A multi-node collaborative logistics data real-time synchronization method and system

Abstract

This invention discloses a multi-node collaborative real-time synchronization method and system for logistics data, specifically relating to the field of logistics data synchronization management technology. By measuring the round-trip latency between logistics nodes and the cloud platform, collecting and analyzing latency jitter data, and assessing the stability of the network transmission environment of the nodes, when the network is unstable, the initial time difference is recorded and the changing trend of the clock drift value is evaluated. The accuracy of clock synchronization is analyzed, and by combining network stability and clock synchronization accuracy, the severity of time synchronization deviations between logistics nodes is determined and classified into minor, moderate, and severe deviations. A graded early warning signal is generated to take targeted handling measures. This effectively solves the problem of data misordering and scheduling errors caused by time synchronization deviations in existing technologies, improves the time synchronization accuracy, network transmission stability, and overall operating efficiency of the logistics system, and significantly enhances the accuracy and reliability of logistics scheduling and event handling.

Description

Technical Field

[0001] This invention relates to the field of logistics data synchronization management technology, specifically to a method and system for real-time synchronization of logistics data through multi-node collaboration. Background Technology

[0002] Real-time synchronization of logistics data through multi-node collaboration refers to the real-time sharing and updating of logistics information among different nodes in a logistics system through the collaborative work of multiple data nodes (such as warehouses, transport vehicles, sorting centers, and distribution terminals). This process relies on modern information technologies, such as cloud computing, big data, and the Internet of Things, to efficiently transmit logistics data from each node into the system, enabling each link in the logistics chain to obtain the latest data in the shortest possible time, thereby optimizing resource allocation and improving logistics efficiency.

[0003] In traditional logistics systems, information lag or asymmetry often leads to inefficiencies such as inventory backlogs, transportation delays, or resource waste. However, real-time synchronization through multi-node collaboration enables transparent and dynamic information management. For example, transportation nodes can update the location and status of goods in real time, and warehouse nodes can prepare to receive goods in advance based on transportation information, thereby shortening the entire logistics cycle. This approach not only reduces operating costs but also improves customer experience and response speed. By deploying sensors, smart devices, and information systems at each logistics node, each node can collect and upload relevant data to the cloud platform. Subsequently, leveraging big data analytics and edge computing technologies, this data is processed in real time and distributed to other relevant nodes. For instance, when a package is dispatched from a warehouse, its status is immediately updated in the system, and relevant sorting centers and delivery terminals can obtain the latest information in real time. The entire process relies on efficient data transmission networks (such as 5G) and reliable collaboration mechanisms to ensure data consistency and synchronization.

[0004] The existing technology has the following shortcomings:

[0005] Time synchronization discrepancies between logistics nodes can lead to incorrect timestamps in data records, causing confusion in the system's handling of event sequences. For example, when goods are just loaded from a warehouse, the system might incorrectly record that the goods have been delivered to their destination due to time synchronization issues. This time misordering can trigger a series of problems: sorting centers might skip processing the goods, delivery terminals might fail to match the corresponding goods information, and duplicate notifications or operations might be triggered, resulting in resource waste and decreased logistics efficiency. Furthermore, modern logistics systems rely on real-time data for dynamic scheduling (such as vehicle route optimization and sorting priority adjustment). Time discrepancies causing data synchronization errors can lead to scheduling systems optimizing based on false information, potentially dispatching the wrong vehicles or ignoring high-priority orders. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for real-time synchronization of logistics data through multi-node collaboration, so as to overcome the shortcomings of the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for real-time synchronization of logistics data through multi-node collaboration, comprising the following steps:

[0008] S1: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows;

[0009] S2: Analyze the latency jitter in the collected network latency data, determine the degree of latency anomaly between the node and the cloud platform, and evaluate the stability of the network transmission environment between the node and the cloud platform.

[0010] S3: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized through GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to evaluate the accuracy of node clock synchronization.

[0011] S4: Determine the severity of time synchronization deviation between logistics nodes based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of node clock synchronization;

[0012] S5: Classify the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and implement corresponding early warning measures;

[0013] S6: For moderate deviations, predict and analyze the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjust node priorities based on the analysis results.

