Cross-system hierarchical perception routing decision method, apparatus and device, and storage medium

Abstract

The invention belongs to the technical field of cross-domain network communication, and discloses a cross-system hierarchical sensing routing decision method, device and equipment and a storage medium. According to the method, a routing optimization scheme oriented to a cross-domain network is provided, hierarchical network performance collection is carried out by embedding a service level identifier and a time stamp in a detection data packet, differential thresholds are set according to different service types, and collected time delay, jitter, packet loss and bandwidth utilization data are comprehensively evaluated. And quantitatively adjusting the path priority attribute in the border gateway protocol according to the evaluation result, and driving the automatic switching of the transmission path. According to the method, the defect that data and services are disjointed in traditional detection is overcome; according to the method, a dynamic threshold value is set in combination with service requirements, multi-index comprehensive judgment is carried out, finally, a performance evaluation result and routing protocol attributes are linked, an automatic closed loop from sensing to decision making is established, and therefore the overall reliability and experience of cross-domain service transmission are improved under the condition that opposite-end cooperation is not needed.

Description

Technical Field

[0001] This application relates to the field of cross-domain network communication technology, and in particular to a cross-system hierarchical awareness routing decision method, apparatus, device and storage medium. Background Technology

[0002] With the deepening of digitalization, the operation of critical urban information infrastructure such as power, transportation, and finance increasingly relies on stable and efficient data communication. The business systems of these facilities often span multiple administrative divisions or management domains, requiring data transmission and exchange over wide area networks comprised of autonomous systems from different operators or institutions. Therefore, achieving efficient and reliable scheduling of cross-domain (or cross-system) network traffic has become crucial for ensuring the normal operation of cities.

[0003] In existing technical implementations, the Border Gateway Protocol (BGP) primarily serves as the de facto standard for inter-domain routing on the Internet, undertaking the core functions of cross-system routing information exchange and path selection. However, the traditional decision-making mechanism of this protocol mainly relies on static, policy-based routing attributes such as autonomous system path length and multi-exit authentication attributes. This decision-making process is completely independent of the real-time transmission quality status of the network. In practice, the "optimal" path selected by the protocol often faces problems such as high latency, high jitter, or high packet loss in actual transmission, leading to a decline in the experience of critical services and making it difficult to meet the stringent network performance requirements of critical infrastructure.

[0004] Therefore, in cross-domain transmission scenarios, how to design a method that can deeply integrate real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The main objective of this application is to provide a cross-system hierarchical awareness routing decision-making method, apparatus, device, and storage medium, aiming to solve the technical problem in the prior art of how to design a method that can deeply integrate real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling.

[0006] To achieve the above objectives, this application proposes a cross-system hierarchical awareness routing decision method, the method comprising: Based on the preset detection targets, layered network detection is performed to obtain network performance detection data for each external gateway link; Based on the network performance detection data, a link quality assessment is performed to obtain the path performance assessment result of the external gateway link; Based on the path performance evaluation results, the gateway links to be optimized are identified; According to the preset routing policy adjustment process, a routing update operation is performed on the gateway link to be optimized in order to optimize global traffic scheduling.

[0007] Optionally, the step of performing layered network probing based on preset detection targets to obtain network performance detection data for each external gateway link includes: Based on multiple preset detection targets, a hierarchical detection data packet sequence is constructed; By sending the hierarchical probe data packet sequence to the peer gateway of the external gateway link and parsing the returned information, network status interaction data is obtained; Obtain the associated marker information from the probe data payload, the associated marker information including probe type identifier and service priority; Based on the network status interaction data and the associated tag information, network performance detection data is obtained, which includes link latency characteristics, jitter characteristics, packet loss characteristics, and bandwidth utilization characteristics.

[0008] Optionally, constructing a hierarchical detection data packet sequence based on multiple preset detection targets includes: According to a preset baseline detection strategy, a base layer detection data packet sequence is constructed. The base layer detection data packet sequence consists of detection data packets that satisfy a first preset data payload and are sent at a first preset frequency. According to the preset jitter simulation strategy, a jitter layer probe data packet sequence is constructed. The jitter layer probe data packet sequence consists of probe data packets that satisfy the preset micro-burst mode and are sent at a second preset frequency. According to the preset load testing strategy, a stress layer probe data packet sequence is constructed. The stress layer probe data packet sequence consists of probe data packets that meet the second preset data load and are sent at the third preset frequency. The second preset frequency is greater than the third preset frequency, the third preset frequency is greater than the first preset frequency, and the second preset data load is greater than the first preset data load. The base layer probe data packet sequence, the jitter layer probe data packet sequence, and the stress layer probe data packet sequence are integrated to obtain the layered probe data packet sequence.

[0009] Optionally, the step of obtaining network status interaction data by sending the hierarchical probe data packet sequence to the peer gateway of the external gateway link and parsing the returned information includes: The basic layer probe data packet sequence is sent and received through a preset first network path, and the delay reference measurement result is obtained based on the transmission timestamp information in the received data; The jitter layer probe data packet sequence is sent and received through a preset second network path, and the network jitter characteristic analysis results are obtained based on the arrival interval information in the received data. The pressure layer probe data packet sequence is sent and received through a preset third network path, and the packet loss rate analysis result and available bandwidth analysis result are obtained based on the transmission status information in the received data. The network status interaction data is obtained based on the latency benchmark measurement results, network jitter characteristic analysis results, packet loss rate analysis results, and available bandwidth analysis results.

[0010] Optionally, the step of performing link quality assessment based on the network performance probe data to obtain the path performance assessment result of the external gateway link includes: Based on the link latency index in the network performance detection data and the preset latency degradation threshold, a link latency score is obtained; Based on the transmission jitter index in the network performance detection data and the preset jitter degradation threshold, the link jitter score is obtained; Based on the transmission packet loss index in the network performance detection data and the preset packet loss rate degradation threshold, the link packet loss rate score is obtained. Based on the bandwidth utilization index in the network performance detection data and the preset bandwidth utilization degradation threshold, the link bandwidth congestion score is obtained. Based on a comprehensive analysis of the link latency score, link jitter score, link packet loss rate score, and link bandwidth congestion score, a path performance evaluation result is generated that characterizes the overall performance degradation of the external gateway link.

[0011] Optionally, the step of performing a route update operation on the gateway link to be optimized to optimize global traffic scheduling according to a preset routing policy adjustment process includes: Based on the preset path impact parameter adjustment rules and the path performance evaluation results, the multi-exit authentication attribute values ​​of each external gateway link are updated to obtain the updated multi-exit authentication attribute values. Based on the multi-exit identification attribute value, a border gateway protocol routing update message is generated, the update message including the destination network prefix and the next-hop path; The Border Gateway Protocol routing update message is sent to the neighboring device so that the neighboring device can re-execute path selection based on the updated multi-exit authentication attribute value and obtain the updated gateway link. Cross-domain traffic scheduling is performed based on the updated gateway link, thereby achieving optimized scheduling of global traffic.

