characteristics of the node aggregation path and the SMS link state fluctuation sequence. In step 202, the dynamic communication topology is a temporary communication network structure formed by a UAV cluster and is used to support emergency communication. The SMS link state migration detection is an algorithm tool for monitoring the changes in the SMS link state. The abnormal correlation cluster refers to the key factors affecting the communication quality and is identified from the distribution characteristics of the node aggregation path and the SMS link state fluctuation sequence through clustering analysis techniques. This process helps to accurately locate the source of the problem and guides subsequent optimization measures.

[0069] In the embodiment of the present application, first, all nodes in the dynamic communication topology are monitored in real time, their status information is collected, and the SMS link state fluctuation sequence is constructed using time series analysis techniques. Then, a clustering algorithm is used to determine the node aggregation path according to the behavior characteristics of the nodes, aiming to find groups of nodes with similar behavior patterns. Then, through the analysis of the deep learning model on the state fluctuation sequence, the abnormal patterns are identified, and these patterns represent the abnormal correlation clusters. Finally, by combining the node aggregation path and the identified abnormal patterns, the specific abnormal transmission path is further analyzed and located, and corresponding measures are taken for repair or optimization. This series of operations ensures the security and stability of the SMS link.

[0070] In practical applications, first, for each node aggregation path, calculate its state migration characteristics (such as the number of sudden increases in delay and the fluctuation range of packet loss rate). Using a sliding window statistic, if the migration characteristics of a certain path exceed the 90th percentile of the same type of path, it is marked as a suspicious path.

[0071] Secondly, input the delay gradient and packet loss rate data of all suspicious paths into the clustering model, and group them according to spatial proximity (UAV distance < 100 meters) and time synchronization (delay mutation time difference < 1 second). Output the abnormal correlation clusters: the paths within the same group are considered to be affected by the same factor (such as regional signal interference).

[0072] 203. Quantify the spatio-temporal coupling relationship of the abnormal correlation clusters into a spatio-temporal coupling coefficient, and the spatio-temporal coupling coefficient forms a cross-validation relationship with the aggregation weight of the node aggregation path. In step 203, the spatio-temporal coupling coefficient is a numerical value that quantifies the temporal and spatial distribution characteristics of the abnormal correlation clusters and is used to evaluate the degree of their impact on the overall network. The aggregation weight is a parameter dynamically adjusted according to the time delay gradient and packet loss rate between nodes. The cross-validation relationship refers to the mutual verification between the spatio-temporal coupling coefficient and the aggregation weight to ensure the accuracy of the spatial distribution boundary of the abnormal clusters. This process improves the accuracy of the identification of abnormal clusters.

[0073] In the embodiments of the present application, first, based on the identified abnormal correlation clusters, the spatio-temporal distances between the clusters are calculated, including the time interval and the geographical distance, and then the spatio-temporal coupling coefficient is obtained. This step uses geographic information system technology and time series analysis methods to quantify these parameters. Next, for each node aggregation path, a graph theory algorithm is used to calculate its aggregation weight, which reflects the tightness of the connection of the node in the network and the key of information transmission. Then, the spatio-temporal coupling coefficient and the aggregation weight are compared and analyzed to form a cross-validation relationship to confirm the authenticity and severity of the abnormal correlation clusters. Finally, the above results are integrated to generate a report containing all the abnormal correlation clusters and their spatio-temporal coupling coefficients and aggregation weights, which serves as the basis for optimizing the network structure and enhancing security.

[0074] In practical applications, first, the spatio-temporal coupling coefficient is calculated, including calculating the time coupling degree and the spatial coupling degree for each abnormal correlation cluster and combining them to obtain the spatio-temporal coupling coefficient. For example, it can be calculated through the following formula: Time coupling degree = Temporal correlation of the time delay mutation in the cluster path (such as Pearson coefficient) Spatial coupling degree = Reciprocal of the average geographical distance of the UAVs in the cluster (the closer the distance, the larger the value) Spatio-temporal coupling coefficient = Time coupling degree × Spatial coupling degree Secondly, cross-validation of the spatio-temporal coupling coefficient and the aggregation weight: If the spatio-temporal coupling coefficient of a cluster is high (>0.7), but the average value of the aggregation weight is low (<0.4), then it is confirmed that the cluster is a real anomaly. If the spatio-temporal coupling coefficient is low but the aggregation weight is high, it is determined as a false detection and the cluster is excluded.

[0075] 204. Modify the spatial distribution boundary of the abnormal correlation cluster based on the cross-validation relationship, generate an abnormal correlation cluster correction parameter, and feedback it to the dynamic spatial correlation analysis process of the short message link state fluctuation sequence through the node aggregation path.

[0076] In step 204, the cross-validation relationship refers to the result of the comparative analysis between the spatio-temporal coupling coefficient and the aggregation weight of the node aggregation path, which is used to evaluate the authenticity and severity of the abnormal association cluster. The spatial distribution boundary of the abnormal association cluster refers to the boundary that demarcates the influence range of the abnormal association cluster in the geographical space. The abnormal association cluster correction parameter is the adjustment parameter for the original spatial distribution boundary according to the cross-validation result, which is used to more accurately describe the actual influence area of the abnormal situation. The dynamic spatial association analysis process is a process of continuously monitoring and analyzing the short message link state fluctuation sequence, aiming to identify potential spatial association patterns in the network.

[0077] In the embodiment of the present application, first, based on the established cross-validation relationship, analyze whether the spatial distribution boundary of each abnormal association cluster needs to be adjusted. This step uses geographic information system technology combined with machine learning algorithms to determine the correction direction and amplitude by comparing the spatio-temporal coupling coefficient and the aggregation weight. Then, generate the abnormal association cluster correction parameter, which contains the adjusted spatial distribution boundary information. Next, feedback these correction parameters to the optimization process of the node aggregation path, use graph theory algorithms to recalculate the importance weights of each node, and update the node aggregation path. Finally, integrate the corrected node aggregation path information into the dynamic spatial association analysis of the short message link state fluctuation sequence to achieve real-time monitoring and optimization of the short message link state. The entire process ensures that the spatial distribution of the abnormal association cluster is more accurate, and improves the response speed and accuracy of the system to abnormal situations.

[0078] In practical applications, first correct the spatial distribution boundary. For the confirmed abnormal association cluster, adjust the influence range according to its spatio-temporal coupling coefficient: If the spatio-temporal coupling coefficient > 0.8, expand the boundary to adjacent nodes (such as increasing the radius by 50 meters).

[0079] If the spatio-temporal coupling coefficient < 0.5, shrink the boundary to the core node (such as only retaining the path with the most significant time delay mutation).

[0080] Generate the abnormal association cluster correction parameter (such as the new boundary coordinates, influence intensity).

[0081] Secondly, feedback to the dynamic spatial association analysis: Input the corrected parameter into the node aggregation path generation module, and forcefully reduce the aggregation weight of the paths within the abnormal cluster.

[0082] Update the analysis strategy of the short message link state fluctuation sequence, and give priority to monitoring the nodes within the corrected boundary during subsequent detections.

[0083] The following is a specific example: In a rescue scenario after a sudden earthquake, drones are quickly deployed over the disaster area to establish a temporary communication network. The real-time data collection module starts working to collect various performance indicators of the short message links in the disaster area. After a period of data accumulation, the system generates node aggregation paths and dynamically adjusts the aggregation weights. Subsequently, several key abnormal association clusters are identified through clustering analysis technology. Then, the spatio-temporal coupling relationship of these clusters is quantified as a spatio-temporal coupling coefficient, which is cross-validated with the aggregation weights, and the spatial distribution boundary of the abnormal clusters is corrected. Finally, the system automatically adjusts the distribution density of the drones, optimizes the topological structure of the short message links, greatly improves the communication efficiency in the disaster area, and ensures the smooth progress of the rescue work.

