Container logistics whole-course tracking management system based on RFID

Abstract

The invention discloses an RFID-based container logistics whole-course tracking management system, and relates to the technical field of logistics management, a signal acquisition module acquires RFID signals in different environments and evaluates the environmental interference degree of the RFID signals, and a data transmission monitoring module records and analyzes a delay scene, so that the reliability of the system is improved. The real-time performance evaluation module performs real-time performance level-to-level management on the logistics data, and the dynamic management module performs real-time performance level-to-level management on the logistics data by predicting the real-time performance change condition in a fixed time period in the future according to the real-time performance data so as to comprehensively master the data transmission performance. The data uploading frequency is dynamically adjusted, efficient classification management and resource optimization configuration of the container logistics data are achieved, transparency, reliability and decision-making efficiency of the logistics management system are effectively improved, and the logistics management system is particularly prominent in emergency scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a container logistics full-process tracking management system based on RFID. Background Art

[0002] RFID is a technology that transmits and identifies data through wireless radio frequency signals. It has the characteristics of contactless, fast scanning and batch reading. In container logistics, each container can be installed with a unique RFID tag, which stores information about the container (such as number, cargo category, destination, etc.). RFID reading and writing devices are arranged at various nodes in the logistics chain (such as ports, warehouses, transport vehicles, etc.). When the container passes through these nodes, the system automatically scans and records its location, status and time information. By integrating with the background management system, this tracking method can update the dynamic information of the container in real time and realize transparent management from shipment to destination. RFID-based tracking management has the advantages of strong real-time, high efficiency and accurate data, which can significantly improve the efficiency of logistics operations and reduce the cost of manual intervention. In practical applications, this technology can be widely used in international trade, port operations and logistics companies to help companies optimize transportation routes, monitor container status (such as temperature, vibration), and prevent cargo loss or damage.

[0003] The prior art has the following deficiencies: In the global logistics chain, a large amount of real-time data generated by the RFID system needs to be uploaded to the centralized backend management platform. However, due to network conditions, server load or compatibility issues between different systems, data upload and synchronization may be delayed, especially in sea transportation or remote logistics scenarios. This delay will cause the container logistics management system to be unable to reflect the status of the container in real time, affecting the efficiency of logistics management and the accuracy of decision-making, especially in emergency scenarios (such as the need to quickly re-dispatch goods). In addition, the delay in data upload and synchronization of the container logistics management system will directly lead to the inability to update the container location information in real time, and the system may display a lagging or erroneous status. In this case, all parties in the logistics chain (such as shippers, transportation companies, ports) cannot accurately grasp the dynamic location of the goods, lose transparency into the transportation progress and container status, and may lead to a crisis of trust. Summary of the invention

[0004] The purpose of the present invention is to provide a container logistics full-process tracking management system based on RFID to solve the shortcomings of the background technology.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a container logistics full-process tracking and management system based on RFID, comprising a signal acquisition module, a signal interference analysis module, a data transmission monitoring module, a throughput analysis module, a real-time evaluation module and a dynamic management module; Signal acquisition module: select test points in different environments at several logistics nodes, including open areas, metal-intensive areas, and high-humidity areas, and use RFID reading and writing equipment to collect multiple signals from tags at different locations; Signal interference analysis module: measures the signal strength of the collected RFID tags, compares the signal strength and reading success rate under different environments, determines the correlation between signal strength and reading delay, and evaluates the degree of interference of environmental factors on the signal strength of RFID reading and writing equipment; Data transmission monitoring module: If the interference level is high, different types of monitoring tools are deployed at each logistics node to record the entire process from data reading to data uploading. Comparative tests are conducted in high-latency and low-latency scenarios to measure the transmission delay between nodes. Throughput analysis module: builds a high-load scenario, increases simulated data traffic, analyzes the fluctuation of the occupancy rate of data transmission throughput between nodes during the actual transmission process, and evaluates the abnormality of data transmission efficiency from RFID reading and writing devices to the background management platform; Real-time evaluation module: Based on the degree of interference of the signal strength of the RFID reader / writer device by environmental factors and the abnormality of the data transmission efficiency from the RFID reader / writer device to the background management platform, the real-time performance of the container logistics data upload and synchronization is evaluated. Based on the evaluation results, the corresponding container logistics data is divided into high real-time data, medium real-time data and low real-time data, and corresponding management is carried out; Dynamic management module: For real-time data, further prediction is made on the real-time changes in container logistics data upload and synchronization within a fixed time period in the future, and the frequency of data upload is dynamically adjusted based on the prediction results.