[0012] Optionally, the cross-system hierarchical awareness routing decision method further includes: After the Border Gateway Protocol routing update message is sent to the neighboring device, a verification probe is performed on the updated gateway link to obtain verification network performance data. Based on the verifiable network performance data and the preset optimization threshold, it is determined whether the routing update operation has achieved the expected scheduling optimization effect. If the judgment result is that the expected scheduling optimization effect has not been achieved, then based on the verifiable network performance data, the parameters in the path influence parameter adjustment rules are adjusted to fine-tune the path attribute values ​​of the gateway link to be optimized, and the route update operation is re-executed based on the fine-tuned path attribute values.

[0013] Furthermore, to achieve the above objectives, this application also proposes a cross-system hierarchical awareness routing decision-making device, which includes: The detection module is used to perform layered network detection based on preset detection targets to obtain network performance detection data for each external gateway link; The transmission evaluation module is used to perform link quality evaluation processing based on the network performance detection data to obtain the path performance evaluation result of the external gateway link; The decision module is used to determine the gateway links to be optimized based on the path performance evaluation results. The routing update module is used to adjust the process according to the preset routing policy and perform routing update operations on the gateway link to be optimized in order to optimize global traffic scheduling.

[0014] Furthermore, to achieve the above objectives, this application also proposes a cross-system hierarchical awareness routing decision device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the cross-system hierarchical awareness routing decision method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the cross-system hierarchical awareness routing decision method described above.

[0016] The proposed technical solutions (one or more) in this application have at least the following technical effects: This solution, through the design of a hierarchical detection mechanism associated with service types, collects multi-dimensional network performance data in real time, including latency, jitter, and packet loss rate, and performs a comprehensive evaluation based on thresholds set according to service requirements. When path performance is determined to be degraded, the relevant path attributes of the border gateway protocol are quantitatively adjusted according to the evaluation results, achieving automatic switching and forming a state-aware dynamic routing adjustment closed loop. This solution solves the problem that traditional border gateway protocols rely solely on static attributes for routing and cannot perceive real-time link quality. Because it quantitatively links performance evaluation results with routing protocol attributes, routing decisions can respond promptly to dynamic changes in network status, shifting from passive routing to proactive optimization. This enhances the adaptability of cross-domain transmission to service requirements, thereby effectively improving the reliability and stability of critical services transmitted between different autonomous systems. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the hierarchical awareness routing decision method across systems in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the cross-system hierarchical awareness routing decision method of this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the cross-system hierarchical awareness routing decision method of this application; Figure 4 This is a schematic diagram of the module structure of the cross-system hierarchical perception routing decision device according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the cross-system hierarchical awareness routing decision method in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] In this embodiment, for ease of description, the following description uses a cross-system hierarchical awareness routing decision device as the execution subject.

[0024] This application proposes a routing optimization scheme for cross-domain networks. It performs hierarchical network performance collection by embedding service layer identifiers and timestamps into probe packets. Differential thresholds are set according to different service types, and the collected latency, jitter, packet loss, and bandwidth utilization data are comprehensively evaluated. Based on the evaluation results, the path priority attribute in the border gateway protocol is quantitatively adjusted to drive automatic switching of transmission paths. This method overcomes the defect of data and service disconnect in traditional probes. By setting dynamic thresholds based on service requirements and performing comprehensive judgment of multiple indicators, and finally linking the performance evaluation results with routing protocol attributes, an automatic closed loop from perception to decision-making is established. This improves the overall reliability and experience of cross-domain service transmission without requiring cooperation from the peer end.

[0025] This application provides a solution aimed at addressing the technical problem of the lack of a global resource scheduling mechanism in the prior art, which can dynamically perceive task characteristics, coordinate computing and communication resources, and thus achieve overall performance optimization.

[0026] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a cross-system hierarchical awareness routing decision-making device capable of performing the above functions. The following description uses a cross-system hierarchical awareness routing decision-making device as the executing entity to illustrate this embodiment and the subsequent embodiments.

[0027] Based on this, embodiments of this application provide a cross-system hierarchical awareness routing decision method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the cross-system hierarchical awareness routing decision method of this application.

[0028] In this embodiment, the cross-system hierarchical awareness routing decision method includes steps S10 to S40: Step S10: Perform layered network probing according to the preset detection targets to obtain network performance detection data for each external gateway link.

[0029] It should be noted that hierarchical network probing based on preset detection targets refers to designing and executing hierarchical proactive probing tasks for links leading to different external gateways, based on the measurement requirements of different performance indicators. This process simulates the characteristics of real business traffic, acquiring key data layer by layer. For example, firstly, basic connectivity probing is used to obtain the round-trip latency baseline of the link; then, by simulating the transmission of continuous data packets, latency fluctuations are analyzed to assess jitter and initially observe packet loss; finally, by applying progressively increasing traffic load, the actual throughput and stability of the link under pressure are tested, thereby systematically obtaining a set of network performance probing data covering latency, jitter, packet loss, and bandwidth utilization.

[0030] Understandably, the core principle of layered design lies in the fact that different network performance metrics require different probe traffic patterns to effectively stimulate and measure them. Basic layer probes use lightweight, standard protocol messages, aiming to obtain stable latency reference values ​​with minimal interference. The jitter layer, on the other hand, sends a set of probe packets with specific intervals, leveraging the characteristics of connectionless protocols to capture differences in the processing time of consecutive data packets, thereby quantifying its jitter level. The essence of stress layer probes is to simulate congestion control behavior in real-world transmission. By gradually increasing the sending rate until a performance inflection point is observed, such as a significant increase in packet loss rate, it objectively assesses the available bandwidth and load saturation of the link, making the probe results closer to the actual experience of business traffic.

[0031] In a preferred embodiment, to ensure high traceability and relevance of the probe data, custom tagging information can be embedded in the payload of each probe packet. This tagging information includes at least a probe level identifier, the precise transmission time, and the service type associated with this probe mission. Upon receiving the probe packet, the receiving end not only records the arrival time but also encapsulates and returns complete data containing the original tagging information and the local time. This approach ensures that subsequent calculations can accurately pair response packets with transmission packets and strongly correlate performance data with specific probe levels and service scenarios, laying a solid data foundation for subsequent differentiated performance evaluation.