[0084] In summary, steps 201 to 204 form a complete closed-loop feedback mechanism from anomaly detection to optimization and adjustment. This method can dynamically optimize the short message transmission path in a complex environment, greatly improving the reliability and response speed of the short message service in emergency situations. Specifically, it quickly deploys temporary communication facilities, monitors and marks link anomalies in real time, accurately identifies the root cause of problems, and ensures the accuracy of data through spatio-temporal coupling relationships, ultimately achieving efficient and flexible emergency communication support. This system not only improves the adaptive ability and stability of the communication network but also provides strong support at critical moments.

[0085] In some embodiments, quantifying the spatio-temporal coupling relationship of the abnormal association clusters as a spatio-temporal coupling coefficient in step 203, and the spatio-temporal coupling coefficient and the aggregation weight of the node aggregation path form a cross-validation relationship, including: 301. Based on the three-dimensional coordinate distribution of the drone nodes in the emergency area, by dividing geographical grid units and counting the ratio of the number of active nodes to the grid volume, a coverage density index is generated; In step 301, the coverage density index is an index generated based on the three-dimensional coordinate distribution of the drone nodes in the emergency area, and is calculated by dividing geographical grid units and counting the ratio of the number of active nodes to the grid volume. This index is used to evaluate the density of communication resources in a certain area, so as to guide the effective allocation of resources. Geographical grid units refer to dividing the emergency area into multiple small geographical units for statistical analysis.

[0086] In the embodiments of the present application, first, according to the three-dimensional coordinates (longitude, latitude, altitude) of all UAV nodes in the emergency area, the area is divided into uniform geographical grid units (such as a cube of 100m×100m×50m). Secondly, the number of active UAV nodes in each grid unit is counted, and the ratio of it to the grid volume is calculated to obtain the coverage density index (such as number of nodes / m³). Then, the index is smoothed to eliminate the noise influence of the edge grids. Finally, the coverage density index of each grid unit is output to evaluate the distribution density of regional communication resources.

[0087] 302. Statistically analyze the trigger frequency distribution of the SMS link anomaly flag according to a preset time window, generate an anomaly frequency histogram, and extract the duration of the peak interval in the anomaly frequency histogram as the anomaly time aggregation factor; In step 302, the anomaly frequency histogram is the result of statistically analyzing the trigger frequency distribution of the SMS link anomaly flag according to a preset time window, and is used to identify the frequency pattern of anomaly occurrence. The anomaly time aggregation factor is the duration of the peak interval extracted from the anomaly frequency histogram to quantify the time concentration of anomaly occurrence. This factor reflects the aggregation characteristics of anomaly events within a specific time period.

[0088] In the embodiments of the present application, first, count the number of triggers of the SMS link anomaly flag according to a preset time window (such as every 10 minutes) to generate an anomaly frequency histogram of the time-frequency distribution. Secondly, identify the highest frequency interval in the histogram through a peak detection algorithm (such as the frequency in 3 consecutive windows > 5 times), and calculate the duration of this interval. Then, normalize this duration into the anomaly time aggregation factor (such as 0~1, 1 indicates continuous high anomaly). Finally, dynamically adjust the factor weight in combination with historical data to ensure the sensitivity to sudden anomalies.

[0089] 303. Perform weighted fusion on the coverage density index and the anomaly time aggregation factor to generate an initial spatio-temporal coupling coefficient, and at the same time, the weight of the coverage density index is dynamically adjusted according to the priority of the emergency area; In step 303, the initial spatio-temporal coupling coefficient is the result of weighted fusion of the coverage density index and the anomaly time aggregation factor, and is used to comprehensively evaluate the spatio-temporal coupling relationship. The weight of the coverage density index is dynamically adjusted according to the priority of the emergency area to adapt to the demand changes in different emergency situations. This process enables the spatio-temporal coupling coefficient to reflect the actual situation in the area and provide a more accurate evaluation.

[0090] In the embodiments of the present application, first, normalize the coverage density index in step 301 and the abnormal time aggregation factor in step 302 (such as Z-score standardization). Secondly, dynamically allocate weights according to the priority of the emergency area (for example, the coverage density weight of the high-priority area accounts for 70%, and the time aggregation factor accounts for 30%). Then, generate the initial spatio-temporal coupling coefficient through the weighted summation formula (such as coefficient = 0.7×density index + 0.3×time factor). Finally, perform threshold segmentation on the coefficient (such as >0.6 is the high-risk coupling area), and mark the grid cells that need to be monitored key points.

[0091] 304. Extract the weight distribution entropy value of the central area of the abnormal association cluster, and quantify the spatio-temporal coupling relationship into a spatio-temporal coupling coefficient based on the difference degree between the weight distribution entropy value and the initial spatio-temporal coupling coefficient; In step 304, the weight distribution entropy value is a measure of the uncertainty of the importance degree of the node aggregation path in the central area of the abnormal association cluster, and is used to evaluate the uniformity of the node distribution in this area. The initial spatio-temporal coupling coefficient is a value calculated based on the spatio-temporal distance when the abnormal association cluster is initially identified, and is used to measure the strength of its spatial and temporal interaction. The spatio-temporal coupling coefficient is a quantified index adjusted based on the difference degree between the weight distribution entropy value and the initial spatio-temporal coupling coefficient, and is used to more accurately describe the spatio-temporal characteristics of the abnormal association cluster.

[0092] In the embodiments of the present application, first, calculate the weight distribution of the node aggregation path in the central area of the abnormal association cluster, and apply the entropy formula in information theory to calculate the weight distribution entropy value, so as to evaluate the uniformity and complexity of the node distribution. Then, compare this entropy value with the initially determined initial spatio-temporal coupling coefficient, and analyze the difference degree between the two. Then, adjust the spatio-temporal coupling coefficient according to this difference, and use an adaptive algorithm to take the new spatio-temporal characteristics into consideration, so as to update the spatio-temporal coupling coefficient. Finally, integrate all the data to obtain a spatio-temporal coupling coefficient that more accurately reflects the spatio-temporal characteristics of the abnormal association cluster for subsequent analysis.

[0093] Specifically, first, extract the aggregation weights of all nodes in the central area of the abnormal association cluster (such as within a radius of 200m), and calculate its weight distribution entropy value (the higher the entropy value, the more chaotic the weight distribution). Secondly, compare the difference degree between the entropy value and the initial spatio-temporal coupling coefficient (such as difference degree = |entropy value - initial coefficient|). Then, if the difference degree exceeds the tolerance (such as >0.2), adjust the spatio-temporal coupling coefficient proportionally (such as new coefficient = initial coefficient × (1 + difference degree)). Finally, output the corrected spatio-temporal coupling coefficient, which is used to characterize the spatio-temporal stability of the abnormal cluster.

[0094] 305. Construct an aggregation weight-spatiotemporal coupling cross-validation matrix, generate a validation factor by pairwise comparison of the change rate of the aggregation weight gradient and the update amplitude of the spatiotemporal coupling coefficient element by element, and trigger the reconstruction of the spatial distribution boundary of the abnormal association cluster when the validation factor is lower than the confidence threshold.

[0095] In step 305, the aggregation weight-spatiotemporal coupling cross-validation matrix is a two-dimensional matrix that contains data on the change rate of the aggregation weight gradient and the update amplitude of the spatiotemporal coupling coefficient. The change rate of the aggregation weight gradient reflects the rate of change of the importance of the node aggregation path over time, while the update amplitude of the spatiotemporal coupling coefficient represents the degree of change of the spatiotemporal coupling coefficient. The validation factor is a comprehensive evaluation index generated based on the pairwise comparison of the above two types of data, and is used to determine whether it is necessary to reconstruct the spatial distribution boundary of the abnormal association cluster.