[0006] Preferably, in the signal interference analysis module, the correlation between the signal strength and the read delay is analyzed to generate a delay correlation index, and the delay correlation index is obtained by: The signal strength X is divided into multiple intervals by range, and the reading delay Y is divided into multiple intervals by time. Each sample data is mapped to the corresponding interval according to its value to form a discretized data set. For all sample pairs (xi, yi), the frequency of occurrence of each interval combination is counted, and then normalized to obtain the probability. The formula is: ;in, represents the number of samples where X=x and Y=y. The sum of P(x,y) by y or x is P(x) and P(y), respectively. The expressions are: ; Sum all interval combinations (x, y) and calculate the delay correlation index, the expression is: ; In the formula, is the delay correlation index.

[0007] Preferably, in the throughput analysis module, after analyzing the fluctuation of the occupancy ratio of the data transmission throughput between each node during the actual transmission process, a throughput occupancy ratio fluctuation index is generated, and the method for obtaining the throughput occupancy ratio fluctuation index is: Collect the actual throughput usage ratio in high-load scenarios , define the ideal throughput utilization ratio curve , the distance function d(q,c) is used to calculate the difference between the actual value q and the ideal value c, using the Euclidean distance formula: ; Construct an n×m cumulative distance matrix D to represent the alignment cost of sequences Q and C, where n is the length of the actual sequence Q and m is the length of the ideal sequence C. Recursively calculate D(i,j): D(i,j)=d(qi,cj)+min{D(i−1,j),D(i,j−1),D(i−1,j−1)}; where D(i−1,j) represents the cost of aligning the current point with the previous point in the actual sequence, D(i,j−1) represents the cost of aligning the current point with the previous point in the ideal sequence, and D(i−1,j−1) represents the cost of aligning the current point with the previous point in both sequences. The initial condition is: D(0,0)=d(q0,c0); The boundary condition is that the cumulative value of the first row and the first column is the one-way sum on the path. Starting from the lower right corner of the matrix D(n,m), backtrack along the path with the minimum cumulative cost to find the optimal alignment path w(i); Accumulate the cost value on the path , the expression is: ; The calculated cost value on the cumulative path is normalized to obtain the throughput occupancy ratio fluctuation index.

[0008] Preferably, in the real-time evaluation module, the real-time performance of uploading and synchronizing container logistics data is evaluated according to the degree of interference of the signal strength of the RFID reading and writing device by environmental factors and the abnormality of the data transmission efficiency from the RFID reading and writing device to the background management platform; The delay correlation index and the throughput occupancy ratio fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the real-time value label of container logistics data upload and synchronization with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of all real-time value labels of container logistics data upload and synchronization as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The real-time value of container logistics data upload and synchronization is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0009] Preferably, the obtained real-time value of uploading and synchronizing the container logistics data is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time value of uploading and synchronizing the container logistics data is compared with the first standard threshold and the second standard threshold respectively; If the real-time value of the container logistics data upload and synchronization is greater than the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is high, and a high real-time signal is generated at this time, and the corresponding container logistics data is classified as high real-time data; If the real-time value of the container logistics data upload and synchronization is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is medium, and a medium real-time signal is generated at this time, and the corresponding container logistics data is classified as medium real-time data; If the real-time value of container logistics data uploading and synchronization is less than the first standard threshold, it means that the real-time of container logistics data uploading and synchronization is low. At this time, a low real-time signal is generated and the corresponding container logistics data is classified as low real-time data.

[0010] Preferably, in the dynamic management module, for the real-time data, the real-time changes of container logistics data upload and synchronization in a future fixed time period are further predicted, and the frequency of data upload is dynamically adjusted according to the prediction results, specifically: For medium real-time data, that is, the real-time value of container logistics data upload and synchronization generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time values ​​generated in the future fixed time period 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 data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, further predictions are made on the real-time changes of container logistics data upload and synchronization in the future fixed time period based on the analysis results.

[0011] Preferably, if the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, a third-level warning signal is generated, the upload frequency is reduced, the upload cycle is extended, and batch processing is adopted; If the mean of the real-time values ​​is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, no warning signal will be generated, the upload frequency will be maintained, and monitoring will be strengthened; If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, a first-level warning signal is generated, the upload frequency is increased, the timeliness of data upload is prioritized, and network conditions are optimized; If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, a secondary warning signal is generated to reduce the upload frequency and concentrate resources to optimize the transmission link.

[0012] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention significantly improves the real-time performance and stability of the container logistics management system during data upload and synchronization through multi-module collaborative design. Through the signal acquisition module and the signal interference analysis module, the RFID signal strength and delay characteristics under different logistics environments are deeply analyzed, and the environmental factors affecting data transmission are effectively identified; combined with the data transmission monitoring module and the throughput analysis module, the delay and throughput fluctuations in the data transmission process are accurately measured and evaluated, providing a scientific basis for optimizing transmission performance. At the same time, through the real-time evaluation module, the system can achieve efficient classification management of logistics data (high real-time, medium real-time, low real-time), and dynamically adjust the resource allocation strategy, thereby improving the system's responsiveness to high-priority tasks.