[0032] It should be noted that in the specific implementation, the probing task will be clearly divided into three layers: the basic layer, the jitter layer, and the stress layer, to systematically obtain network performance data of the external gateway link. The basic layer probing uses the standard Internet Control Message Protocol (ICP-IP) echo request, and its core objective is to obtain stable round-trip time (RTT) benchmark data as a measure of network performance. Specifically, this layer continuously sends a small number of probe packets and accurately records the sending time of each packet and the arrival time after the receiver's echo. By collecting multiple samples and calculating the average, the statistical validity of the latency data is ensured, avoiding random errors from single measurements. The jitter layer uses the User Datagram Protocol (UDP) to send probe packets in batches. The connectionless nature of this protocol allows it to effectively simulate the packet sending characteristics of real-time streaming services. By analyzing the fluctuation range of the RTT values ​​of this series of continuously sent probe packets, the jitter of the link can be quantitatively assessed; simultaneously, by counting the number of packets sent and received, direct basic data can be provided for subsequent packet loss rate calculations. The stress layer goes a step further, using the Transmission Control Protocol (TCP) to simulate real business traffic and initiate probing. The built-in congestion control mechanism of this protocol ensures that the probing process closely matches actual data transmission scenarios. The probe at this level will start at a lower rate and gradually increase the sending rate, maintaining the test at each rate level for a period of time to observe the link performance, and simultaneously recording the actual throughput and packet loss rate. This process can be used to calculate the link bandwidth utilization and evaluate the performance stability of the link under high load pressure.

[0033] Step S20: Perform link quality assessment processing based on the network performance detection data to obtain the path performance assessment result of the external gateway link.

[0034] It should be noted that link quality assessment refers to using network performance probe data obtained from layered probing as input, and through standardized calculation and analysis methods, deriving path performance assessment results with clear business implications. This process first requires preprocessing the probe data from each layer. For example, it involves calculating the average round-trip time and maximum round-trip time obtained from the base layer probe, extracting latency fluctuations between consecutive packets in jitter layer data transmission to assess jitter levels, and combining this with packet loss statistics. Simultaneously, it also requires analyzing throughput and packet loss rate data obtained from stress layer testing to evaluate the link's bandwidth utilization efficiency and stability. Finally, the calculated quantitative indicators are compared one-to-one with pre-set performance target thresholds based on different service types to comprehensively determine the overall transmission performance level of the external gateway link.

[0035] Understandably, average round-trip time reflects the dwell time of data packets in the network, its standard deviation (jitter) reflects the latency stability of the network path, packet loss rate is directly related to the reliability of data transmission, and bandwidth utilization reflects the saturation level of the link's carrying capacity. By setting differentiated performance thresholds for different service types (such as real-time audio / video services and file download services), the evaluation results can be linked to the service experience. For example, the evaluation result might ultimately be expressed as "this link meets the requirements for real-time service transmission" or "this link has an anomaly in a certain performance indicator."

[0036] It should be understood that only through systematic quantification and integrated analysis of core indicators such as latency, jitter, packet loss, and throughput can the operational status of physical links be converted into quality labels that are strongly correlated with service quality and can be understood and utilized by subsequent path optimization algorithms. For example, a link may have extremely high available bandwidth, but if its round-trip latency jitter is severe, the transmission quality of this line will be substandard for real-time audio and video services; conversely, a link with extremely low and stable latency may not be suitable for large file transfer scenarios if its throughput is close to saturation. The evaluation results are the conclusions drawn from a comprehensive trade-off of these multi-dimensional performance characteristics.

[0037] In one embodiment, the step of performing link quality assessment based on the network performance detection data to obtain the path performance assessment result of the external gateway link includes: obtaining a link latency score based on the link latency index in the network performance detection data and a preset latency degradation threshold; obtaining a link jitter score based on the transmission jitter index in the network performance detection data and a preset jitter degradation threshold; obtaining a link packet loss score based on the transmission packet loss index in the network performance detection data and a preset packet loss rate degradation threshold; obtaining a link bandwidth congestion score based on the bandwidth utilization index in the network performance detection data and a preset bandwidth utilization rate degradation threshold; and performing a comprehensive analysis based on the link latency score, link jitter score, link packet loss rate score, and link bandwidth congestion score to generate a path performance assessment result characterizing the overall performance degradation degree of the external gateway link.

[0038] Step S30: Based on the path performance evaluation results, determine the gateway link to be optimized.

[0039] It should be noted that in this step, after evaluating the performance levels of all external gateway links, the system will filter out those links whose evaluation results do not meet the preset quality standards and mark them as targets requiring priority intervention or optimization. The final evaluation label for each link, such as "Excellent," "Qualified," "Warning," or "Abnormal," will be compared with the minimum acceptable level set for different service routing strategies. All links with a level below the threshold will be automatically included in the optimization list. For example, when setting routing for real-time video conferencing services, if a link is determined to not meet service requirements due to an "Abnormal" jitter evaluation result, then that link will be identified as a link requiring optimization.

[0040] Understandably, the core of this step lies in linking quality assessment with specific network operation and maintenance actions. The path performance assessment result itself is merely a state description, while "identifying links to be optimized" is a decision made based on this state description. Its purpose is to focus operational resources, avoiding indiscriminate monitoring and adjustment of all links, thereby improving the efficiency and targeting of network optimization efforts. Essentially, it's a policy-based filtering and prioritization mechanism that ensures the network management system always focuses its attention on the weakest links most likely to impact service experience.

[0041] In a preferred embodiment, identifying links to be optimized requires further analysis based on performance trends. The system performs short-term historical data backtesting on the marked links. If key indicators (such as latency or packet loss rate) show a continuously deteriorating trend, even if the current value has not yet fallen below the "abnormal" threshold, the links may be prematurely added to the optimization list due to their high potential risk. This strategy allows operations personnel to take optimization measures such as capacity expansion, traffic adjustment, or path switching before a link completely fails or services are significantly impaired, thereby significantly improving the overall robustness and service assurance capabilities of the network.

[0042] Step S40: According to the preset routing policy adjustment process, perform a routing update operation on the gateway link to be optimized in order to optimize global traffic scheduling.

[0043] It should be noted that this step can be described as executing a Border Gateway Protocol (BGP) routing attribute modification process. First, BGP routing information needs to be obtained, which involves synchronizing complete routing table entries between the local Autonomous System (AS) border router and its external neighbors through the standard interface of the network protocol. Then, based on this information, the core information of each route is determined. This core information includes the destination network address prefix, the address of the next-hop device, the length of the AS path traversed by the route, the current multi-exit discriminator value, and the original priority of the route. Next, the path performance evaluation results for the corresponding next-hop address obtained in the previous detection are correlated one by one with their routing table entries, thereby generating a detailed "route-performance" correlation table. This table intuitively reflects the network quality status of each available path.