[0096] In the embodiment of the present application, first, construct an aggregation weight-spatiotemporal coupling cross-validation matrix, and collect data on the change rate of the aggregation weight gradient and the update amplitude of the spatiotemporal coupling coefficient. Next, apply statistical methods to pairwise compare these two sets of data and calculate the correlation between them. Then, generate a validation factor based on the correlation result. If the factor is lower than the preset confidence threshold, it indicates that the current spatial distribution boundary may be inaccurate or has failed. Finally, when the validation factor is lower than the confidence threshold, automatically trigger the reconstruction process of the spatial distribution boundary of the abnormal association cluster to ensure the high precision and reliability of the system.

[0097] Specifically, first, construct an aggregation weight-spatiotemporal coupling cross-validation matrix. The rows of the matrix represent time windows, the columns represent spatial grids, and the element values are the ratios of the weight gradient change rate to the update amplitude of the spatiotemporal coupling coefficient. Second, calculate the deviation degree of the ratio from the historical mean element by element to generate a validation factor (e.g., factor = 1 - |current ratio / mean - 1|). Then, if the factor is lower than the confidence threshold (e.g., <0.7), it is determined that the spatiotemporal coupling has failed. Finally, trigger the reconstruction of the spatial distribution boundary of the abnormal association cluster, and re-execute steps 301-304 to update the boundary parameters.

[0098] The following is a specific example: In a rescue scenario after a sudden earthquake, drones are quickly deployed over the disaster area to establish a temporary communication network. First, according to the three-dimensional coordinate distribution of drone nodes, geographical grid units are divided and the coverage density index is calculated. Then, the triggering frequency of the abnormal markers of the SMS link is counted, and the abnormal time clustering factor is extracted from it. Next, the coverage density index and the abnormal time clustering factor are weighted and fused, and the weights are dynamically adjusted according to the priority of the emergency area. After that, the weight distribution entropy value of the central area of the abnormal correlation cluster is calculated. Finally, an aggregated weight-spatiotemporal coupling cross-validation matrix is constructed and a validation factor is generated. When the validation factor is lower than the confidence threshold, the reconstruction of the spatial distribution boundary of the abnormal correlation cluster is triggered, optimizing the communication efficiency within the disaster area and ensuring the smooth progress of the rescue work.

[0099] In summary, steps 301 to 305 achieve the accurate quantification and effective verification of the spatiotemporal coupling relationship of the abnormal correlation cluster. This method not only improves the accuracy of anomaly detection in the dynamic communication topology but also enhances the system's self-optimization ability in complex environments, greatly improving the reliability and response speed of emergency communication. This solution provides strong technical support for dealing with emergencies and ensures the timely transmission of critical information. The entire process constructs an efficient, flexible, and secure emergency communication guarantee system through precise data analysis, dynamic threshold adjustment, and effective anomaly marking mechanisms.

[0100] In some embodiments, the triggering of the SMS link abnormal marker when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold in step 101 includes: 401. Analyze the SMS transmission delay gradient based on the difference between adjacent time windows in the SMS link state fluctuation sequence, and perform normalization processing through the cumulative mean of the delay change rate within the sliding window to generate a normalized SMS transmission delay gradient; In step 401, the SMS link state fluctuation sequence records the transmission state of SMS at different time points. The difference between adjacent time windows refers to the change amount of the SMS transmission delay within two consecutive time periods. The SMS transmission delay gradient represents the speed and direction of these delay changes. The sliding window technique is used to observe the change trend of data within a certain length of time period. The cumulative mean is the process of averaging all delay change rates within the sliding window. The normalization processing is the process of converting data into a standard range for convenient comparison and analysis.

[0101] In the embodiments of the present application, first, the system extracts the delay difference data of adjacent time windows (such as 5 - second intervals) from the short - message link - state fluctuation sequence. Secondly, the sliding window technique (window length 30 seconds, step size 5 seconds) is used to calculate the cumulative mean of the delay change rate within each window. Then, the cumulative mean is converted into a normalized short - message transmission delay gradient value within the range of 0 - 1 through the maximum - minimum normalization method. Finally, the system establishes a delay gradient change curve to provide basic data for subsequent threshold adjustment.

[0102] 402. Dynamically adjust the emergency communication threshold according to the historical distribution characteristics of the normalized short - message transmission delay gradient and the gradient change trend within the current window; In step 402, the historical distribution characteristics refer to the data distribution of the normalized short - message transmission delay gradient over a past period of time. The gradient change trend within the current window reflects the development direction of the short - message transmission delay gradient in the latest time period. The emergency communication threshold is a criterion for triggering an alarm or taking actions, which is dynamically adjusted according to real - time data to adapt to changing environmental conditions.

[0103] In the embodiments of the present application, first, analyze the historical distribution characteristics of the normalized short - message transmission delay gradient to determine its normal fluctuation range. Then, evaluate the gradient change trend within the current window to judge whether there is an abnormal increase. Next, based on this two - aspect information, dynamically adjust the emergency communication threshold to ensure that it can timely reflect the latest network conditions. Finally, apply the adjusted threshold to the real - time monitoring system to quickly respond to any situation exceeding the threshold.

[0104] Specifically, first, the system analyzes the normalized delay gradient data within the past 24 hours, and calculates its mean μ and standard deviation σ as the historical distribution characteristics. Secondly, continuously monitor the gradient change trend within the current sliding window. When it is detected that three consecutive windows show a monotonically increasing trend, start the threshold dynamic adjustment mechanism. Then, according to the current network load status (such as the density of drone nodes, channel utilization rate) and the 3σ principle of historical data, set the emergency communication threshold as a dynamic value between μ + 2σ and μ+3σ. Finally, recalculate and update the threshold parameters every 5 minutes.

[0105] 403. When the normalized short - message transmission delay gradient exceeds the adjusted emergency communication threshold, combine the time length and the number of times exceeding the adjusted emergency communication threshold to generate an abnormal - marking trigger condition; In step 403, the abnormal marking trigger condition is generated based on whether the normalized SMS transmission delay gradient exceeds the adjusted emergency communication threshold, the duration of the excess, and the number of times of the excess. This condition is used to determine when to trigger the SMS link abnormal marking to timely discover potential problems. The duration of the excess refers to the time period during which the threshold is exceeded, and the number of times of the excess refers to the frequency of exceeding the threshold. These parameters work together to ensure the accuracy and timeliness of the abnormal marking.

[0106] In the embodiments of the present application, first, it is monitored whether the normalized SMS transmission delay gradient exceeds the adjusted emergency communication threshold. Then, the duration of each excess beyond the threshold and the cumulative number of times are recorded. Then, based on the preset rules, if both the time and the number reach the preset conditions, an abnormal marking trigger condition is generated. Finally, these conditions are applied to the SMS link abnormal analysis module to start further inspection and response processes.

[0107] Specifically, first, the system compares the normalized delay gradient with the dynamic threshold in real time. When the gradient value exceeds the threshold, timing and counting start. Second, two-level trigger conditions are set: the primary condition is that the duration of a single excess beyond the threshold exceeds 10 seconds, and the advanced condition is that the cumulative number of times of exceeding the threshold within 1 minute reaches 3 times. Then, when either condition is met, a corresponding abnormal marking trigger signal is generated, where the advanced condition triggers a more serious abnormal level. Finally, the system records the detailed parameters of each trigger (exceeding amplitude, duration, occurrence location, etc.) to form an abnormal event log.