[0013] 2. The present invention can significantly reduce data upload delays, improve the efficiency of collaboration between logistics nodes, provide real-time and accurate cargo dynamic information to all parties in the logistics chain (such as shippers, transportation companies, ports), enhance the transparency of the logistics system, and reduce trust risks and management decision-making errors caused by information lags. In addition, through the prediction and frequency adjustment of real-time data in the dynamic management module, the utilization of system resources is optimized, and the network load and transmission performance are balanced, especially in emergency scenarios and high-load scenarios. The application of the present invention not only realizes real-time tracking and management of the entire container logistics process, but also provides reliable support for the digital and intelligent development of the logistics chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] For examples, see Figure 1 As shown, the RFID-based container logistics full-process tracking management system described in this embodiment includes a signal acquisition module, a signal interference analysis module, a data transmission monitoring module, a throughput analysis module, a real-time evaluation module and a dynamic management module; Signal acquisition module: select test points in different environments at several logistics nodes, including open areas, metal-intensive areas, and high-humidity areas, and use RFID reading and writing equipment to collect multiple signals from tags at different locations; Signal interference analysis module: measures the signal strength of the collected RFID tags, compares the signal strength and reading success rate under different environments, determines the correlation between signal strength and reading delay, and evaluates the degree of interference of environmental factors on the signal strength of RFID reading and writing equipment; Data transmission monitoring module: If the interference level is high, different types of monitoring tools are deployed at each logistics node to record the entire process from data reading to data uploading. Comparative tests are conducted in high-latency and low-latency scenarios to measure the transmission delay between nodes. Throughput analysis module: builds a high-load scenario, increases simulated data traffic, analyzes the fluctuation of the occupancy rate of data transmission throughput between nodes during the actual transmission process, and evaluates the abnormality of data transmission efficiency from RFID reading and writing devices to the background management platform; Real-time evaluation module: Based on the degree of interference of the signal strength of the RFID reader / writer device by environmental factors and the abnormality of the data transmission efficiency from the RFID reader / writer device to the background management platform, the real-time performance of the container logistics data upload and synchronization is evaluated. Based on the evaluation results, the corresponding container logistics data is divided into high real-time data, medium real-time data and low real-time data, and corresponding management is carried out; Dynamic management module: For real-time data, further prediction is made on the real-time changes in container logistics data upload and synchronization within a fixed time period in the future, and the frequency of data upload is dynamically adjusted based on the prediction results.

[0018] In the signal acquisition module, test points are arranged in representative logistics environments to cover typical RFID application scenarios. Open area: few obstacles and good signal propagation conditions. Test location: open yards at ports and open areas in logistics parks. Test the signal strength and reading success rate under the best environment as a performance benchmark. Metal-dense area: dense metal objects may cause signal reflection and shielding. Test location: warehouses with large amounts of metal goods, and transport vehicles loaded with metal products. Evaluate the impact of metal interference on RFID signals. High humidity area: more water molecules, which may absorb or attenuate radio frequency signals in certain frequency bands. Test location: cold storage, logistics scenarios in coastal areas, and rainy operating environments. Test the impact of humidity environment on signal propagation and tag reading.

[0019] Arrange RFID readers and writers at each test point to ensure that the coverage is consistent with the actual logistics operation. Select an ultra-high frequency (UHF) RFID reader / writer suitable for logistics scenarios, usually with a frequency band of 860-960MHz. Tags should support multi-environment applications (such as anti-metal tags, waterproof tags). Install the reader / writer according to typical usage (such as fixed installation at the entrance, or handheld for scanning). Ensure that the line of sight between the reader / writer and the tag is clear (avoid obstructions) and record the distance between the tag and the reader / writer. Adjust the reader / writer's transmit power (such as 0.1W to 2W) and antenna angle to optimize the signal reception range. Configure the tag's data storage fields, including unique ID, cargo type, etc.

[0020] Perform multiple signal acquisitions on tags at different locations, and record the signal strength and reading results. Arrange several tags at the test point. The tag installation positions should include: Easy-to-read position: The tag is facing the antenna or close to the reader. The tag is partially blocked or installed on an irregular surface (such as metal). Use the reader to scan each tag at least 20 times, and record data including: Signal strength (RSSI): The power of the signal returned by the tag. Read success rate: The ratio of successful reads to the total number of attempts. Read delay: The time from initiating the read to receiving the tag data. Record environmental parameters (such as metal object density, humidity, and temperature) at each test point and associate them with the signal data for analysis. Store the acquisition results on the local device and upload them to the central management platform for centralized analysis.

[0021] Signal interference analysis module: measures the signal strength of the collected RFID tags, compares the signal strength and reading success rate in different environments, determines the correlation between signal strength and reading delay, and evaluates the degree of interference of environmental factors on the signal strength of RFID reading and writing equipment.