[0014] Preferably, in S2, after analyzing the latency jitter in the network latency data, a latency jitter anomaly index is generated. The method for obtaining the latency jitter anomaly index is as follows:

[0015] Set latency jitter data From a certain latent distribution Where θ is the distribution parameter, and n is the total number of time-delay jitter data, a standard normal distribution is chosen. By using variational inference, the posterior is approximated by the distribution q(θ). The optimization objective is to minimize the KL divergence between the two, expressed as: q(θ) is chosen to be a Gaussian distribution. Where μ and σ are the parameters to be optimized, and the prior distribution p(θ) is defined as follows: ; To represent the prior variance, we define the observation likelihood p(X|θ): Given the observed data... It follows a normal distribution, and its expression is: ; The mean of the jitter represents the center of stability of network latency. Let q(θ) be the variance of the jitter, representing the amplitude of network jitter fluctuations. The variational distribution q(θ) is chosen to be a Gaussian distribution. ; The approximate posterior parameters obtained through optimization are further optimized using gradient descent. Maximize the ELBO of the lower bound of evidence: For a Gaussian distribution, KL has an analytical solution: Using the optimized q(θ), calculate the q(θ) for each data point. The probability of an anomaly: Based on the anomaly probability of all data points, the latency jitter anomaly index is defined, and its expression is: In the formula, HWK is the time delay jitter anomaly index.

[0016] Preferably, in S3, after analyzing the changes in the drift value over time, a drift value fluctuation index is generated. The method for obtaining the drift value fluctuation index is as follows:

[0017] Setting clock drift value time series Where N is the total number of sampling points and the sampling interval is Ts, the expression for removing the mean from the sequence is: ; for the mean-removed drift value sequence Performing a Fast Fourier Transform yields the frequency domain signal in complex form: ; It is the kth frequency component. These are the amplitude and phase of a frequency domain signal; the magnitude of the amplitude represents the intensity of the vibration at each frequency. The kernel function for the Fourier transform; calculate the frequency amplitude: In the formula, yes The real part, yes The imaginary part; calculating the total energy of the frequency domain signal. The expression is: ; Calculate the energy of high-frequency components , It is the high-frequency boundary point, expressed as: The drift value fluctuation index is calculated using the following expression: GHQ is the drift value fluctuation index.

[0018] Preferably, in S4, the severity of time synchronization deviation between logistics nodes is determined based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of node clock synchronization, specifically as follows:

[0019] The time delay jitter anomaly index and drift value fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to the machine learning model. The machine learning model uses the prediction of the severity label of time synchronization deviation between logistics nodes for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of prediction errors for the severity labels of time synchronization deviation between all logistics nodes. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The severity value of time synchronization deviation between logistics nodes is determined based on the model output. The machine learning model is a multinomial regression model.

[0020] Preferably, in S5, the severity of time synchronization deviation between logistics nodes is divided into slight deviation, moderate deviation, and severe deviation, and corresponding early warning processing is carried out.

[0021] The severity values ​​of time synchronization deviation between logistics nodes are compared with gradient standard thresholds, which include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold. The severity values ​​of time synchronization deviation between logistics nodes are compared with the first standard threshold and the second standard threshold respectively.

[0022] If the severity of the time synchronization deviation between logistics nodes is greater than the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is high. At this time, a first-level warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a severe deviation.

[0023] If the severity of the time synchronization deviation between logistics nodes is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is moderate. At this time, a level 2 warning signal is generated to classify the severity of the time synchronization deviation between logistics nodes as a moderate deviation.

[0024] If the severity of the time synchronization deviation between logistics nodes is less than the first standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is low. At this time, a level three warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a minor deviation.

[0025] Preferably, in S6, for moderate deviation, that is, the severity value of time synchronization deviation between logistics nodes generated within a fixed time window is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the severity values ​​of time synchronization deviation between logistics nodes generated within subsequent fixed time windows that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding dataset is established. The mean and standard deviation of the dataset are calculated, and after analysis, the node priority is dynamically adjusted based on the analysis results.

[0026] Preferably, if the average severity value of time synchronization deviation within the dataset is greater than or equal to the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is less than the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall severity of time synchronization deviation is high but the fluctuation is small. In this case, a medium priority should be maintained, and the clock should be recalibrated or the network configuration adjusted periodically to reduce the overall deviation level.

[0027] If the mean severity of time synchronization deviation is greater than or equal to the reference threshold for the mean severity of time synchronization deviation, and the standard deviation of the severity of time synchronization deviation is greater than or equal to the reference threshold for the standard deviation of the severity of time synchronization deviation, the overall severity of time synchronization deviation is high and fluctuates greatly. In this case, the node priority should be reduced.

[0028] If the average severity value of time synchronization deviation is less than the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is greater than or equal to the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low but fluctuates greatly. In this case, a medium priority should be maintained, and dynamic monitoring of the node should be enhanced.

[0029] If the average severity value of time synchronization deviation is less than the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is less than the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low and the fluctuation is small. In this case, the node priority should be increased, the occupation of its monitoring resources should be reduced, and the system load should be reduced.