[0044] Understandably, the core of this process lies in leveraging the routing algorithm characteristics of the Border Gateway Protocol (BGP) to guide neighboring devices to choose paths that align with our optimization goals by purposefully modifying attribute values ​​that influence route priority. Specifically, based on the aforementioned association table, the system recalculates and sets the multi-egress discriminator (MED) value for each path according to preset adjustment rules and the path's performance level. This value is a metric announced to external neighbors to influence their inbound traffic decisions. For example, for a path assessed as having degraded performance, a higher MED value is calculated and assigned, lowering its priority for neighbors. After all calculations are complete, the system broadcasts the updated routing information, especially the new MED attributes, to relevant neighboring devices via standard protocol messages. Upon receiving the update, neighboring devices will re-compare path priorities according to protocol standards, thus spontaneously migrating traffic from high-latency, high-packet-loss inferior paths to higher-performance alternative paths, achieving automated optimization of global traffic scheduling.

[0045] It is important to note that monitoring and effect verification are necessary before and after performing route update operations. After updating the multi-egress discriminator value, network performance probes should be initiated at a higher frequency for a period of time. For example, the probe interval should be shortened from once every five minutes to once every minute to intensively monitor the actual switching of target network traffic and the performance of the new path. This verifies whether the traffic has migrated to the optimized path as expected and ensures that the service quality of the new path is stable and meets the standards. If monitoring finds that the traffic has not switched successfully or the performance of the new path does not meet expectations, the attribute value calculation and publication process needs to be repeated to fine-tune the multi-egress discriminator value, or to check whether there are routing policy constraints between autonomous systems that have caused unexpected routing behavior. This closed-loop monitoring and verification mechanism is a key detail to ensure that route optimization operations are accurate, effective, and do not affect the stable operation of the network.

[0046] In a preferred embodiment, after sending the Border Gateway Protocol (BGP) routing update message to neighboring devices, a verification probe is performed on the updated gateway link to obtain verification network performance data. Based on the verification network performance data and a preset optimization threshold, it is determined whether the routing update operation has achieved the expected scheduling optimization effect. If the determination result is that the expected scheduling optimization effect has not been achieved, the parameters in the path influence parameter adjustment rule are adjusted based on the verification network performance data to fine-tune the path attribute values ​​of the gateway link to be optimized, and the routing update operation is re-executed based on the fine-tuned path attribute values.

[0047] This embodiment implements hierarchical proactive network performance detection on external gateway links, systematically acquiring key performance indicators such as latency, jitter, packet loss, and throughput that reflect the true transmission quality of the links. Based on this data, a correlation assessment matching the service quality requirements of each link is performed, thereby identifying all gateway links that do not meet the preset network quality standards and need optimization. Subsequently, according to the preset automated routing policy adjustment process, such as calculating and modifying the border gateway protocol path attribute values ​​that affect routing priority, network traffic is proactively guided to migrate from degraded links to better-performing alternative paths, ultimately achieving dynamic and intelligent scheduling of global network traffic distribution.

[0048] In summary, this technical solution forms a closed-loop decision-making system by standardizing network performance detection, service-related quality assessment, and automated path control commands. Through tiered network performance measurement that closely reflects real-world service characteristics, it obtains more accurate and comprehensive link status data than traditional passive monitoring. Based on this, the assessment results are directly mapped to the automatic adjustment process of routing policies, enabling the network to proactively optimize traffic distribution based on real-time perceived changes in link quality. This ensures a smooth transmission experience for critical applications and significantly improves the automation and response speed of network management from problem detection to optimization execution, enhancing the overall resilience and resource utilization efficiency of the network.

[0049] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S10 in the cross-system hierarchical awareness routing decision method includes steps S101 to S104: Step S101: Construct a hierarchical detection data packet sequence based on multiple preset detection targets.

[0050] It should be noted that the layered probing here is based on a systematic evaluation framework that breaks down the complex objective of overall path performance into several independent yet interconnected performance dimensions. Each layer specifically measures a core network transmission characteristic and selects the network protocol that best exposes the details of that characteristic to construct the probe packet.

[0051] Understandably, to achieve the aforementioned multi-dimensional measurements, this method designs a three-layer active probing mechanism. The first layer is the basic probing layer, which aims to obtain a baseline latency for the network path. This is implemented using the standard Internet Control Message Protocol (ICP-C), which features request-response capabilities. Specifically, the sending end continuously sends multiple probe requests at fixed intervals and accurately records the sending time of each packet and the time of receiving the response from the other party. The round-trip time (RTT), representing the signal propagation delay, can be calculated from the difference between these two times. The second layer is the jitter probing layer, designed to assess the fluctuations in packet transmission time and simulate service types sensitive to latency changes. This layer uses the User Datagram Protocol (UDP) to construct and send probe packets in batches, as its connectionless nature makes it easier to observe pure network fluctuations. By analyzing the variation in RTT of multiple consecutive packets, the jitter level of the link can be quantified, and the number of received packets also provides a basis for calculating the packet loss rate. The third layer is the stress probing layer, which aims to test the link's performance under simulated real service traffic pressure. This layer employs a Transmission Control Protocol (TCP) with flow control mechanisms. The probe traffic starts at a moderate rate and gradually increases in stages, maintaining the test for a period of time at each stress stage. This allows us to observe the changes in link throughput and packet loss rate as the load increases, providing crucial data for assessing the maximum available bandwidth of the link and its utilization.

[0052] In one embodiment, the step of constructing a hierarchical detection data packet sequence based on a plurality of preset detection targets includes steps A10 to A40.

[0053] Step A10: Construct a base layer probe data packet sequence according to the preset baseline probe strategy.

[0054] It should be noted that in this step, the probe data packets ("baseline probe data packet sequence") constructed using the baseline probe strategy have a small data payload (first preset data payload) and the lowest transmission frequency (first preset frequency). The purpose is to measure baseline performance, similar to a lightweight "heartbeat detection," aiming to obtain baseline metrics such as basic round-trip time and connectivity of the link with minimal network overhead, serving as a baseline for subsequent analysis.

[0055] Step A20: Construct a jitter layer probe data packet sequence according to the preset jitter simulation strategy.

[0056] It should be noted that in this step, a jitter simulation strategy is used to construct the corresponding data packet sequence. The key to the construction mode of its probe packets lies in the "micro-burst mode," which involves sending packets at a higher frequency (a second preset frequency). The purpose is to evaluate stability and immediacy. "Micro-burst" simulates the burst characteristics of small data packets in real-time interactive services (such as voice and video calls). By sending small batches of data packets at high frequency, subtle changes in latency between data packets (i.e., "jitter") can be captured, and occasional packet loss can be detected more sensitively, thereby evaluating the link's quality of service for real-time services.

[0057] Step A30: Construct a stress layer probe packet sequence according to the preset load testing strategy.