[0022] Use RFID reader / writer to read the specified tag multiple times at each test point (such as open areas, metal-dense areas, and high-humidity areas). Record the signal strength (RSSI, Received Signal Strength Indicator) returned during each read. RSSI is usually expressed as a negative decibel milliwatt (dBm). The closer the value is to 0, the stronger the signal. Calculate the read success rate: At each test point, read the same tag multiple times and record the ratio of the number of successful reads to the total number of attempts. For example: Analyze the relationship between signal strength and read success rate: Compare the signal strength and read success rate in different environments to observe whether there are the following trends: High signal strength (such as -30dBm to -50dBm): Usually corresponds to a higher read success rate. Low signal strength (such as below -70dBm): May cause read failure or a significant decrease in success rate.

[0023] Measures the time taken from initiating a read request to successfully reading data (in milliseconds). Record the latency of each read at each test point and take the average as the representative value at that point. Compare the changing trends between signal strength and read latency: High signal strength: Usually low latency and fast reading. It may cause multiple read attempts or communication errors, increasing latency. Determine whether the decrease in signal strength directly leads to an increase in read latency, thereby revealing the specific impact of the environment on read performance.

[0024] After analyzing the correlation between signal strength and reading delay, a delay correlation index is generated to evaluate the degree to which the signal strength of the RFID reader / writer is affected by environmental factors. The delay correlation index is obtained as follows: Divide the signal strength X into multiple intervals by range (for example, -90dBm to -30dBm is divided into 10 intervals). Divide the read delay Y into multiple intervals by time (for example, 0ms to 200ms is divided into 10 intervals). Map each sample data to the corresponding interval according to its value to form a discretized data set.

[0025] For all sample pairs (xi, yi), count the frequency of occurrence of each interval combination, and then normalize it to get the probability, formula: ;in, represents the number of samples where X=x and Y=y. The sum of P(x,y) by y or x is P(x) and P(y), respectively. The expressions are: ; Sum all possible interval combinations (x, y) and calculate the delay correlation index, the expression is: ; In the formula, is the delay correlation index.

[0026] When the delay correlation index is large, it means that the RFID signal strength is highly dependent on the reading delay, and the fluctuation of signal strength has a significant impact on the reading delay. This usually means that environmental factors (such as metal interference, high humidity, obstacle obstruction, etc.) have a significant interference with signal propagation, resulting in reduced or unstable signal strength, which in turn significantly increases the reading delay. For example, in metal-dense areas or high-humidity scenarios, the signal strength attenuates significantly, and the system needs multiple retries to successfully read the data, and the delay increases accordingly.

[0027] When the delay correlation index is small, it means that the relationship between signal strength and reading delay is weak, and reading delay is not significantly affected by signal strength fluctuations. This may indicate that the signal propagation of RFID reading and writing equipment in the current environment is relatively stable, and environmental factors have a low degree of interference with the signal. For example, in open areas or unobstructed logistics nodes, the signal strength remains at a high level, data can be read quickly, and the delay remains basically stable and is not significantly affected by signal strength.

[0028] Data transmission monitoring module: If the interference level is high, different types of monitoring tools are deployed at each logistics node to record the entire process from data reading to data uploading. Comparative tests are conducted in high-latency and low-latency scenarios to measure the transmission delay between nodes.

[0029] Select logistics nodes with severe signal interference (such as metal-dense areas, high-humidity areas, or nodes on complex transportation routes) for key monitoring. At the same time, select nodes with relatively stable signals (such as open areas) as comparison samples. Arrange appropriate monitoring equipment to cover the entire process of data from RFID readers to the background management platform: Reader performance monitor: Record tag reading success rate, signal strength, and reading delay. Edge computing equipment: Monitor local cache and data processing time. Network traffic analysis tool: Monitor transmission delay and throughput during data upload. Tool layout: Fixed monitoring: Installed in a fixed location at the port or warehouse for long-term monitoring of node performance. Mobile monitoring: Equipped with handheld RFID devices or vehicle-mounted edge computing devices to monitor dynamic data in transportation.

[0030] Record the complete data transmission process and categorize and store the test results in high-latency and low-latency scenarios. When reading data from RFID tags, record parameters such as signal strength, read success rate, and read latency. Data upload time from edge devices to the backend management platform, including network transmission latency and processing time. Scenarios with strong signal interference, unstable network, and latency exceeding the predetermined threshold. Scenarios with stable signals, smooth network, and latency within the normal range.

[0031] Test data transmission performance in scenarios with different levels of interference and analyze the key factors affecting latency. Design comparative tests: Run data transmission tests in high-latency scenarios (such as metal-dense areas) and low-latency scenarios (such as open areas). Test the latency distribution of each node in the transmission path, including: read latency from the tag to the reader. Upload latency from the edge device to the background. Adjust environmental variables (such as adding interference sources, changing signal frequency) to simulate scenarios with different levels of interference. Test changes in network status (such as high traffic congestion compared to idle periods). Compare data in high-latency and low-latency scenarios: Is the signal strength significantly reduced? Is the data upload latency significantly increased? Is there any abnormal retransmission or packet loss in high-latency scenarios.