[0030] This invention also provides a real-time synchronization system for multi-node collaborative logistics data, including a network latency monitoring module, a network stability analysis module, a clock synchronization and drift assessment module, a deviation severity assessment module, an early warning response module, and a node priority adjustment module.

[0031] Network latency monitoring module: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows;

[0032] Network stability analysis module: Analyzes the latency jitter in the collected network latency data, determines the degree of latency anomaly between the node and the cloud platform, and evaluates the stability of the network transmission environment between the node and the cloud platform;

[0033] Clock synchronization and drift assessment module: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized by GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to assess the accuracy of node clock synchronization.

[0034] Deviation Severity Assessment Module: Based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of the node clock synchronization, the severity of time synchronization deviation between logistics nodes is determined;

[0035] Early warning response module: Classifies the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and performs corresponding early warning processing;

[0036] Node priority adjustment module: For moderate deviations, it predicts and analyzes the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjusts node priorities based on the analysis results.

[0037] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0038] 1. This invention combines network monitoring tools, GPS clock synchronization, and machine learning models to accurately assess the severity of time synchronization deviations between logistics nodes. It then uses a tiered early warning system and dynamically adjusts node priorities based on latency jitter anomaly indices and drift value fluctuation indices. This method effectively solves the problems of out-of-order logistics data and scheduling errors caused by time synchronization deviations, improves the accuracy of the logistics system's judgment of event sequence and dynamic scheduling, and significantly enhances the overall efficiency and reliability of the logistics system.

[0039] 2. This invention can capture subtle fluctuations in network transmission and clock synchronization, enabling deviation trend prediction and optimized resource allocation. The early warning mechanism has clear hierarchical levels, and the handling measures are highly targeted. While ensuring the efficient operation of nodes with minor deviations, it can take necessary interventions for nodes with moderate and severe deviations, reducing system risks and optimizing performance, ultimately providing stable and efficient real-time data synchronization for the logistics system. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0041] Figure 1 This is a flowchart of the method of the present invention.

[0042] Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1, please refer to Figure 1 and Figure 2 As shown in this embodiment, a real-time synchronization method for multi-node collaborative logistics data includes the following steps:

[0045] S1: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows;

[0046] S2: Analyze the latency jitter in the collected network latency data, determine the degree of latency anomaly between the node and the cloud platform, and evaluate the stability of the network transmission environment between the node and the cloud platform.

[0047] S3: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized through GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to evaluate the accuracy of node clock synchronization.

[0048] S4: Determine the severity of time synchronization deviation between logistics nodes based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of node clock synchronization;

[0049] S5: Classify the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and implement corresponding early warning measures;

[0050] S6: For moderate deviations, predict and analyze the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjust node priorities based on the analysis results.

[0051] In S1, network monitoring tools are deployed at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and to collect network latency data within several time windows, specifically:

[0052] Network monitoring tools (such as Ping, Traceroute, or dedicated latency analysis tools) are installed at each logistics node to continuously monitor network performance. These tools can run on servers or embedded devices at the logistics node and are responsible for measuring data transmission latency between the node and the cloud platform. The network monitoring tools run on devices that communicate with the cloud platform, typically including the node's host system or edge computing devices. The tools automatically send data packets to the cloud platform at a set frequency and measure the time from sending to receiving acknowledgment.

[0053] Each node periodically sends probe data packets to the cloud platform, recording the following key information: Data packet transmission time: Records the timestamp of the data packet being sent from the logistics node. Data packet return time: Records the timestamp of the cloud platform receiving the data packet and returning an acknowledgment packet. Round-trip time (RTT): Calculated by the difference between the transmission time and the return time, indicating the current network latency. For example, if the transmission time is 10:00:00.000 and the return time is 10:00:00.050, then the RTT is 50 milliseconds.

[0054] Measurements are not performed in a single instance, but rather by continuously collecting latency data within a defined time window, forming a statistically significant sample set. Time window setting: Select an appropriate time window (e.g., 10 minutes, 1 hour, or 24 hours) to capture dynamic changes in network latency. Sampling frequency: Set measurement intervals of one second, one minute, or longer to ensure sufficient sampling density to reflect network conditions. Within a time window, a node may generate several useful data metrics: Average RTT: Reflects the overall level of network latency. Maximum RTT and Minimum RTT: Reflect the worst and best states of network latency, respectively. Jitter: Reflects the volatility of network latency by calculating the difference between consecutive RTTs.

[0055] The collected RTT data is stored in a local database on the node or transmitted to a cloud platform for subsequent analysis. The stored content includes timestamps, RTT values, and network status markers (such as normal or abnormal). Preliminary aggregation and statistical processing are performed on the data, such as calculating the mean, standard deviation, and distribution range.