[0058] It should be noted that the load testing strategy used in this step is characterized by "large data load" (second preset data load) and "intensive transmission rhythm" (third preset frequency). Its purpose is to "test the carrying capacity and bandwidth availability." By intensively sending a large amount of data within a certain period, it aims to temporarily occupy a portion of the bandwidth and observe the link's performance under increased load, such as changes in throughput and packet loss rate under sustained high load, in order to evaluate the link's available bandwidth capacity and resilience.

[0059] Step A40: Integrate the base layer probe data packet sequence, the jitter layer probe data packet sequence, and the stress layer probe data packet sequence to obtain the layered probe data packet sequence.

[0060] It should be noted that in the above steps, the second preset frequency is greater than the third preset frequency, the third preset frequency is greater than the first preset frequency, and the second preset data load is greater than the first preset data load. This parameter design is to ensure that the detection of each layer does not interfere with each other, each performs its own function, and can truly reflect the performance of its respective dimension. For example, the high load of the stress layer may affect the latency, so the base layer needs to measure the purest reference latency with the lowest frequency and minimum load in the most "calm" background; while the high-frequency micro-bursts of the jitter layer can capture more refined latency fluctuations during stress testing.

[0061] It should be understood that constructing a hierarchical probe packet sequence is a prerequisite step in initiating the entire dynamic sensing and optimization process. It directly determines the diversity and relevance of the collected data. The sequence construction must balance efficiency and representativeness, generating data samples sufficient to characterize the link's behavior under multiple scenarios and load conditions, while avoiding excessive pressure on the actual service channel. The output of this step—a series of clearly structured and well-labeled probe packets—provides original and crucial factual evidence for all subsequent calculations, evaluations, and decision-making processes.

[0062] Step S102: By sending the hierarchical probe data packet sequence to the peer gateway of the external gateway link and parsing the returned information, network status interaction data is obtained.

[0063] It should be noted that the core purpose of this step is to actively trigger and collect real-time response data of the network path. Parsing the returned information means that after receiving the probe packet, the peer node will encapsulate and return information containing its local receiving timestamp and original probe marker according to the agreed format. After receiving these responses, the sending end extracts and calculates the original metrics such as the time difference between the two ends.

[0064] Understandably, the final network state interaction data is a structured dataset that integrates composite information from multiple probing layers and various metrics. Specifically, this data includes at least the baseline round-trip time calculated from the base layer, the latency fluctuation range and packet loss count analyzed from the jitter layer, and the throughput and packet loss rate variation curves observed from stress layer tests. This dataset fully records the entire process details of this probing interaction.

[0065] Step S103: Obtain the associated marker information in the probe data payload, the associated marker information including probe type identifier and service priority.

[0066] It should be noted that the association tagging information in the probe data payload refers to the pre-encapsulated attribute information used for identification and association extracted from the original probe data packet payload contained in the return data when parsing and processing the return response data from the peer gateway. Specifically, the probe type identifier refers to the classification label used to distinguish whether the probe originates from different measurement dimensions such as the base layer, jitter layer, or stress layer; while the service priority characterizes the level of network service quality requirements of the service type simulated or served by this probe task.

[0067] Understandably, the purpose of this step is to establish a clear organizational logic for the massive amounts of probe data collected within the same time window, which come from diverse sources and have different objectives. Through structured association tags, the system can classify and associate seemingly disordered raw data packets—for example, one request packet for measuring basic latency and another request packet for testing bandwidth pressure—according to their inherent probe objectives and business context. This lays the foundation for subsequent independent analysis of different performance dimensions (such as latency, jitter, and throughput) and differentiated evaluation based on business needs.

[0068] It should be understood that the purpose of this step is to enable the analysis process to be business-aware. For example, based on business priority marking, the system can prioritize the processing of probe data for latency-sensitive real-time services, ensuring the timeliness of the evaluation results, and may allocate more stable network paths to such services in subsequent decisions. This associated marking information is key metadata for achieving intelligent, differentiated network state management and optimization.

[0069] Step S104: Obtain network performance detection data based on the network status interaction data and the associated tag information.

[0070] Understandably, this step is the core transformation stage of the data processing flow. Its essence is to refine the analysis and calculation of coarse-grained network state interaction data based on associated tagging information, thereby generating performance indicators that can be directly used for quality assessment and decision-making. For example, the system first extracts all interaction data carrying "jitter layer" probe type identifiers and "high priority" service tags. Then, it specifically calculates the latency fluctuation range, i.e., the jitter value, for this data and counts the number of lost packets to obtain the packet loss rate. The final quantitative result set containing specific jitter values ​​and packet loss rates is the link stability performance probe data for high-priority services.

[0071] It should be understood that the network performance detection data generated through this step is normalized information that can be directly used by the decision-making module, providing accurate and differentiated input for subsequent intelligent path selection based on different service performance requirements.

[0072] In this embodiment, a hierarchical probe data packet sequence with different measurement targets such as reference latency, jitter stability, and load capacity is systematically constructed and sent. Then, the response information of each layer probe is collected to form raw interaction data, and the association tags that distinguish the probe type and service level are extracted from it. Finally, the interaction data of different performance dimensions are classified and calculated according to these tags, so as to obtain network performance probe data with a clear structure.

[0073] Through the above design, this invention enables precise and non-interfering parallel measurement of multiple key performance dimensions of connected network links, and effectively associates the measurement results with specific service quality requirements using correlation tags. This allows the routing decision system to comprehensively understand the differentiated performance of links in different application scenarios based on a unified set of probe data, thereby providing more accurate and reliable data support for selecting the most suitable network path for different service characteristics, significantly improving the intelligence and adaptability of routing decisions.

[0074] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S40 in the cross-system hierarchical awareness routing decision method includes steps S401 to S404: Step S401: Based on the preset path influence parameter adjustment rules and the path performance evaluation results, update the multi-exit authentication attribute values ​​of each external gateway link to obtain the updated multi-exit authentication attribute values.

[0075] It's important to note that the system follows a clear and quantifiable set of adjustment rules when updating multi-egress authentication attribute values. The core of these rules is comparing the actual measured values ​​of various path performance indicators with preset thresholds for their corresponding service types, and determining a specific increase in the attribute value based on the proportion or range exceeding the threshold. For example, for high-latency paths, if the latency exceeds the threshold but is less than 1.5 times the threshold, the multi-egress authentication attribute value increases by 100; if it exceeds 1.5 times the threshold, it increases by 150. For high packet loss paths, if the packet loss rate is between 1% and 3%, the attribute value increases by 200; exceeding 3% is considered severe degradation, and the increase is set to 300. Bandwidth utilization adjustments also follow this principle: 80% to 90% requires a moderate increase, while exceeding 90% necessitates a more significant reduction in priority. This tiered, differentiated design aims to accurately distinguish the degree of degradation while avoiding unnecessary and frequent disturbances to the routing system.