[0032] Generate a latency analysis report to identify latency bottlenecks and provide optimization directions. Calculate total latency: Total latency = read latency + data upload latency. Calculate the mean and standard deviation for all test samples to evaluate latency distribution. Based on latency data, analyze whether the problem is mainly concentrated in the read phase or the upload phase: If the read latency is high, optimize the signal transmission performance of the reader and the tag. If the upload latency is high, optimize the network bandwidth or edge computing performance. Latency distribution chart (comparison of high latency and low latency scenarios). Evaluate the impact of environmental factors on latency (such as metal interference or humidity on the signal attenuation rate). Make optimization suggestions (such as improving equipment layout and introducing anti-interference tags).

[0033] Throughput analysis module: Build a high-load scenario, increase the simulated data traffic, analyze the fluctuation of the occupancy rate of the data transmission throughput between nodes during the actual transmission process, and evaluate the abnormality of the data transmission efficiency from the RFID reader to the background management platform.

[0034] Simulate a scenario where data traffic surges in the logistics chain to test the maximum throughput and stability of the transmission system. Simulate peak hours (such as concentrated loading and unloading of goods at ports or peak hours in and out of warehouses). Set up multiple RFID devices to read and upload data simultaneously to increase the amount of data. Use data generation tools or scripts to simulate large-scale RFID tag reading data. Each piece of data contains the tag ID, location, timestamp, and status information. Set the data frequency to 2 times, 5 times, or even higher than the normal traffic. Gradually increase the data traffic in the simulation environment and observe the changes in the system's throughput. Test traffic performance under different network conditions (such as bandwidth limitations, network congestion).

[0035] Measure the data throughput between nodes and analyze their performance under high load conditions. Define throughput: Throughput: The amount of data successfully transmitted per unit time (unit: Mbps or pieces / second). Formula: Throughput = total amount of data successfully transmitted / time; record the amount of data successfully read by the RFID device per second. Measure the data transmission speed from the reading device to the edge device. Measure the upload throughput from the edge device to the background. Monitor the data throughput utilization ratio under high load conditions, and record the instantaneous peak, average, and minimum values ​​of the throughput. Capture throughput fluctuations and calculate the fluctuation amplitude.

[0036] The throughput utilization ratio of each node is defined as the ratio of actual throughput to maximum theoretical throughput: utilization ratio = actual throughput / maximum throughput; compare the throughput utilization ratio under high load and normal load conditions. Calculate the fluctuation range of throughput: fluctuation range = (peak throughput - minimum throughput) / average throughput; when the utilization ratio is close to 100% or the fluctuation range is too high, it may mean that there is a transmission bottleneck or abnormality at the node.

[0037] After analyzing the fluctuation of the occupancy ratio of the data transmission throughput between nodes during the actual transmission process, a throughput occupancy ratio fluctuation index is generated to evaluate the abnormality of the data transmission efficiency from the RFID reader to the background management platform. The method for obtaining the throughput occupancy ratio fluctuation index is as follows: Actual throughput utilization ratio time series Q: collects the actual throughput utilization ratio under high load scenarios , recorded at fixed time intervals (such as every second or every minute). Ideal throughput occupancy ratio time series C: Defines the throughput occupancy ratio curve under ideal conditions , usually a stable constant value or an expected trend curve.

[0038] The distance function d(q,c) is used to calculate the difference between the actual value q and the ideal value c, using the Euclidean distance formula: ; Construct an n×m cumulative distance matrix D to represent the alignment cost of sequences Q and C, where n is the length of the actual sequence Q and m is the length of the ideal sequence C. Recursively calculate D(i,j): D(i,j)=d(qi,cj)+min{D(i−1,j),D(i,j−1),D(i−1,j−1)}; D(i−1,j) represents the cost of aligning the current point with the previous point in the actual sequence, D(i,j−1) represents the cost of aligning the current point with the previous point in the ideal sequence, and D(i−1,j−1) represents the cost of aligning the current point with the previous point in the two sequences at the same time. The initial condition is: D(0,0)=d(q0,c0); The boundary condition is that the cumulative value of the first row and the first column is the one-way sum on the path. Starting from the lower right corner of the matrix D(n,m), backtrack along the path with the minimum cumulative cost to find the optimal alignment path w(i); Accumulate the cost value on the path , the expression is: ; The calculated cost value on the cumulative path is normalized to obtain the throughput occupancy ratio fluctuation index.

[0039] When the throughput occupancy ratio fluctuation index is large, it indicates that the actual throughput is significantly different from the ideal state, and there is obvious fluctuation or instability in the transmission process. This usually reflects that the data transmission efficiency from the RFID reader to the background management platform is abnormally high, which may be caused by network congestion, insufficient node device performance or improper data traffic management. A high fluctuation index means that the transmission efficiency of the system is greatly affected, and data delays, packet loss or insufficient throughput may occur, which seriously affects the real-time and reliability of the logistics system.