[0056] During data collection, network monitoring tools also analyze latency in real time for anomalies: Latency threshold setting: Set a normal range for RTT (e.g., within 50ms); values ​​exceeding this range are marked as abnormal. Trend monitoring: Detect whether RTT shows a gradual increase or severe fluctuations, indicating potential network problems.

[0057] Latency data analysis is used to assess network stability between nodes and the cloud platform. Transmission time during time synchronization is compensated based on latency data, reducing the impact of latency on time synchronization accuracy. Latency data can also be used to optimize network configurations, such as adjusting routing paths or increasing bandwidth.

[0058] S2: Analyze the latency jitter in the collected network latency data, determine the degree of latency anomaly between the node and the cloud platform, and evaluate the stability of the network transmission environment between the node and the cloud platform.

[0059] Latency jitter refers to the degree of variation between consecutive network delays, i.e., the range of unstable latency fluctuations. Jitter is usually caused by network congestion, routing changes, or hardware performance issues. Low jitter: The network transmission environment is stable, and the packet transmission delay is basically consistent. High jitter: The network transmission environment is unstable, and the latency varies significantly, which may affect the real-time performance and accuracy of logistics data.

[0060] From the collected RTT data, calculate the absolute difference between two consecutive RTTs: record all calculated jitter values ​​and calculate the average jitter to reflect the overall jitter level, and the maximum jitter to reflect the peak value of network jitter and show the fluctuation range under extreme conditions.

[0061] The calculated jitter values ​​are statistically analyzed to determine the concentrated areas of jitter and the frequency of outliers: Normal jitter range: A normal range is set based on the network environment (e.g., jitter ≤ 5ms). Outlier jitter ratio: The proportion of jitter values ​​exceeding the normal range is counted out of the total sample. A high outlier jitter ratio indicates network instability. Based on the statistical results of the jitter values, further latency anomaly detection is performed using the average RTT and the maximum and minimum RTT values: Stability indicators: Is the RTT range small (e.g., the difference between the minimum and maximum RTT ≤ 10ms)? Is the average jitter within a reasonable range (e.g., ≤ 5ms)? Outlier fluctuation detection: Does the RTT frequently jump significantly (e.g., two consecutive RTT changes exceeding 50ms)? Are there obvious latency spikes (e.g., RTT suddenly rising above 100ms in a short period of time)?

[0062] After analyzing the latency jitter in the network latency data, a latency jitter anomaly index is generated to assess the stability of the network transmission environment between the node and the cloud platform. The method for obtaining the latency jitter anomaly index is as follows:

[0063] Set latency jitter data From a certain latent distribution , where θ is the distribution parameter (such as mean and variance), and n is the total number of time-delay jitter data. A prior distribution p(θ) is set to reflect the initial belief about the parameters; a standard normal distribution is typically chosen. .

[0064] Through variational inference, the posterior is approximated by an easily tractable distribution q(θ). The optimization objective is to minimize the KL divergence between the two, expressed as: q(θ) is chosen to be a Gaussian distribution. Where μ and σ are the parameters to be optimized, and the prior distribution p(θ) is defined as follows: ; The prior variance, reflecting the initial belief about the uncertainty of the parameters, is defined as the observation likelihood p(X|θ): given the observation data. It follows a normal distribution, and its expression is: ; The mean of the jitter represents the center of stability of network latency. Let q(θ) be the variance of the jitter, representing the amplitude of network jitter fluctuations. The variational distribution q(θ) is chosen to be a Gaussian distribution. ; These are the approximate posterior parameters obtained through optimization. Optimization is performed using gradient descent. Maximize the ELBO of the lower bound of evidence: For a Gaussian distribution, KL has an analytical solution: Using the optimized q(θ), calculate the q(θ) for each data point. The probability of an anomaly: Based on the anomaly probability of all data points, the latency jitter anomaly index is defined, and its expression is: In the formula, HWK is the time delay jitter anomaly index.

[0065] When the latency jitter index is high, it indicates significant instability in the network transmission environment between the node and the cloud platform. This means that the latency jitter value fluctuates frequently or exceeds the normal range, resulting in high volatility in network latency. In this situation, issues such as network congestion, route jumps, and insufficient hardware performance may lead to inconsistent data packet transmission times, further affecting the real-time synchronization and reliability of logistics data. If network configuration is not optimized in a timely manner, it may lead to a decline in system performance and even threaten the normal operation of the logistics system.