[0076] It is understandable that the preset thresholds mentioned in this step are not single, fixed values, but rather dynamic benchmarks associated with the nature of the services being carried (such as voice, video, and ordinary data transmission). Specifically, when external gateway protocol routing entries are filtered and imported through a multi-attribute decision-making process, the system has already identified their corresponding typical service type based on information such as their target prefix, quality of service policy, or traffic engineering tags. For example, a route to a real-time communication server group is labeled as "voice service," and its preset latency threshold may be set to a relatively strict 50 milliseconds; a route to a video content delivery network is classified as "video streaming service," and its jitter threshold may be set to 30 milliseconds. For ordinary web or file transfer services, the performance requirements are relatively relaxed, and the thresholds are set higher. This service-related threshold mechanism ensures that subsequent performance evaluation and route priority adjustments are guided by actual application needs, avoiding undue impact of static threshold strategies on different sensitive services.

[0077] It should be understood that, based on the aforementioned threshold system for business awareness, the execution of path impact parameter adjustment rules is highly contextualized. After performing "route-performance" correlation, the system first needs to determine the service type associated with the route entry and retrieve its corresponding personalized threshold set. For example, if a 70-millisecond latency is detected on a path marked "voice service," it will be classified as a high-latency path because it exceeds its 50-millisecond threshold, thus triggering an adjustment to the multi-exit identification attribute value, such as increasing it by 100 according to the rules. However, if this 70-millisecond latency occurs on a path marked "ordinary data service," since its threshold may be set at 100 milliseconds, this path will not be classified as abnormal, and its priority will remain unchanged. This design allows for more granular differentiation of service priorities in cross-domain network traffic scheduling, prioritizing the experience of performance-sensitive critical service flows when overall network resources are limited.

[0078] Step S402: Generate a Border Gateway Protocol routing update message based on the multi-exit authentication attribute value.

[0079] It's important to note that the generation process here is not a simple numerical write-in, but rather a formatted encapsulation process that adheres to protocol specifications and local policies. Core components of the routing update message, such as specific path attribute fields, will be filled directly with the updated multi-egress authentication attribute values ​​or filled after logical transformation. The system will also decide, based on the routing policy, whether to simultaneously adjust other path attributes such as local priority to ensure that the sent routing messages accurately and consistently reflect the local end's egress path preference for a specific network prefix.

[0080] Understandably, the purpose of this step is to effectively broadcast the latest performance evaluation of a certain external path within the autonomous system to its internal peer routers. For example, when the system detects a significant latency degradation on path A leading to a data center prefix and accordingly increases its multi-egress authentication attribute value, the system generates an update message carrying this higher attribute value and sends it to neighboring devices. Routers receiving this message, when comparing and selecting paths, will reduce the priority of that path due to the increased attribute value, thereby guiding subsequent traffic destined for that data center to be forwarded via other, better paths (such as path B), achieving traffic redirection based on real-time quality.

[0081] Step S403: Send the Border Gateway Protocol routing update message to the neighboring device so that the neighboring device can re-execute path selection based on the updated multi-exit authentication attribute value to obtain the updated gateway link.

[0082] It should be noted that the neighboring devices in this step refer to adjacent routers that have established a peer-to-peer session with the executing device via the Border Gateway Protocol (BGP), including internal neighbors within the same autonomous system. Message transmission strictly adheres to the message format and transmission mechanism specified in the protocol to ensure that the peer can correctly receive and parse the messages.

[0083] Understandably, upon receiving this update message, the neighboring device will integrate the multi-escape authentication attribute value and other information it carries into its own routing database. Subsequently, the neighbor will re-execute its internal decision-making process based on the updated attribute values. Generally, the multi-escape authentication attribute is used as a key metric for path comparison; a higher value typically indicates a lower path priority. For example, if congestion is detected on a path to a website, causing the attribute value to increase, the neighboring device will receive the update and recalculate, potentially ultimately selecting a lower-valued, higher-quality path as the new data transmission link to that website.

[0084] Step S404: Perform cross-domain traffic scheduling based on the updated gateway link to achieve optimized scheduling of global traffic.

[0085] It should be noted that the core of this process is that the network device, based on the latest preferred path for a specific destination network prefix in its routing information database, directs subsequent arriving data packets to the corresponding egress link. The updated gateway link is the next-hop physical or logical channel to the external network that has been reconfirmed as better after the aforementioned performance evaluation and path selection process.

[0086] Understandably, this scheduling enables the optimization of global traffic capacity. Specifically, global traffic refers to all service data flows that traverse the entire autonomous system and are destined for external networks. By dynamically migrating traffic from degraded links to better links, the system improves the end-to-end transmission quality of critical services overall. For example, when video conferencing traffic is scheduled to low-latency links while large-scale file download traffic is directed to high-bandwidth links, the needs of different service types are met simultaneously, thereby improving the overall efficiency of network resource utilization and user experience.

[0087] In this embodiment, the performance of external paths is evaluated based on preset threshold rules associated with service types, and the corresponding path priority attribute values ​​are updated differentially according to the degree of degradation. Subsequently, a routing update message carrying the updated attribute values ​​is generated and sent to neighboring devices, enabling them to recalculate and select a better outbound link. Finally, the network devices perform actual cross-domain traffic scheduling based on this updated preferred path, thereby guiding different service flows to match the current gateway link with better quality.

[0088] In summary, this technical solution quantifies real-time path performance detection results into dynamically adjustable priority attributes, thereby driving the updating and convergence of routing information within the network, achieving self-optimizing scheduling of cross-domain traffic. Because the priority adjustment rules consider the differentiated quality requirements of different service types, traffic scheduling decisions can more granularly guarantee the experience of critical services. Simultaneously, by disseminating optimization strategies throughout the network through a standardized routing information propagation mechanism, the overall network resource utilization efficiency and service reliability are effectively improved in variable environments.

[0089] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the hierarchical awareness routing decision method across systems in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0090] This application also provides a cross-system hierarchical awareness routing decision-making device; please refer to... Figure 4 The cross-system hierarchical sensing routing decision-making device includes: The detection module 10 is used to perform layered network detection according to preset detection targets to obtain network performance detection data of each external gateway link; The transmission evaluation module 20 is used to perform link quality evaluation processing based on the network performance detection data to obtain the path performance evaluation result of the external gateway link; The decision module 30 is used to determine the gateway link to be optimized based on the path performance evaluation results. The routing update module 40 is used to adjust the process according to the preset routing policy and perform routing update operations on the gateway link to be optimized in order to optimize global traffic scheduling.