[0040] When the throughput occupancy rate fluctuation index is small, it means that the actual throughput is close to the ideal state, the data transmission process is relatively stable, and the fluctuation range is small. In this case, the data transmission efficiency from the RFID reader to the background management platform is less abnormal, and the transmission link can maintain good performance under high-load scenarios. The low fluctuation index reflects that the system has strong anti-interference and resource allocation capabilities, and can effectively meet the large-scale data transmission needs between logistics nodes.

[0041] Real-time evaluation module: Based on the degree of interference of the signal strength of the RFID reader / writer device by environmental factors and the abnormality of the data transmission efficiency from the RFID reader / writer device to the background management platform, the real-time performance of the container logistics data upload and synchronization is evaluated. Based on the evaluation results, the corresponding container logistics data is divided into high real-time data, medium real-time data and low real-time data, and corresponding management is carried out; The delay correlation index and the throughput occupancy ratio fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the real-time value label of container logistics data upload and synchronization with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of all real-time value labels of container logistics data upload and synchronization as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The real-time value of container logistics data upload and synchronization is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0042] The method for obtaining the real-time value of container logistics data upload and synchronization is: obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, is the delay correlation index, GHM is the throughput occupancy ratio fluctuation index, It is the real-time value of uploading and synchronizing container logistics data.

[0043] The obtained real-time value of uploading and synchronizing the container logistics data is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time value of uploading and synchronizing the container logistics data is compared with the first standard threshold and the second standard threshold respectively; If the real-time value of the container logistics data upload and synchronization is greater than the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is high, and a high real-time signal is generated at this time, and the corresponding container logistics data is classified as high real-time data; If the real-time value of the container logistics data upload and synchronization is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is medium, and a medium real-time signal is generated at this time, and the corresponding container logistics data is classified as medium real-time data; If the real-time value of container logistics data uploading and synchronization is less than the first standard threshold, it means that the real-time of container logistics data uploading and synchronization is low. At this time, a low real-time signal is generated and the corresponding container logistics data is classified as low real-time data.

[0044] Highly real-time data is usually related to critical tasks or emergencies, and has high real-time requirements and needs to be uploaded and processed immediately. The delay of such data may cause the system to be unable to respond in time, thus affecting the key links of logistics operations.

[0045] High-real-time data is processed through a priority queue and immediately uploaded to the backend management platform. Use low-latency transmission protocols (such as MQTT, HTTPS) or dedicated transmission channels to ensure transmission timeliness. When high-real-time data (such as equipment anomalies, path deviations, and delays exceeding the standard) is detected, an alarm signal is triggered to notify the relevant person in charge or system. The alarm is sent to the user through multiple channels (SMS, email, APP push). Dispatch edge computing devices or network resources to assign priorities to high-real-time data to ensure that it is not occupied by low-priority tasks. Bandwidth or computing resources. When necessary, suspend low-real-time task processing to ensure the integrity and timeliness of high-real-time data.

[0046] Medium real-time data has relatively moderate timeliness requirements and is mostly used for periodic uploading and analysis. Its processing can be slightly delayed, but it needs to be completed within a specified time range to support logistics planning and resource allocation. Medium real-time data is uploaded to the backend management platform in batches. Set a time interval (such as every 10 minutes or every hour) to trigger the upload task regularly to avoid continuous occupation of network resources. Use the cache function of the edge device to temporarily store the medium real-time data and upload it when the network conditions are stable or the system load is reduced. Prevent medium real-time data transmission failure or occupation of high real-time channels when the network is congested. De-duplicate, clean and aggregate the medium real-time data before uploading to reduce the amount of redundant data and improve transmission efficiency. For example, continuous temperature data from multiple sensors can be uploaded with average values ​​or trend data instead of raw data.

[0047] Low real-time data is usually auxiliary or historical records of the logistics process and has no direct impact on the system's immediate response. The upload and processing of this type of data can be significantly delayed and is suitable for non-peak hours or background tasks.

[0048] Upload low-real-time data during off-peak hours (such as at night or when network traffic is low) to avoid occupying system resources. Use background tasks for batch processing to reduce the burden on the main system. Store low-real-time data on edge devices or local servers, and periodically archive and upload to the cloud. You can set upload cycles with long time intervals (such as daily or weekly). Highly compress low-real-time data to retain core information and reduce the bandwidth required for upload. For example, simplify hourly records of environmental data into daily summaries. Use for historical trend analysis, performance evaluation, and predictive maintenance, which do not require immediate processing. Combine with big data analysis tools to mine long-term accumulated data to support future decision optimization.

[0049] Dynamic management module: For real-time data, further prediction is made on the real-time changes in container logistics data upload and synchronization within a fixed time period in the future, and the frequency of data upload is dynamically adjusted based on the prediction results.

[0050] For medium real-time data, that is, the real-time value of container logistics data upload and synchronization generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time values ​​generated in the future fixed time period 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 data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, further predictions are made on the real-time changes of container logistics data upload and synchronization in the future fixed time period based on the analysis results.