[0066] When the time-latency jitter anomaly index is low, it indicates that the network transmission environment between the node and the cloud platform is relatively stable, the fluctuation range of network latency is small, and the jitter value is basically within the normal range. This reflects that the data packet transmission time is relatively consistent, the network condition is good, and it can support the requirements of efficient logistics data synchronization and real-time performance. This stable transmission environment helps to reduce time synchronization deviations, improve the overall efficiency and response speed of the logistics system, and provide reliable data support for dynamic scheduling and event processing.

[0067] S3: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized by GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to evaluate the accuracy of node clock synchronization.

[0068] Deploy GPS clock synchronization devices, installing GPS clock modules at each logistics node as time reference devices. GPS clocks provide high-precision Global Standard Time (UTC) by receiving satellite signals, with errors typically on the nanosecond level.

[0069] Record the initial time difference ΔTinit between the clock of each node device and the GPS standard time: ΔTinit = TGPS - Tnode; where: TGPS is the time of the GPS clock, and Tnode is the time of the local clock of the node device.

[0070] Adjust the node device clock to align it with GPS time and eliminate the initial time difference: T after synchronization = T node + ΔTinit; ensure that the time of each node is consistent with the GPS clock and establish a unified time reference.

[0071] During the operation of the node device, the time difference between the node clock and the GPS clock is compared periodically. The expression is: ΔT(t) = TGPS(t) - Tnode(t); t is the time point for comparison.

[0072] Record the time difference at different time points and calculate the time drift value ΔR: in, They are time points and The time difference. The time interval is defined as ΔR. The time drift value ΔR represents the clock offset per unit time and is used to assess clock stability.

[0073] After analyzing the changes in drift value over time, a drift value fluctuation index is generated to evaluate the accuracy of node clock synchronization. The method for obtaining the drift value fluctuation index is as follows:

[0074] Input data: Clock drift value time series Where N is the total number of sampling points, and the sampling interval is Ts (seconds). To eliminate the DC component (zero-frequency component) of the drift values, the mean of the sequence is removed, expressed as: ; for the mean-removed drift value sequence Performing a Fast Fourier Transform yields the frequency domain signal in complex form: ; It is the kth frequency component. These are the amplitude and phase of a frequency domain signal; the magnitude of the amplitude represents the intensity of the vibration at each frequency. The kernel function for the Fourier transform; calculate the frequency amplitude: In the formula, yes The real part, yes The imaginary part; calculating the total energy of the frequency domain signal. The expression is: Only the first N / 2 points are used because the FFT output is symmetric. The energy of the high-frequency components is calculated. , It is the high-frequency boundary point, expressed as: The drift value fluctuation index is calculated using the following expression: GHQ is the drift value fluctuation index.

[0075] A large drift value fluctuation index indicates that high-frequency fluctuations dominate the node clock's drift value, with frequent and significant changes. This suggests poor clock stability and a significantly irregular time difference from the standard clock. A larger drift value fluctuation index indicates lower clock synchronization accuracy, potentially leading to accumulated time synchronization errors and affecting the system's accurate judgment of event sequence and time-sensitive tasks.

[0076] When the drift value fluctuation index is small, it indicates that the node clock's drift value changes relatively smoothly, with low-frequency components dominating and fluctuation amplitudes being small. This suggests that the node clock operates relatively stably, its time difference with the standard clock follows the same trend, and the amplitude is within a controllable range. The smaller the drift value fluctuation index, the higher the accuracy of node clock synchronization, enabling more reliable support for real-time synchronization and scheduling of logistics data.

[0077] S4: Determine the severity of time synchronization deviation between logistics nodes based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of node clock synchronization.

[0078] The time delay jitter anomaly index and drift value fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to the machine learning model. The machine learning model uses the prediction of the severity label of time synchronization deviation between logistics nodes for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of prediction errors for the severity labels of time synchronization deviation between all logistics nodes. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The severity value of time synchronization deviation between logistics nodes is determined based on the model output. The machine learning model is a multinomial regression model.

[0079] The method for obtaining the severity value of time synchronization deviation between logistics nodes is as follows: Obtain the corresponding function expression from the training data of the comprehensive feature vector of the trained machine learning model. In the formula, This is the model's output function, where HWK is the latency jitter anomaly index and GHQ is the drift value fluctuation index. This represents the severity of time synchronization deviations between logistics nodes.

[0080] S5: Classify the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and implement corresponding early warning measures;

[0081] The severity values ​​of time synchronization deviation between logistics nodes are compared with gradient standard thresholds, which include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold. The severity values ​​of time synchronization deviation between logistics nodes are compared with the first standard threshold and the second standard threshold respectively.

[0082] If the severity of the time synchronization deviation between logistics nodes is greater than the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is high. At this time, a first-level warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a severe deviation.