[0108] 404. Take the normalized SMS transmission delay gradient, the adjusted emergency communication threshold, and the parameters corresponding to the abnormal marking trigger condition as associated parameters, and transfer them to the subsequent SMS link abnormal analysis module to trigger the SMS link abnormal marking.

[0109] In step 404, the associated parameters include the normalized SMS transmission delay gradient, the adjusted emergency communication threshold, and the parameters corresponding to the abnormal marking trigger condition. These parameters are transferred to the subsequent SMS link abnormal analysis module to trigger the SMS link abnormal marking. This step realizes the effective transfer and integration of data and provides a basis for subsequent analysis. The associated parameters not only contain the current delay change information but also reflect the historical trend and real-time status, which helps to comprehensively evaluate the status of the SMS link.

[0110] In the embodiments of the present application, first, relevant data such as the normalized SMS transmission delay gradient, the adjusted emergency communication threshold, and the abnormal marking trigger condition are collected. Then, these data are packaged into associated parameters and sent to the SMS link abnormal analysis module. Then, this module uses these parameters for in-depth analysis to identify possible abnormal situations. Finally, based on the analysis results, it is decided whether to trigger the SMS link abnormal marking to take corresponding corrective measures.

[0111] Specifically, first, the system packages the normalized delay gradient curve, the dynamic threshold curve, and the trigger condition parameters into a structured data packet. Second, the data packet is transmitted to the anomaly analysis module in real time through a dedicated message queue to ensure that the transmission delay is less than 100 ms. Then, after the anomaly analysis module parses the data packet, it first performs a fast mode matching (such as determining whether it conforms to known fault characteristics), and then performs in-depth analysis (such as machine learning model prediction). Finally, when it is confirmed that the anomaly is valid, the system marks the anomaly on the topology map of the affected area and sends an alarm instruction to the relevant drone nodes through the control channel.

[0112] The following is a specific example: In a rescue scenario after a sudden earthquake, drones are quickly deployed over the disaster area to establish a temporary communication network. The real-time data collection module starts to work and collects various performance indicators of the short message link in the disaster area. First, calculate the delay difference between adjacent time windows, and calculate and normalize the short message transmission delay gradient through the sliding window technique. Then, based on historical data and the gradient change trend within the current window, dynamically adjust the emergency communication threshold. When the normalized short message transmission delay gradient exceeds the adjusted emergency communication threshold, an anomaly mark is generated. Finally, the anomaly mark of the short message link is triggered to ensure smooth communication during the rescue operation.

[0113] In summary, steps 401 to 404 achieve precise monitoring and rapid response to the short message link status. This method not only improves the accuracy of delay gradient analysis but also enhances the system's self-optimization ability in complex environments, greatly improving the reliability and response speed of emergency communication. This solution provides strong technical support for dealing with emergencies and ensures the timely transmission of key information.

[0114] In some embodiments, in step 101, forming a dynamic communication topology by deploying a drone cluster to collect the delay mutation rate and packet loss rate data of the damaged short message link in real time and generating a short message link state fluctuation sequence includes: 501. According to the spatial distribution of the damaged short message link and the current channel quality, control the signal strength and interference level of each node in the drone cluster to generate dynamic weight parameters, and form a dynamic communication topology through iterative update of the drone cluster position; In step 501, the dynamic weight parameter is a parameter generated based on the spatial distribution of the damaged SMS link and the current channel quality to control the signal strength and interference level of each node in the UAV cluster. The signal strength refers to the strength of the signal transmitted by the UAV node and is used to ensure the quality of communication; the interference level reflects the degree of interference of the surrounding environment on signal transmission. The dynamic communication topology is a temporary communication network structure formed by the UAV cluster through position iterative update and is used to support emergency communication. Position iterative update is an algorithm that optimizes the overall communication topology structure by adjusting the positions of the UAVs.

[0115] In the embodiment of the present application, first, the optimal signal strength and interference level of each UAV node are evaluated based on the spatial distribution of the damaged SMS link and the current channel quality to generate the dynamic weight parameter. Then, the positions of the nodes are adjusted by using the position iterative update algorithm of the UAV cluster to optimize the overall communication topology structure. This process adopts wireless channel analysis technology and adaptive optimization algorithms to ensure the stability and efficiency of the communication network. Finally, a dynamic communication topology that can quickly respond to changes is formed.

[0116] Specifically, first, the system obtains the spatial distribution heat map of the damaged SMS link and real-time channel quality indicators (such as SNR, RSSI) through GPS positioning and channel detection. Secondly, based on the reinforcement learning algorithm, the optimal signal transmission power (signal strength) and frequency band selection strategy (interference level) are calculated for each UAV node to generate a dynamic weight parameter including position weight, channel weight, and timeliness weight. Then, a distributed consensus algorithm is used to coordinate the cluster nodes, and the optimal topology structure is gradually approximated through three-dimensional position iteration (updated every 30 seconds). Finally, a dynamic communication topology network with self-healing ability is formed, and the key nodes adopt N+1 redundant deployment to ensure reliability.

[0117] 502. In the dynamic communication topology, the delay mutation rate and packet loss rate data of the damaged SMS link are collected at a preset period, and the variance of the packet loss rate within the collected time window is attached to the packet loss rate data as a fluctuation feature; In step 502, the delay mutation rate refers to the rate of change of the delay of the damaged SMS link within a specific time window and is used to describe the change of the delay during the SMS transmission process; the variance of the packet loss rate within the collected time window is attached to the packet loss rate data as a fluctuation feature and is used to describe the proportion of lost data packets and their fluctuations during the data transmission process. These data are collected at a preset period to reflect the real-time state of the SMS link. The preset period refers to the set time interval during which data is collected to ensure the timeliness and accuracy of the data.

[0118] In the embodiments of the present application, first, a damaged SMS link is selected in the dynamic communication topology, and data is collected at a preset period (for example, every 5 minutes). Next, the delay mutation rate of the selected link is calculated, which involves performing differential processing on the delay data at consecutive time points to determine the change speed of the delay. Then, the packet loss rate data within the same time period is collected, and the variance of the packet loss rate within this time window is calculated to quantify the fluctuation of the network performance. Finally, the delay mutation rate, the packet loss rate, and their variances are integrated into a complete set of data, serving as the basis for evaluating the health status of the SMS link.

[0119] Specifically, first, the system identifies all damaged SMS links in the dynamic topology and starts data collection according to an adaptive collection period (initially 5 minutes, dynamically adjusted according to the link stability). Second, the end-to-end delay is measured using the delay probe technology, and the delay mutation rate (unit: ms / s) is calculated through second-order difference. Then, the deep packet inspection technology is used to count the packet loss rate, and the variance of the packet loss rate within a 30-second time window is synchronously calculated as the fluctuation feature. Finally, a precise timestamp to the millisecond level and node location information are attached to each data sample to form a structured monitoring data packet.

[0120] 503. Align the timestamps of the delay mutation rate and packet loss rate data and splice them using a sliding window to generate a time-aligned collection data set, and perform weighted fusion on the collection data set based on the dynamic weight parameter to generate a state fluctuation sequence of the SMS link.

[0121] In step 503, the time-aligned collection data set is a data set generated by aligning the timestamps of the delay mutation rate and packet loss rate data and splicing them using a sliding window. Based on the dynamic weight parameter, weighted fusion is performed on the collection data set to generate a state fluctuation sequence of the SMS link. Timestamp alignment means aligning data from different sources in chronological order to ensure data consistency; sliding window splicing is a technique that splices data in consecutive time periods into a continuous time series. The dynamic weight parameter is used to perform weighted fusion on data in different time periods to generate the final state fluctuation sequence. This sequence contains information on link delay changes and data loss conditions and is used to evaluate the quality of the link.