[0051] If the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, it means that the real-time value is high, indicating that the performance of data upload and synchronization is relatively stable. A small standard deviation indicates that the real-time value fluctuates less and the data characteristics are more consistent. At this time, a third-level warning signal is generated, and the upload frequency is appropriately reduced to reduce the system load while ensuring the effective upload of data. The upload cycle can be extended and batch upload can be used to process data.

[0052] If the mean of the real-time value is greater than or equal to the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is greater than or equal to the reference threshold of the standard deviation of the real-time value, it means that the real-time value is high and the data upload performance is generally good, but the fluctuation is large and unstable. A high standard deviation indicates that the data in some time periods may be inconsistent, and attention should be paid to the cause of the fluctuation. At this time, no warning signal is generated, and the current upload frequency is maintained, and the existing upload frequency is maintained to avoid delays or losses caused by data fluctuations. Enhance monitoring, analyze the source of fluctuations (such as network congestion, insufficient node performance) and optimize.

[0053] If the mean of the real-time value is less than the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is greater than or equal to the reference threshold of the standard deviation of the real-time value, the real-time value is low, indicating that there are major problems with data upload performance. The standard deviation is high and the fluctuation is large, which may be affected by environmental factors or system load. At this time, a first-level warning signal is generated to increase the upload frequency and optimize network conditions: increase the upload frequency and give priority to ensuring the timeliness of data upload. Take optimization measures for the source of fluctuation (such as network congestion and insufficient hardware performance) to improve data transmission efficiency.

[0054] If the mean of the real-time value is less than the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is less than the reference threshold of the standard deviation of the real-time value, it means that the real-time value is low and the data upload performance is poor, but the fluctuation is small. The problem is manifested as poor overall upload performance rather than random anomalies. A low standard deviation indicates that the problem is persistent. At this time, a secondary warning signal is generated to further reduce the upload frequency and focus on optimizing transmission performance: while reducing the upload frequency, optimize the transmission link (such as increasing bandwidth and improving hardware performance). Solve long-term problems of data transmission performance by concentrating resources.

[0055] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. Relevant personnel can take corresponding management measures according to different warning signal levels.

[0056] In this embodiment, first, in the signal acquisition module, RFID signals are collected by logistics nodes in different environments (such as open areas, metal-dense areas, and high-humidity areas) to measure signal strength and reading success rate; then, in the signal interference analysis module, the correlation between signal strength and reading delay and the degree of environmental interference are evaluated; if the signal interference level is high, the data transmission monitoring module will deploy monitoring tools to record the entire process from reading to uploading data, and perform transmission delay tests on high-latency and low-latency scenarios; in the throughput analysis module, the fluctuation of the throughput occupancy ratio during data transmission is analyzed by simulating high-load scenarios, and the abnormal degree of RFID data transmission efficiency is evaluated; the real-time evaluation module comprehensively considers the above results, hierarchically manages the real-time performance of the data, and divides it into high real-time, medium real-time, and low real-time data; finally, the dynamic management module dynamically adjusts the data upload frequency for medium real-time data by predicting real-time changes within a fixed time period to ensure the optimal balance between system resource utilization and transmission efficiency.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0059] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A container logistics full-process tracking management system based on RFID, characterized by: It includes signal acquisition module, signal interference analysis module, data transmission monitoring module, throughput analysis module, real-time evaluation module and dynamic management module; Signal acquisition module: select test points in different environments at several logistics nodes, including open areas, metal-intensive areas, and high-humidity areas, and use RFID reading and writing equipment to collect multiple signals from tags at different locations; Signal interference analysis module: measures the signal strength of the collected RFID tags, compares the signal strength and reading success rate under different environments, determines the correlation between signal strength and reading delay, and evaluates the degree of interference of environmental factors on the signal strength of RFID reading and writing equipment; Data transmission monitoring module: If the interference level is high, different types of monitoring tools are deployed at each logistics node to record the entire process from data reading to data uploading. Comparative tests are conducted in high-latency and low-latency scenarios to measure the transmission delay between nodes. Throughput analysis module: builds a high-load scenario, increases simulated data traffic, analyzes the fluctuation of the occupancy rate of data transmission throughput between nodes during the actual transmission process, and evaluates the abnormality of data transmission efficiency from RFID reading and writing devices to the background management platform; Real-time evaluation module: Based on the degree of interference of the signal strength of the RFID reader / writer device by environmental factors and the abnormality of the data transmission efficiency from the RFID reader / writer device to the background management platform, the real-time performance of the container logistics data upload and synchronization is evaluated. Based on the evaluation results, the corresponding container logistics data is divided into high real-time data, medium real-time data and low real-time data, and corresponding management is carried out; Dynamic management module: For real-time data, further prediction is made on the real-time changes in container logistics data upload and synchronization within a fixed time period in the future, and the frequency of data upload is dynamically adjusted based on the prediction results.