[0083] If the severity of the time synchronization deviation between logistics nodes is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is moderate. At this time, a level 2 warning signal is generated to classify the severity of the time synchronization deviation between logistics nodes as a moderate deviation.

[0084] If the severity of the time synchronization deviation between logistics nodes is less than the first standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is low. At this time, a level three warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a minor deviation.

[0085] It should be noted that Level 1 warning signals are more important than Level 2 warning signals, and Level 2 warning signals are more important than Level 3 warning signals. Relevant personnel can take corresponding measures according to the different warning signal levels.

[0086] Level 1 Warning Signal (Severe Deviation) Importance: Highest priority. It indicates that the time synchronization deviation of logistics nodes seriously affects the normal operation of the system, which may lead to the failure of real-time synchronization of logistics data, disordered event sequence, or scheduling task errors.

[0087] Isolate severely skewed logistics nodes from the real-time synchronization network to prevent their erroneous data from causing a cascading effect on other nodes. Switch to a backup node to ensure continuous operation of the logistics system. Perform deep time calibration on the problematic node using GPS or NTP to reset its clock. Inspect and optimize the network configuration of the problematic node, such as adjusting routing, increasing bandwidth, or replacing hardware. Notify relevant technical personnel to immediately investigate the problem and repair equipment or network faults.

[0088] Level 2 warning signal (moderate deviation) importance level: medium priority, indicating that time synchronization deviation between nodes may affect some functions of the system, such as scheduling delays or event sequence deviations.

[0089] Real-time monitoring of nodes with moderate time synchronization deviations is implemented to observe whether the deviation continues to worsen. During data synchronization, a time deviation compensation mechanism is introduced for nodes with moderate deviations to reduce the impact of the deviation on the system. Regular clock calibration of nodes is scheduled to reduce drift errors, and their time synchronization mechanism with the cloud platform is optimized. Network latency jitter issues are investigated, and transmission lines are optimized or unstable hardware is replaced. Intermediate alerts are sent to the technical support team to track node operational status.

[0090] Level 3 warning signal (minor deviation) importance level: lowest priority, indicating that the time synchronization deviation between nodes is low and has a limited impact on system operation, but attention should be paid to prevent the accumulation of problems.

[0091] Nodes with slight deviations should be placed on a watchlist, and their time synchronization status should be recorded regularly to ensure that the deviation remains within a controllable range. During the next system maintenance or upgrade, the clock synchronization accuracy and network transmission quality of nodes with slight deviations should be optimized. Real-time synchronization data of nodes with slight deviations should be backed up for quick recovery in case of problems. Low-priority notifications should be sent to relevant administrators, only alerting them to the node's operational status.

[0092] S6: For moderate deviations, predict and analyze the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjust node priorities based on the analysis results.

[0093] For moderate deviations, which are defined as the severity of time synchronization deviations between logistics nodes generated within a fixed time window being greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the severity of time synchronization deviations between logistics nodes generated within subsequent fixed time windows that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding dataset is established. The mean and standard deviation of the dataset are calculated, and after analysis, the node priority is dynamically adjusted based on the analysis results.

[0094] If the mean severity of time synchronization deviations within the dataset is greater than or equal to the reference threshold for the mean severity of time synchronization deviations, and the standard deviation of the severity of time synchronization deviations is less than the reference threshold for the standard deviation of the severity of time synchronization deviations, the overall severity of time synchronization deviations is high but the fluctuation is small, indicating that the deviation values ​​are relatively stable. This may be a systemic problem or an inherent characteristic. In this case, a medium priority should be maintained, and deep optimization of the nodes should be planned, such as periodically recalibrating the clock or adjusting the network configuration, to reduce the overall deviation level.

[0095] If the mean severity of time synchronization deviations is greater than or equal to the reference threshold, and the standard deviation of the severity of time synchronization deviations is greater than or equal to the reference threshold of the standard deviation of the severity of time synchronization deviations, the overall severity of time synchronization deviations is high and fluctuates greatly. This indicates that the node's time synchronization is unstable and easily affected by external factors (such as network fluctuations). In this case, the node's priority should be reduced to minimize its interference with the system's real-time synchronization. At the same time, the deviation trend of this node should be closely monitored, and more stringent network and clock calibration measures should be taken if necessary.

[0096] If the mean severity value of time synchronization deviation is less than the reference threshold for the mean severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is greater than or equal to the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low but fluctuates greatly, indicating that the node operates normally most of the time, but occasionally significant deviations occur. In this case, a medium priority should be maintained, while dynamic monitoring of the node should be enhanced. When the deviation fluctuation is significant, temporary optimization measures should be triggered, such as restarting the synchronization process or short-term isolation.