[0122] In the embodiments of the present application, first, the timestamps of the delay mutation rate and packet loss rate data are aligned, and then the sliding window technology is used to splice data in different time periods into a continuous time series. Next, these data are weighted and fused through the dynamic weight parameter to generate a state fluctuation sequence of the SMS link. In this process, time series analysis and data fusion technologies are applied to ensure data consistency and reliability. The finally generated state fluctuation sequence provides a solid foundation for subsequent anomaly detection and optimization.

[0123] Specifically, first, the system uses a timing alignment algorithm to synchronize the collected data of different nodes at the microsecond level according to the GPS clock. Secondly, a sliding window splicing technique (window length of 1 minute and overlap rate of 50%) is adopted to construct a continuous time-domain dataset. Then, three-level weighted fusion is performed according to dynamic weight parameters: spatial weight (node importance), temporal weight (data freshness), and quality weight (signal-to-noise ratio). Finally, a short message link state fluctuation sequence including the delay mutation rate, packet loss rate, and their variances is generated, encapsulated in JSON format and appended with a digital signature to ensure data integrity.

[0124] The following is a specific example: In a rescue scenario after a sudden earthquake, drones are quickly deployed over the disaster area to establish a temporary communication network. First, based on the spatial distribution of the damaged short message links and the current channel quality, the optimal signal strength and interference level of each drone node are evaluated to generate dynamic weight parameters. Then, the position iteration update algorithm of the drone cluster is used to adjust the positions of each node to obtain a dynamic communication topology. Then, the delay mutation rate and packet loss rate data of the damaged short message links are collected at a preset period (such as every minute). Finally, the sliding window technique is used to splice the time-aligned collected dataset to generate a short message link state fluctuation sequence. This process not only improves the accuracy of data collection but also enhances the optimization ability of the system in complex environments, greatly improving the reliability and response speed of emergency communication.

[0125] In summary, steps 501 to 503 achieve precise monitoring and real-time feedback of the state of damaged short message links. This method not only improves the efficiency of data collection and analysis but also enhances the adaptability and stability of the system in emergencies, providing strong technical support for dealing with emergencies. This solution ensures the timely transmission of key information and guarantees the smooth progress of rescue operations. The whole process constructs an efficient and flexible emergency communication guarantee system by dynamically adjusting the communication topology, precisely collecting link performance data, and generating a state fluctuation sequence.

[0126] In some embodiments, the step of performing timestamp alignment and sliding window splicing on the delay mutation rate and packet loss rate data in step 503 to generate a time-aligned collected dataset includes: 601. Determine a reference time axis based on the clock synchronization protocol of each node in the drone cluster, map the timestamps of the collected delay mutation rate and packet loss rate data to the reference time axis, and generate a timestamp mapping table; In step 601, the reference timeline is a standard timeline determined based on the clock synchronization protocol of each node in the UAV cluster, which is used to unify the time reference of each node. The clock synchronization protocol, such as the Precision Time Protocol or the Network Time Protocol, ensures that all nodes use the same time reference. The timestamp mapping table is a table that maps the timestamps of the collected latency mutation rate and packet loss rate data to the reference timeline, which is used to ensure that all data points are processed within the same time frame. In this way, the data deviation caused by time asynchronization can be eliminated.

[0127] In the embodiment of the present application, first, a clock synchronization protocol is applied in the UAV cluster to ensure that the time of all nodes is consistent, thereby establishing a unified reference timeline. Then, the latency mutation rate and packet loss rate data uploaded by each node are collected, and their original timestamps are recorded. Then, these original timestamps are converted according to the reference timeline to generate a timestamp mapping table, so that each data point can be accurately mapped to a unified time coordinate. Finally, all data and the corresponding timestamp mapping information are integrated to form a complete timestamp mapping table for subsequent data analysis.

[0128] Specifically, first, the UAV cluster adopts PTP (Precision Time Protocol) to achieve microsecond-level clock synchronization and determine the UTC timeline based on the master control node. Secondly, the latency mutation rate and packet loss rate data collected by each node are attached with local timestamps, and the timestamps of each node are uniformly mapped to the reference timeline through a time conversion algorithm. Then, a three-column table including the original timestamp, the reference timestamp, and the data content is established as the timestamp mapping table. Finally, a consistency check is performed on the mapping result to ensure that the time error does not exceed 1 millisecond.

[0129] 602. Linearly interpolate and fill the latency mutation rate and packet loss rate data with missing timestamps according to the timestamp mapping table, using the mean value of adjacent valid data points as the interpolation reference value to generate the interpolated latency mutation rate and packet loss rate data; In step 602, linear interpolation filling is a method used to fill in the data points with missing timestamps. The mean value of adjacent valid data points is used as the interpolation reference value to ensure the accuracy of the interpolation result. The interpolated latency mutation rate and packet loss rate data refer to the time series data after interpolation processing, which ensures the continuity and integrity of the data. This method can effectively reduce the impact of data loss and improve the availability of data.

[0130] In the embodiments of the present application, first, check the timestamp mapping table to identify the data points of the delay mutation rate and packet loss rate with missing timestamps. Then, for each missing data point, find the nearest valid data points before and after it, and calculate the average of these two points as the interpolation reference value. Next, use the linear interpolation method to fill in the missing data points based on the interpolation reference value. Finally, integrate all the original data and interpolation results to generate a complete interpolated dataset of the delay mutation rate and packet loss rate, ensuring that the data is continuous and uninterrupted.

[0131] Specifically, first, the system scans the timestamp mapping table to identify the data breakpoints with a time interval exceeding twice the sampling period. Second, locate the nearest valid data points before and after each missing point (time window ± 3 sampling periods), and calculate the arithmetic mean of the two as the interpolation reference. Then, use the linear weighted algorithm for interpolation, assigning higher weights (0.7:0.3) to the data points closer in distance. Finally, generate a complete dataset including the original data and the blue interpolated data, and mark the interpolation source in the data flag bit.

[0132] 603. Divide the interpolated delay mutation rate and packet loss rate data into multiple overlapping sliding windows, perform start and end timestamp calibration and boundary data smoothing processing to generate the delay mutation rate segments and packet loss rate segments aligned within the window. In step 603, the sliding window refers to dividing the data into multiple overlapping time periods, and each window contains a certain number of data points. The start and end timestamp calibration is to adjust the start and end timestamps of each window to ensure time alignment. The boundary data smoothing processing is to smooth the data at the window edges to reduce noise interference. The delay mutation rate segments and packet loss rate segments aligned within the window refer to the time series data segments after the above processing. These processing measures help to improve the quality and consistency of the data.

[0133] In the embodiments of the present application, divide the interpolated delay mutation rate and packet loss rate data into multiple overlapping sliding windows. Perform start and end timestamp calibration for each window to ensure time alignment. Then, smooth the data at the window edges to reduce noise interference. The sliding window technique and data smoothing algorithm are applied in this process to ensure the time alignment and quality of the data. Finally, generate the delay mutation rate segments and packet loss rate segments aligned within the window.

[0134] Specifically, first, divide the continuous data stream into sliding windows with a length of 60 seconds and an overlap rate of 30%. Secondly, perform boundary calibration on each window: align the front boundary backward to the nearest whole second, and ensure that the rear boundary contains a complete data cycle. Then, use the Savitzky-Golay filter for boundary smoothing, and fit the edge data with a 21-point quadratic polynomial. Finally, output the calibrated and smoothed fragments of the delay mutation rate and the packet loss rate, with each fragment attached with a window ID and a boundary marker.