[0091] In one embodiment, the detection module 10 is further configured to construct a hierarchical detection data packet sequence based on multiple preset detection targets; obtain network status interaction data by sending the hierarchical detection data packet sequence to the peer gateway of the external gateway link and parsing the returned information; obtain association marker information in the detection data payload, the association marker information including detection type identifier and service priority; and obtain network performance detection data based on the network status interaction data and the association marker information, the network performance detection data including link latency characteristics, jitter characteristics, packet loss characteristics and bandwidth utilization characteristics.

[0092] In one embodiment, the detection module 10 is further configured to: construct a base layer detection data packet sequence according to a preset baseline detection strategy, wherein the base layer detection data packet sequence consists of detection data packets that satisfy a first preset data payload and are sent at a first preset frequency; construct a jitter layer detection data packet sequence according to a preset jitter simulation strategy, wherein the jitter layer detection data packet sequence consists of detection data packets that satisfy a preset micro-burst mode and are sent at a second preset frequency; construct a stress layer detection data packet sequence according to a preset load test strategy, wherein the stress layer detection data packet sequence consists of detection data packets that satisfy a second preset data payload and are sent at a third preset frequency, wherein the second preset frequency is greater than the third preset frequency, the third preset frequency is greater than the first preset frequency, and the second preset data payload is greater than the first preset data payload; and integrate the base layer detection data packet sequence, the jitter layer detection data packet sequence, and the stress layer detection data packet sequence to obtain the layered detection data packet sequence.

[0093] In one embodiment, the detection module 10 is further configured to send and receive a sequence of basic layer detection data packets through a preset first network path, and obtain a latency benchmark measurement result based on the transmission timestamp information in the received data; send and receive a sequence of jitter layer detection data packets through a preset second network path, and obtain a network jitter characteristic analysis result based on the arrival interval information in the received data; send and receive a sequence of stress layer detection data packets through a preset third network path, and obtain a packet loss rate analysis result and an available bandwidth analysis result based on the transmission status information in the received data; and obtain the network status interaction data based on the latency benchmark measurement result, the network jitter characteristic analysis result, the packet loss rate analysis result, and the available bandwidth analysis result.

[0094] In one embodiment, the transmission evaluation module 20 is further configured to: obtain a link latency score based on the link latency index in the network performance detection data and a preset latency degradation threshold; obtain a link jitter score based on the transmission jitter index in the network performance detection data and a preset jitter degradation threshold; obtain a link packet loss score based on the transmission packet loss index in the network performance detection data and a preset packet loss rate degradation threshold; obtain a link bandwidth congestion score based on the bandwidth utilization index in the network performance detection data and a preset bandwidth utilization rate degradation threshold; and perform a comprehensive analysis based on the link latency score, link jitter score, link packet loss rate score, and link bandwidth congestion score to generate a path performance evaluation result characterizing the overall performance degradation degree of the external gateway link.

[0095] In one embodiment, the routing update module 40 is further configured to update the multi-egress authentication attribute values ​​of each external gateway link based on preset path impact parameter adjustment rules and the path performance evaluation results, to obtain updated multi-egress authentication attribute values; generate a border gateway protocol routing update message based on the multi-egress authentication attribute values, the update message including the destination network prefix and the next-hop path; send the border gateway protocol routing update message to neighboring devices, so that the neighboring devices re-execute path selection based on the updated multi-egress authentication attribute values, to obtain updated gateway links; and perform cross-domain traffic scheduling based on the updated gateway links, thereby achieving optimized scheduling of global traffic.

[0096] In one embodiment, the routing update module 40 is further configured to, after sending the border gateway protocol routing update message to the neighboring device, perform a verification probe on the updated gateway link to obtain verification network performance data; based on the verification network performance data and a preset optimization threshold, determine whether the routing update operation has achieved the expected scheduling optimization effect; if the determination result is that the expected scheduling optimization effect has not been achieved, then based on the verification network performance data, adjust the parameters in the path influence parameter adjustment rule to fine-tune the path attribute value of the gateway link to be optimized, and re-execute the routing update operation based on the fine-tuned path attribute value.

[0097] The cross-system hierarchical awareness routing decision-making device provided in this application, employing the cross-system hierarchical awareness routing decision-making method described in the above embodiments, can solve the technical problem in the prior art of how to design a method that can deeply integrate real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling. Compared with the prior art, the beneficial effects of the cross-system hierarchical awareness routing decision-making device provided in this application are the same as those of the cross-system hierarchical awareness routing decision-making method provided in the above embodiments, and other technical features in the cross-system hierarchical awareness routing decision-making device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0098] This application provides a cross-system hierarchical awareness routing decision device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the cross-system hierarchical awareness routing decision method in the first embodiment described above.

[0099] The following is for reference. Figure 5This document illustrates a structural schematic diagram of a cross-system hierarchical awareness routing decision-making device suitable for implementing embodiments of this application. The cross-system hierarchical awareness routing decision-making device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The illustrated cross-system hierarchical awareness routing decision device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 5 As shown, the cross-system hierarchical awareness routing decision-making device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the cross-system hierarchical awareness routing decision-making device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the cross-system hierarchical awareness routing decision-making device to wirelessly or wiredly communicate with other devices to exchange data. Although a cross-system hierarchical awareness routing decision-making device with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented or possessed alternatively.

[0101] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0102] The cross-system hierarchical awareness routing decision-making device provided in this application, employing the cross-system hierarchical awareness routing decision-making method described in the above embodiments, can solve the technical problem in the prior art of how to design a method that can deeply integrate real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling. Compared with the prior art, the beneficial effects of the cross-system hierarchical awareness routing decision-making device provided in this application are the same as those of the cross-system hierarchical awareness routing decision-making method provided in the above embodiments, and other technical features of this cross-system hierarchical awareness routing decision-making device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0105] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the cross-system hierarchical awareness routing decision method in the above embodiments.

[0106] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), or any suitable combination thereof.

[0107] The aforementioned computer-readable storage medium may be included in a cross-system hierarchical awareness routing decision-making device; or it may exist independently and not be assembled into a cross-system hierarchical awareness routing decision-making device.

[0108] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a cross-system hierarchical awareness routing decision-making device, the device performs the following: hierarchical network probing based on preset detection targets to obtain network performance detection data for each external gateway link; performs link quality assessment processing based on the network performance detection data to obtain path performance assessment results for the external gateway links; determines gateway links to be optimized based on the path performance assessment results; and performs route update operations on the gateway links to be optimized according to a preset routing policy adjustment process to optimize global traffic scheduling.

[0109] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0111] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0112] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned cross-system hierarchical awareness routing decision method. This addresses the technical problem in the prior art of designing a method that deeply integrates real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the cross-system hierarchical awareness routing decision method provided in the above embodiments, and will not be elaborated upon here.

[0113] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the cross-system hierarchical awareness routing decision method as described above.