[0097] If the average severity value of time synchronization deviation is less than the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is less than the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low and the fluctuation is small, indicating that the node's operating status is relatively stable. In this case, the node's priority should be increased, allowing it to participate more in the system's real-time synchronization tasks, while reducing the consumption of its monitoring resources to lower the system load.

[0098] In this embodiment, firstly, network monitoring tools are deployed at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, collecting network latency data within multiple time windows. Next, latency jitter analysis is performed on the collected network latency data to assess the stability of the network transmission environment between the node and the cloud platform. When network transmission instability is detected, the time of each node is synchronized via GPS clock, and the initial time difference is recorded. Clock drift values ​​are periodically compared to assess the accuracy of node clock synchronization. Subsequently, combining network transmission environment stability and clock synchronization accuracy, the severity of time synchronization deviations between logistics nodes is determined. Based on the severity of the deviation, it is classified into minor, moderate, and severe deviations, and corresponding warning signals are generated, with appropriate handling measures implemented. For moderate deviations, the changing trend of time synchronization deviation severity is predicted within subsequent fixed time windows, dynamically adjusting node priorities and optimizing system resource allocation and operating efficiency.

[0099] Example 2: This example describes a multi-node collaborative real-time logistics data synchronization system, which includes a network latency monitoring module, a network stability analysis module, a clock synchronization and drift assessment module, a deviation severity assessment module, an early warning response module, and a node priority adjustment module.

[0100] Network latency monitoring module: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows;

[0101] Network stability analysis module: Analyzes the latency jitter in the collected network latency data, determines the degree of latency anomaly between the node and the cloud platform, and evaluates the stability of the network transmission environment between the node and the cloud platform;

[0102] Clock synchronization and drift assessment module: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized by GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to assess the accuracy of node clock synchronization.

[0103] Deviation Severity Assessment Module: Based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of the node clock synchronization, the severity of time synchronization deviation between logistics nodes is determined;

[0104] Early warning response module: Classifies the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and performs corresponding early warning processing;

[0105] Node priority adjustment module: For moderate deviations, it predicts and analyzes the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjusts node priorities based on the analysis results.

[0106] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0107] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0108] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0109] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for real-time synchronization of logistics data in a multi-node collaborative manner, characterized in that: Includes the following steps: S1: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows; S2: Analyze the latency jitter in the collected network latency data, determine the degree of latency anomaly between the node and the cloud platform, and evaluate the stability of the network transmission environment between the node and the cloud platform. S3: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized through GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to evaluate the accuracy of node clock synchronization. S4: Determine the severity of time synchronization deviation between logistics nodes based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of node clock synchronization; S5: Classify the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and implement corresponding early warning measures; S6: For moderate deviations, predict and analyze the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjust node priorities based on the analysis results.

2. The method for real-time synchronization of multi-node collaborative logistics data according to claim 1, characterized in that: In S2, a latency jitter index is generated after analyzing the latency jitter in the network latency data.

3. The method for real-time synchronization of logistics data through multi-node collaboration according to claim 2, characterized in that: In S3, the drift value fluctuation index is generated after analyzing the changes in the drift value over time. The method for obtaining the drift value fluctuation index is as follows: Setting clock drift value time series Where N is the total number of sampling points and the sampling interval is Ts, the expression for removing the mean from the sequence is: ; The drift value sequence after removing the mean Performing a Fast Fourier Transform yields the frequency domain signal in complex form: ; It is the kth frequency component. It is the amplitude of the frequency domain signal, and the magnitude of the amplitude represents the amplitude intensity at each frequency. This is the kernel function for the Fourier transform; Calculate the frequency amplitude: In the formula, yes The real part, yes The imaginary part; calculating the total energy of the frequency domain signal. The expression is: ; Calculate the energy of high-frequency components , It is the high-frequency boundary point, expressed as: The drift value fluctuation index is calculated using the following expression: GHQ is the drift value fluctuation index.

4. The method for real-time synchronization of logistics data in multi-node collaboration according to claim 3, characterized in that: In S4, the severity of time synchronization deviations between logistics nodes is determined based on the stability of the network transmission environment between the nodes and the cloud platform, as well as the accuracy of node clock synchronization. Specifically: The time delay jitter anomaly index and drift value fluctuation index are converted into a comprehensive feature vector. This comprehensive feature vector is used as the input to the machine learning model. The machine learning model uses the prediction of the severity label of time synchronization deviation between logistics nodes for each set of comprehensive feature vectors as the prediction objective. The training objective is to minimize the sum of prediction errors for the severity labels of time synchronization deviation between all logistics nodes. The machine learning model is trained until the sum of prediction errors converges, at which point the model training stops. The severity value of time synchronization deviation between logistics nodes is determined based on the model output. The machine learning model is a multinomial regression model.