[0135] 604. Concatenate the delay mutation rate fragments and the packet loss rate fragments in chronological order into a delay-packet loss joint data block in a unified time dimension, and extract the time coverage range and data density as window metadata to generate a time-aligned acquisition data set.

[0136] In step 604, the delay-packet loss joint data block is a data set in a unified time dimension formed by concatenating the delay mutation rate fragments and the packet loss rate fragments in chronological order. The window metadata includes information such as the time coverage range and data density, which is used to describe the data characteristics of each window. The time-aligned acquisition data set is a set composed of multiple window metadata, which is used for subsequent analysis. These metadata help to better understand the overall situation of the data and support more refined data analysis and optimization.

[0137] In the embodiment of the present application, first, arrange the delay mutation rate and packet loss rate data processed in step 602 in chronological order and merge them into a delay-packet loss joint data block in a unified time dimension. Then, calculate the time coverage range and data density of this data block, and extract this information as window metadata. Then, further optimize the organization form of the data set based on the window metadata to ensure that all data is under the same time reference. Finally, integrate all processing results to generate the final time-aligned acquisition data set, providing a prepared data basis for subsequent analysis.

[0138] Specifically, first, splice the processed data fragments into continuous data blocks in chronological order to establish a two-dimensional matrix of delay-packet loss rate. Secondly, calculate the key metadata of each data block: the time coverage range (start and end time difference) and data density (effective sampling points / theoretical sampling points). Then, organize the data blocks using a B+ tree index structure and establish a fast query index with the time range as the primary key. Finally, generate a complete acquisition data set including raw data, processed data, and metadata, and store it in a columnar compression format.

[0139] The following is a specific example: In a rescue scenario after a sudden earthquake, to ensure that all devices in the UAV cluster can work synchronously, the system applies a clock synchronization protocol to create a reference timeline. Subsequently, the data of the delay mutation rate and packet loss rate collected from the damaged SMS link are assigned with original timestamps, and are converted into positions on the reference timeline through a timestamp mapping table. When it is found that there are missing data of the delay mutation rate and packet loss rate in certain time periods, the system adopts a linear interpolation method to fill them. By calculating the mean value of adjacent valid data points as the interpolation reference value, the system successfully fills these gaps, making the entire dataset more complete. The system stitches together all the processed data segments of the delay mutation rate and packet loss rate in chronological order to form a joint delay and packet loss data block in a unified time dimension. By analyzing the time coverage range and data density of these data, the system extracts key window metadata. This series of operations helps the rescue team better understand the trend of network state changes, take timely measures to address potential problems, and improve the rescue efficiency and success rate.

[0140] In summary, steps 601 to 604 achieve precise monitoring and real-time feedback of the state of the damaged SMS link. This method not only improves the efficiency of data collection and analysis, but also enhances the adaptability and stability of the system in emergency situations, providing strong technical support for dealing with emergencies. The entire process constructs an efficient and flexible emergency communication guarantee system through technical means such as time alignment, interpolation filling, and sliding window stitching. This solution ensures the timely transmission of key information and guarantees the smooth progress of rescue operations. Finally, these steps work together to form a system that can quickly respond to changes and provide high-quality data support, greatly improving the reliability and efficiency of emergency communication.

[0141] In some embodiments, in step 103, the multi-node parallel archiving of binding the time stamps to the abnormal association cluster and the SMS link state migration characteristics to generate a blockchain state change event including the SMS link state fluctuation sequence includes: 701. Perform timestamp binding processing on the abnormal feature vector of the abnormal association cluster and the dynamic feature vector of the SMS link state migration feature through a time window sliding alignment mechanism to generate a group of abnormal state joint feature vectors; In step 701, the abnormal feature vector is a data set describing the characteristics of the abnormal association cluster, including indicators such as the delay mutation rate and packet loss rate; the dynamic feature vector is a data set reflecting the SMS link state migration characteristics, such as transmission path changes, node aggregation weights, etc. The time window sliding alignment mechanism is a technology that makes the timestamps of data from different sources consistent by adjusting the time window, generating a group of abnormal state joint feature vectors. This vector group contains the time-synchronized data of all relevant features for subsequent analysis and processing.

[0142] In the embodiments of the present application, first, the abnormal feature vectors of the abnormal association cluster and the dynamic feature vectors of the short message link state migration features are processed for timestamp binding through a time window sliding alignment mechanism. The sliding window technology and time series analysis algorithm are adopted to ensure that data from different sources are processed under the same time frame. The finally generated combined abnormal state feature vector group contains the time-synchronized data of all relevant features, providing a basis for subsequent data processing.

[0143] Specifically, first, the system extracts multi-dimensional abnormal feature vectors (including indicators such as delay mutation rate, packet loss rate variance, and spatial distribution density) from the abnormal association cluster, and at the same time extracts dynamic feature vectors (including parameters such as the number of path jumps and weight change gradients) from the state migration features. Secondly, the dynamic time warping algorithm (DTW) is used to align the time dimensions of the two feature sequences, and millisecond-level timestamp synchronization is achieved through a sliding window mechanism (window length 10 seconds, step size 2 seconds). Then, the aligned feature vectors are normalized (Z-score normalization), and finally, they are concatenated in time order to generate a combined abnormal state feature vector group with a unified dimension, and each vector is attached with a timestamp label accurate to the millisecond.

[0144] 702. Split the combined abnormal state feature vector group into multiple parallel evidence storage sub-units according to the timestamp label, and perform hash evidence storage to generate an evidence storage hash chain, and perform cross-node cross-verification to construct an evidence storage topology structure; In step 702, the combined abnormal state feature vector group refers to a set of a series of eigenvalue representing different abnormal states extracted from the short message link. The timestamp label is the time identifier of each feature vector, used to determine its position in the time series. The parallel evidence storage sub-unit is a small data block formed by splitting the feature vectors according to the timestamp, which is convenient for distributed storage and verification. Hash evidence storage is to use the hash algorithm to encrypt the data to ensure data integrity and non-tamperability. The evidence storage hash chain is a chain composed of a series of connected hash values, and each hash value is calculated based on the previous hash value. The evidence storage topology structure is a network structure formed through cross-node cross-verification, used to enhance the security and reliability of the data.

[0145] In the embodiments of the present application, first, the combined abnormal state feature vector group is split into multiple parallel evidence storage sub-units according to the timestamp label. Then, the hash algorithm is applied to each sub-unit to generate the corresponding hash value, and an evidence storage hash chain is constructed based on this. Then, cross-node cross-verification is performed to ensure that the data on each node is consistent and not tampered with. Finally, based on the verification results, a distributed evidence storage topology structure is constructed, which not only enhances data security but also improves the fault tolerance of the system.

[0146] Specifically, first, the system divides the combined feature vector group into fixed-size evidence storage sub-units according to timestamps (each unit contains 30 seconds of data), and organizes the data blocks using the Merkle tree structure. Second, perform double hashing operations (SHA-256 + SM3) on each sub-unit to generate an evidence storage hash chain containing forward hash pointers. Then, perform cross-verification among at least 5 nodes through the Byzantine fault tolerance mechanism, and require more than 3 / 5 of the nodes to reach a consensus to confirm the data validity. Finally, construct a multi-level evidence storage topology structure based on the verification results, where the main chain nodes store the complete hash chain, and the edge nodes store the local verification results, forming a hierarchical verification network.

[0147] 703. Extract the state coding values corresponding to the short message link state transition features for each timestamp label in the evidence storage topology structure, and perform fluctuation fitting on the state coding values according to the state transition relationship in ascending order of timestamps to generate a short message link state fluctuation sequence; In step 703, the state coding value is a quantitative representation form of the short message link state transition feature, which is convenient for computer processing. The state transition relationship describes the pattern of the short message link state changing over time. Fluctuation fitting is a statistical method used to identify and predict the change trend of data. The short message link state fluctuation sequence is a set of state coding values arranged in chronological order, reflecting the dynamic change process of the short message link state.