[0114] The computer program product provided in this application solves the technical problem of how to design a method that deeply integrates real-time network quality awareness with traditional routing protocols to achieve dynamic and refined intelligent traffic scheduling. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the cross-system hierarchical awareness routing decision method provided in the above embodiments, and will not be elaborated here.

[0115] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A cross-system hierarchical awareness routing decision method, characterized in that, The cross-system hierarchical awareness routing decision method includes: Based on the preset detection targets, layered network detection is performed to obtain network performance detection data for each external gateway link; Based on the network performance detection data, a link quality assessment is performed to obtain the path performance assessment result of the external gateway link; Based on the path performance evaluation results, the gateway links to be optimized are identified; According to the preset routing policy adjustment process, a routing update operation is performed on the gateway link to be optimized in order to optimize global traffic scheduling.

2. The cross-system hierarchical awareness routing decision method according to claim 1, characterized in that, The layered network probing based on preset detection targets, to obtain network performance detection data for each external gateway link, includes: Based on multiple preset detection targets, a hierarchical detection data packet sequence is constructed; By sending the hierarchical probe data packet sequence to the peer gateway of the external gateway link and parsing the returned information, network status interaction data is obtained; Obtain the associated marker information from the probe data payload, the associated marker information including probe type identifier and service priority; Based on the network status interaction data and the associated tag information, network performance detection data is obtained, which includes link latency characteristics, jitter characteristics, packet loss characteristics, and bandwidth utilization characteristics.

3. The cross-system hierarchical awareness routing decision method according to claim 2, characterized in that, The construction of a hierarchical detection data packet sequence based on multiple preset detection targets includes: According to a preset baseline detection strategy, a base layer detection data packet sequence is constructed. The base layer detection data packet sequence consists of detection data packets that satisfy a first preset data payload and are sent at a first preset frequency. According to the preset jitter simulation strategy, a jitter layer probe data packet sequence is constructed. The jitter layer probe data packet sequence consists of probe data packets that satisfy the preset micro-burst mode and are sent at a second preset frequency. According to the preset load testing strategy, a stress layer probe data packet sequence is constructed. The stress layer probe data packet sequence consists of probe data packets that meet the second preset data load and are sent at the third preset frequency. The second preset frequency is greater than the third preset frequency, the third preset frequency is greater than the first preset frequency, and the second preset data load is greater than the first preset data load. The base layer probe data packet sequence, the jitter layer probe data packet sequence, and the stress layer probe data packet sequence are integrated to obtain the layered probe data packet sequence.

4. The cross-system hierarchical awareness routing decision method according to claim 2, characterized in that, The process of sending the hierarchical probe data packet sequence to the peer gateway of the external gateway link and parsing the returned information to obtain network status interaction data includes: The basic layer probe data packet sequence is sent and received through a preset first network path, and the delay reference measurement result is obtained based on the transmission timestamp information in the received data; The jitter layer probe data packet sequence is sent and received through a preset second network path, and the network jitter characteristic analysis results are obtained based on the arrival interval information in the received data. The pressure layer probe data packet sequence is sent and received through a preset third network path, and the packet loss rate analysis result and available bandwidth analysis result are obtained based on the transmission status information in the received data. The network status interaction data is obtained based on the latency benchmark measurement results, network jitter characteristic analysis results, packet loss rate analysis results, and available bandwidth analysis results.

5. The cross-system hierarchical awareness routing decision method according to claim 1, characterized in that, The step of performing link quality assessment based on the network performance detection data to obtain the path performance assessment result of the external gateway link includes: Based on the link latency index in the network performance detection data and the preset latency degradation threshold, a link latency score is obtained; Based on the transmission jitter index in the network performance detection data and the preset jitter degradation threshold, the link jitter score is obtained; Based on the transmission packet loss index in the network performance detection data and the preset packet loss rate degradation threshold, the link packet loss rate score is obtained. Based on the bandwidth utilization index in the network performance detection data and the preset bandwidth utilization degradation threshold, the link bandwidth congestion score is obtained. Based on a comprehensive analysis of the link latency score, link jitter score, link packet loss rate score, and link bandwidth congestion score, a path performance evaluation result is generated that characterizes the overall performance degradation of the external gateway link.

6. The cross-system hierarchical awareness routing decision method according to claim 1, characterized in that, The process of adjusting the routing according to the preset routing policy, which involves performing a routing update operation on the gateway link to be optimized to optimize global traffic scheduling, includes: Based on the preset path impact parameter adjustment rules and the path performance evaluation results, the multi-exit authentication attribute values ​​of each external gateway link are updated to obtain the updated multi-exit authentication attribute values. Based on the multi-exit identification attribute value, a border gateway protocol routing update message is generated, the update message including the destination network prefix and the next-hop path; The Border Gateway Protocol routing update message is sent to the neighboring device so that the neighboring device can re-execute path selection based on the updated multi-exit authentication attribute value and obtain the updated gateway link. Cross-domain traffic scheduling is performed based on the updated gateway link, thereby achieving optimized scheduling of global traffic.

7. The cross-system hierarchical awareness routing decision method according to claim 6, characterized in that, The cross-system hierarchical awareness routing decision method further includes: After the Border Gateway Protocol routing update message is sent to the neighboring device, a verification probe is performed on the updated gateway link to obtain verification network performance data. Based on the verifiable network performance data and the preset optimization threshold, it is determined whether the routing update operation has achieved the expected scheduling optimization effect. If the judgment result is that the expected scheduling optimization effect has not been achieved, then based on the verifiable network performance data, the parameters in the path influence parameter adjustment rules are adjusted to fine-tune the path attribute values ​​of the gateway link to be optimized, and the route update operation is re-executed based on the fine-tuned path attribute values.

8. A cross-system hierarchical sensing routing decision-making device, characterized in that, The cross-system hierarchical sensing routing decision-making device includes: The detection module is used to perform layered network detection based on preset detection targets to obtain network performance detection data for each external gateway link; The transmission evaluation module is used to perform link quality evaluation processing based on the network performance detection data to obtain the path performance evaluation result of the external gateway link; The decision module is used to determine the gateway links to be optimized based on the path performance evaluation results. The routing update module is used to adjust the process according to the preset routing policy and perform routing update operations on the gateway link to be optimized in order to optimize global traffic scheduling.

9. A cross-system hierarchical sensing routing decision-making device, characterized in that, The cross-system hierarchical awareness routing decision device includes: a memory, a processor, and a cross-system hierarchical awareness routing decision program stored in the memory and executable on the processor, wherein the cross-system hierarchical awareness routing decision program is configured to implement the cross-system hierarchical awareness routing decision method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a cross-system hierarchical awareness routing decision program, which, when executed by a processor, implements the steps of the cross-system hierarchical awareness routing decision method as described in any one of claims 1 to 7.

Images