5. The method for real-time synchronization of logistics data in multi-node collaboration according to claim 4, characterized in that: In S5, the severity of time synchronization deviations between logistics nodes is divided into minor deviations, moderate deviations, and severe deviations, and corresponding early warning measures are implemented. The severity values ​​of time synchronization deviation between logistics nodes are compared with gradient standard thresholds, which include a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold. The severity values ​​of time synchronization deviation between logistics nodes are compared with the first standard threshold and the second standard threshold respectively. If the severity of the time synchronization deviation between logistics nodes is greater than the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is high. At this time, a first-level warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a severe deviation. If the severity of the time synchronization deviation between logistics nodes is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is moderate. At this time, a level 2 warning signal is generated to classify the severity of the time synchronization deviation between logistics nodes as a moderate deviation. If the severity of the time synchronization deviation between logistics nodes is less than the first standard threshold, it indicates that the severity of the time synchronization deviation between logistics nodes is low. At this time, a level three warning signal is generated, classifying the severity of the time synchronization deviation between logistics nodes as a minor deviation.

6. The method for real-time synchronization of logistics data in multi-node collaboration according to claim 5, characterized in that: In S6, for moderate deviations, i.e., the severity of time synchronization deviations between logistics nodes generated within a fixed time window is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the severity of time synchronization deviations between logistics nodes generated within subsequent fixed time windows that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding dataset is established. The mean and standard deviation of the dataset are calculated, and after analysis, the node priority is dynamically adjusted based on the analysis results.

7. The method for real-time synchronization of logistics data in multi-node collaboration according to claim 6, characterized in that: If the mean severity of time synchronization deviation within the dataset is greater than or equal to the reference threshold for the mean severity of time synchronization deviation, and the standard deviation of the severity of time synchronization deviation is less than the reference threshold for the standard deviation of the severity of time synchronization deviation, the overall severity of time synchronization deviation is high but the fluctuation is small. In this case, a medium priority should be maintained, and the clock should be recalibrated or the network configuration adjusted periodically to reduce the overall deviation level. If the mean severity of time synchronization deviation is greater than or equal to the reference threshold for the mean severity of time synchronization deviation, and the standard deviation of the severity of time synchronization deviation is greater than or equal to the reference threshold for the standard deviation of the severity of time synchronization deviation, the overall severity of time synchronization deviation is high and fluctuates greatly. In this case, the node priority should be reduced. If the average severity value of time synchronization deviation is less than the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is greater than or equal to the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low but fluctuates greatly. In this case, a medium priority should be maintained, and dynamic monitoring of the node should be enhanced. If the average severity value of time synchronization deviation is less than the reference threshold for the average severity value of time synchronization deviation, and the standard deviation of the severity value of time synchronization deviation is less than the reference threshold for the standard deviation of the severity value of time synchronization deviation, the overall time synchronization deviation is low and the fluctuation is small. In this case, the node priority should be increased, the occupation of its monitoring resources should be reduced, and the system load should be reduced.

8. A multi-node collaborative real-time logistics data synchronization system, used to implement the multi-node collaborative real-time logistics data synchronization method according to any one of claims 1-7, characterized in that: It includes a network latency monitoring module, a network stability analysis module, a clock synchronization and drift assessment module, a deviation severity assessment module, an early warning response module, and a node priority adjustment module. Network latency monitoring module: Deploy network monitoring tools at each logistics node to periodically measure the round-trip latency between the node and the cloud platform, and collect network latency data within several time windows; Network stability analysis module: Analyzes the latency jitter in the collected network latency data, determines the degree of latency anomaly between the node and the cloud platform, and evaluates the stability of the network transmission environment between the node and the cloud platform; Clock synchronization and drift assessment module: When the network transmission environment between the node and the cloud platform becomes unstable, the time of each node is synchronized by GPS clock, and the initial time difference of each node is recorded. The clock of each node is periodically compared with the standard clock to determine the change of drift value over time and to assess the accuracy of node clock synchronization. Deviation Severity Assessment Module: Based on the stability of the network transmission environment between the node and the cloud platform and the accuracy of the node clock synchronization, the severity of time synchronization deviation between logistics nodes is determined; Early warning response module: Classifies the severity of time synchronization deviations between logistics nodes into minor deviations, moderate deviations, and severe deviations, and performs corresponding early warning processing; Node priority adjustment module: For moderate deviations, it predicts and analyzes the severity of time synchronization deviations between logistics nodes within a subsequent fixed time window, and dynamically adjusts node priorities based on the analysis results.

Images