[0148] In the embodiment of the present application, first, extract the state coding values of the short message link state transition features corresponding to each timestamp label in the evidence storage topology structure. Next, analyze the state transition relationship according to the ascending order of timestamps, and use the fluctuation fitting technology to process the state coding values. Then, through fluctuation fitting, identify the trend of the state coding values changing over time, and generate a short message link state fluctuation sequence. Finally, integrate all the information to form a complete short message link state fluctuation sequence, providing basic data for subsequent analysis.

[0149] Specifically, first, extract the state coding values corresponding to each timestamp from the evidence storage topology (8-bit binary coding, each bit representing a specific state flag). Second, use the hidden Markov model to analyze the state transition probability and establish a time-dependent relationship matrix. Then, repair the missing coding through cubic spline interpolation, and use the Kalman filter to eliminate the observation noise. Finally, arrange the processed coding values in chronological order, append the sliding window statistics (mean, variance, range), and generate a standardized short message link state fluctuation sequence, with the data interval accurate to 100 milliseconds.

[0150] 704. Package and bind the short message link state fluctuation sequence with the evidence storage hash chain to generate a blockchain state change event containing the short message link state fluctuation sequence.

[0151] In step 704, event encapsulation binding is the process of combining the SMS link status fluctuation sequence with the deposit hash chain to form a complete blockchain state change event. This event contains all relevant data and verification information to ensure data integrity and traceability. The blockchain state change event is an immutable record for long-term storage and verification.

[0152] In the embodiments of the present application, first, the generated SMS link status fluctuation sequence is matched and associated with the deposit hash chain. Then, blockchain technology is used to perform event encapsulation on these two parts of data to create a new blockchain state change event. Next, through the consensus mechanism, it is ensured that this event is recognized and recorded by all nodes in the network. Finally, this event is added to the blockchain to form a permanent record containing the SMS link status fluctuation sequence, ensuring data integrity and immutability.

[0153] Specifically, first, the status fluctuation sequence and the deposit hash chain are logically bound through a smart contract to construct an event structure including the following elements: ① event header (block height, timestamp); ② data body (compressed fluctuation sequence); ③ verification information (Merkle root, digital signature); ④ association pointer (previous event hash). Secondly, it is broadcast across the network through an improved DPoS consensus mechanism (Delegated Proof of Stake), requiring at least 51% of the accounting nodes to confirm. Then, the confirmed event is written into the blockchain in chronological order, and side chain technology is used to store large-capacity fluctuation sequence data. Finally, a receipt containing the unique identifier of the event is generated for subsequent query and verification.

[0154] The following is a specific example: In a rescue scenario after a sudden earthquake, drones were quickly deployed over the disaster area to establish a temporary communication network. First, the system divided the abnormal state joint feature vector group into multiple parallel evidence storage sub-units according to the timestamp tags. Subsequently, hash-based evidence storage was performed on these sub-units to generate an evidence storage hash chain. To ensure the authenticity and integrity of the data, the system performed cross-node cross-verification to confirm that the data of all nodes was correct. Then, the system extracted the state coding values corresponding to each timestamp tag from the evidence storage topology. In ascending order of timestamps, the system analyzed the state transition relationship and processed the data using fluctuation fitting technology to generate a short message link state fluctuation sequence. This step helped the rescue team better understand the change trend of the short message link state, enabling them to more effectively address communication bottleneck problems and ensure the rapid transmission of emergency information. Finally, during the earthquake rescue process, the system encapsulated and bound the short message link state fluctuation sequence with the evidence storage hash chain to generate a blockchain state change event. This process not only ensured the integrity and authenticity of the data but also enabled all relevant parties to track and verify the data in real time. This method greatly improved the transparency and efficiency of emergency response, ensured the reliable transmission of key information, and laid a solid foundation for the successful implementation of rescue operations.

[0155] In summary, steps 701 to 704 achieved precise monitoring and real-time feedback of abnormal association clusters and short message link state migration characteristics. This method not only improved the efficiency of data collection and analysis but also enhanced the adaptability and stability of the system in emergency situations, providing strong technical support for dealing with emergencies. The entire process constructed an efficient, flexible, and secure emergency communication guarantee system through technical means such as time alignment, hash-based evidence storage, and state fitting. This solution ensured the timely transmission of key information and guaranteed the smooth progress of rescue operations. Finally, these steps worked together to form a system that could quickly respond to changes and provide high-quality data support, greatly improving the reliability and efficiency of emergency communication.

[0156] Figure 2 The following is a schematic structural diagram of a system for an intelligent high-efficiency detection method of a short message link provided by an embodiment of the present application, as Figure 2 shown. The device includes: A collection module 21, which forms a dynamic communication topology by deploying a drone cluster to collect data on the delay mutation rate and packet loss rate of damaged short message links in real time, generates a short message link state fluctuation sequence, and triggers a short message link abnormality mark when the short message transmission delay gradient in the short message link state fluctuation sequence exceeds the emergency communication threshold; The recognition module 22 performs SMS link state migration detection on the dynamic communication topology based on the SMS link state fluctuation sequence, identifies abnormal correlation clusters of the transmission path, and forms a spatio-temporal coupling relationship with the SMS link anomaly mark; The generation module 23 binds time stamps to the abnormal correlation clusters and SMS link state migration features for multi-node parallel archiving, and generates a blockchain state change event including the SMS link state fluctuation sequence; The update module 24 adjusts the distribution density of the drones according to the verification result of the blockchain state change event, generates an SMS link topology reconstruction factor, and forms a closed-loop feedback with the spatio-temporal coupling relationship to update the topology association detection path of SMS transmission.

[0157] Figure 2 The intelligent SMS link high-efficiency detection method system described above can execute Figure 1 The intelligent SMS link high-efficiency detection method described in the embodiments shown, the implementation principle and technical effects will not be elaborated. For the intelligent SMS link high-efficiency detection system in the above embodiments, the specific manners of operations of each module and unit have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0158] In a possible design, Figure 2 The intelligent SMS link high-efficiency detection system of the embodiments shown can be implemented as a computing device, such as Figure 3 shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0159] The processing component 32 is used for the intelligent SMS link high-efficiency detection method of the above Figure 1 embodiments.

[0160] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0161] The storage component 31 is configured to store various types of data to support the operations of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0162] Of course, the computing device may necessarily further include other components, such as an input / output interface, a display component, a communication component, and the like.

[0163] The input / output interface provides an interface between the processing component and the peripheral interface module, and the peripheral interface module may be an output device, an input device, or the like.

[0164] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0165] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0166] The embodiments of the present application also provide a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 intelligent short message link efficient detection method shown in the above embodiments.

[0167] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0168] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent SMS link efficient detection method, characterized in that: include: By deploying a drone cluster to form a dynamic communication topology, the delay mutation rate and packet loss rate data of the damaged SMS link are collected in real time, and a SMS link state fluctuation sequence is generated. When the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold, the SMS link abnormality mark is triggered; Based on the SMS link state fluctuation sequence, SMS link state migration detection is performed on the dynamic communication topology to identify abnormal associated clusters of the transmission path and form a spatiotemporal coupling relationship with the SMS link abnormality mark; Bind the abnormal association cluster and the SMS link state migration feature to timestamps for multi-node parallel storage, and generate a blockchain state change event containing the SMS link state fluctuation sequence; The distribution density of drones is adjusted according to the verification result of the blockchain state change event, a short message link topology reconstruction factor is generated, and a closed-loop feedback is formed with the space-time coupling relationship to update the topological association detection path of the short message transmission.