2. The RFID-based container logistics full-process tracking management system according to claim 1 is characterized by: In the signal interference analysis module, the correlation between the signal strength and the read delay is analyzed to generate a delay correlation index. The delay correlation index is obtained as follows: The signal strength X is divided into multiple intervals by range, and the reading delay Y is divided into multiple intervals by time. Each sample data is mapped to the corresponding interval according to its value to form a discretized data set. For all sample pairs (xi, yi), the frequency of occurrence of each interval combination is counted, and then normalized to obtain the probability. The formula is: ;in, represents the number of samples where X=x and Y=y. The sum of P(x,y) by y or x is P(x) and P(y), respectively. The expressions are: ; Sum all interval combinations (x, y) and calculate the delay correlation index, the expression is: ; In the formula, is the delay correlation index.

3. The RFID-based container logistics full-process tracking management system according to claim 2 is characterized by: In the throughput analysis module, after analyzing the fluctuation of the occupancy ratio of the data transmission throughput between each node during the actual transmission process, a throughput occupancy ratio fluctuation index is generated. The method for obtaining the throughput occupancy ratio fluctuation index is as follows: Collect the actual throughput usage ratio in high-load scenarios , define the ideal throughput utilization ratio curve , the distance function d(q,c) is used to calculate the difference between the actual value q and the ideal value c, using the Euclidean distance formula: ; Construct an n×m cumulative distance matrix D to represent the alignment cost of sequences Q and C, where n is the length of the actual sequence Q and m is the length of the ideal sequence C. Recursively calculate D(i,j): D(i,j)=d(qi,cj)+min{D(i−1,j),D(i,j−1),D(i−1,j−1)}; where D(i−1,j) represents the cost of aligning the current point with the previous point in the actual sequence, D(i,j−1) represents the cost of aligning the current point with the previous point in the ideal sequence, and D(i−1,j−1) represents the cost of aligning the current point with the previous point in both sequences. The initial condition is: D(0,0)=d(q0,c0); the boundary condition is that the cumulative value of the first row and the first column is the one-way sum on the path. Starting from the lower right corner of the matrix D(n,m), backtrack along the path with the minimum cumulative cost to find the optimal alignment path w(i); accumulate the cost value on the path , the expression is: ; The calculated cost value on the cumulative path is normalized to obtain the throughput occupancy ratio fluctuation index.

4. The RFID-based container logistics full-process tracking management system according to claim 3 is characterized by: In the real-time evaluation module, the real-time performance of container logistics data upload and synchronization is evaluated based on the degree of interference of the signal strength of the RFID reader / writer device by environmental factors and the abnormality of the data transmission efficiency from the RFID reader / writer device to the background management platform. The delay correlation index and the throughput occupancy ratio fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the real-time value label of container logistics data upload and synchronization with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of all real-time value labels of container logistics data upload and synchronization as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The real-time value of container logistics data upload and synchronization is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The RFID-based container logistics full-process tracking management system according to claim 4 is characterized in that: The obtained real-time value of uploading and synchronizing the container logistics data is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time value of uploading and synchronizing the container logistics data is compared with the first standard threshold and the second standard threshold respectively; If the real-time value of the container logistics data upload and synchronization is greater than the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is high, and a high real-time signal is generated at this time, and the corresponding container logistics data is classified as high real-time data; If the real-time value of the container logistics data upload and synchronization is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the real-time of the container logistics data upload and synchronization is medium, and a medium real-time signal is generated at this time, and the corresponding container logistics data is classified as medium real-time data; If the real-time value of container logistics data uploading and synchronization is less than the first standard threshold, it means that the real-time of container logistics data uploading and synchronization is low. At this time, a low real-time signal is generated and the corresponding container logistics data is classified as low real-time data.

6. The RFID-based container logistics full-process tracking management system according to claim 1 is characterized by: In the dynamic management module, for real-time data, further predictions are made on the real-time changes in container logistics data upload and synchronization within a fixed time period in the future, and the frequency of data upload is dynamically adjusted according to the prediction results, specifically: For medium real-time data, that is, the real-time value of container logistics data upload and synchronization generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time values ​​generated in the future fixed time period 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 data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, further predictions are made on the real-time changes of container logistics data upload and synchronization in the future fixed time period based on the analysis results.

7. The RFID-based container logistics full-process tracking management system according to claim 6 is characterized by: If the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, a third-level warning signal is generated, the upload frequency is reduced, the upload cycle is extended, and batch processing is adopted; If the mean of the real-time values ​​is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, no warning signal will be generated, the upload frequency will be maintained, and monitoring will be strengthened; If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, a first-level warning signal is generated, the upload frequency is increased, the timeliness of data upload is prioritized, and network conditions are optimized; If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, a secondary warning signal is generated to reduce the upload frequency and concentrate resources to optimize the transmission link.

Images