2. The method according to claim 1, characterized in that The method of performing SMS link state migration detection on the dynamic communication topology based on the SMS link state fluctuation sequence, identifying abnormal associated clusters of the transmission path, and forming a spatiotemporal coupling relationship with the SMS link abnormality mark includes: Generate a node aggregation path based on the SMS link state fluctuation sequence, dynamically adjust the aggregation weight according to the delay gradient and packet loss rate of adjacent nodes, and form a positive feedback association with the trigger condition of the SMS link abnormality mark; Performing SMS link state migration detection on the dynamic communication topology, identifying abnormal associated clusters of transmission paths in the distribution characteristics of the node aggregation path and the SMS link state fluctuation sequence; quantifying the spatiotemporal coupling relationship of the abnormal association cluster into a spatiotemporal coupling coefficient, wherein the spatiotemporal coupling coefficient forms a cross-validation relationship with the aggregation weight of the node aggregation path; The spatial distribution boundary of the abnormal association cluster is corrected based on the cross-validation relationship, and the abnormal association cluster correction parameter is generated, and is fed back to the dynamic spatial association analysis process of the SMS link state fluctuation sequence through the node aggregation path.

3. The method according to claim 2, characterized in that The step of quantifying the spatiotemporal coupling relationship of the abnormal associated cluster into a spatiotemporal coupling coefficient, wherein the spatiotemporal coupling coefficient forms a cross-validation relationship with the aggregation weight of the node aggregation path, includes: Based on the three-dimensional coordinate distribution of drone nodes in the emergency area, the coverage density index is generated by dividing the geographic grid units and counting the ratio of the number of active nodes to the grid volume; Counting the trigger frequency distribution of SMS link abnormality marks according to a preset time window, generating an abnormal frequency histogram, and extracting the duration of the peak interval in the abnormal frequency histogram as an abnormal time aggregation factor; The coverage density index and the abnormal time agglomeration factor are weightedly integrated to generate an initial spatiotemporal coupling coefficient, and the weight of the coverage density index is dynamically adjusted according to the priority of the emergency area; Extracting a weight distribution entropy value of a central region of the abnormal association cluster, and quantifying the spatiotemporal coupling relationship into a spatiotemporal coupling coefficient based on a difference between the weight distribution entropy value and the initial spatiotemporal coupling coefficient; An aggregation weight-space-time coupling cross-validation matrix is ​​constructed, and a verification factor is generated by comparing the correlation between the aggregation weight gradient change rate and the space-time coupling coefficient update amplitude element by element. When the verification factor is lower than the confidence threshold, the spatial distribution boundary reconstruction of the abnormal association cluster is triggered.

4. The method according to claim 1, characterized in that: The triggering of the SMS link abnormality mark when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold includes: Analyzing the SMS transmission delay gradient based on the difference between adjacent time windows in the SMS link state fluctuation sequence, performing normalization processing through the cumulative mean of the delay change rate in the sliding window, and generating a normalized SMS transmission delay gradient; Dynamically adjust the emergency communication threshold according to the historical distribution characteristics of the normalized SMS transmission delay gradient and the gradient change trend in the current window; When the normalized SMS transmission delay gradient exceeds the adjusted emergency communication threshold, an abnormal marking trigger condition is generated in combination with the time length and the number of times the adjusted emergency communication threshold is exceeded; The normalized SMS transmission delay gradient, the adjusted emergency communication threshold and the parameters corresponding to the abnormal mark triggering condition are passed as associated parameters to the SMS link abnormality analysis module to trigger the SMS link abnormality mark.

5. The method according to claim 1, characterized in that The method forms a dynamic communication topology by deploying a drone cluster to collect the delay mutation rate and packet loss rate data of the damaged SMS link in real time and generate a SMS link state fluctuation sequence, including: According to the spatial distribution of damaged SMS links and the current channel quality, the signal strength and interference level of each node in the drone cluster are controlled, dynamic weight parameters are generated, and a dynamic communication topology is formed through iterative updates of the drone cluster position; In the dynamic communication topology, the delay mutation rate and packet loss rate data of the damaged SMS link are collected according to a preset period, and the packet loss rate data is additionally collected with the packet loss rate variance within the time window as a fluctuation feature; The delay mutation rate and packet loss rate data are timestamp aligned and sliding window spliced ​​to generate a time-aligned collection data set, and the collection data set is weightedly fused based on the dynamic weight parameter to generate a short message link status fluctuation sequence.

6. The method according to claim 5, characterized in that The performing timestamp alignment and sliding window splicing on the delay mutation rate and packet loss rate data to generate a time-aligned collection data set includes: Determine a reference time axis based on the clock synchronization protocol of each node in the drone cluster, map the timestamps of the collected delay mutation rate and packet loss rate data to the reference time axis, and generate a timestamp mapping table; Performing linear interpolation filling on the delay mutation rate and packet loss rate data of the missing timestamps according to the timestamp mapping table, taking the mean of the adjacent valid data points as the interpolation reference value, and generating the delay mutation rate and packet loss rate data after interpolation; Dividing the interpolated delay mutation rate and packet loss rate data into multiple overlapping sliding windows, performing head and tail timestamp calibration and boundary data smoothing processing, and generating delay mutation rate segments and packet loss rate segments aligned within the windows; The delay mutation rate fragments and the packet loss rate fragments are spliced ​​in chronological order into a delay-packet-loss joint data block of a unified time dimension, and the time coverage and data density are extracted as window metadata to generate a time-aligned acquisition data set.

7. The method according to claim 1, characterized in that The method of binding the abnormal association cluster and the SMS link state migration feature to a timestamp for multi-node parallel evidence storage to generate a blockchain state change event containing the SMS link state fluctuation sequence includes: Perform timestamp binding processing on the abnormal feature vector of the abnormal association cluster and the dynamic feature vector of the SMS link state transition feature through a time window sliding alignment mechanism to generate an abnormal state joint feature vector group; Divide the abnormal state joint feature vector group into multiple parallel evidence sub-units according to the timestamp label, perform hash evidence, generate an evidence hash chain, perform cross-node cross-validation, and build an evidence topology structure; Extract the state code value of the SMS link state transition feature corresponding to each timestamp tag in the evidence topology structure, perform fluctuation fitting on the state code value according to the state transition relationship in ascending order of timestamps, and generate a SMS link state fluctuation sequence; The SMS link state fluctuation sequence is event-encapsulated and bound to the evidence hash chain to generate a blockchain state change event containing the SMS link state fluctuation sequence.

8. An intelligent SMS link efficient detection system, characterized in that: include: The collection module deploys a drone cluster to form a dynamic communication topology to collect the delay mutation rate and packet loss rate data of the damaged SMS link in real time, generate an SMS link state fluctuation sequence, and trigger an SMS link abnormality mark when the SMS transmission delay gradient in the SMS link state fluctuation sequence exceeds the emergency communication threshold; An identification module, based on the SMS link state fluctuation sequence, performs SMS link state migration detection on the dynamic communication topology, identifies abnormal association clusters of the transmission path, and forms a spatiotemporal coupling relationship with the SMS link abnormality mark; A generation module binds the abnormal association cluster and the SMS link state migration feature to a timestamp for multi-node parallel evidence storage, and generates a blockchain state change event containing the SMS link state fluctuation sequence; The update module adjusts the distribution density of the drones according to the verification result of the blockchain state change event, generates a short message link topology reconstruction factor, forms a closed-loop feedback with the space-time coupling relationship, and updates the topological association detection path of the short message transmission.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent SMS link efficient detection method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an intelligent short message link efficient detection method as described in any one of claims 1 to 7 is implemented.

Images