Container tracking management system and method

Abstract

The invention discloses a container tracking management system and method. The method comprises the following steps: S1, carrying out dynamic encryption binding and multi-dimensional data acquisition on an RFID chip; s2, realizing real-time position data acquisition of the container under different environmental conditions through a multi-source signal fusion and error correction algorithm; s3, various sensor modules are installed inside and outside the container, and data processing is carried out through distributed edge nodes; s4, performing on-chain storage on total data generated in the transportation process through a Hash encryption algorithm, and realizing automatic data verification, state tracking and abnormity alarm in combination with an intelligent contract; s5, carrying out real-time dynamic modeling analysis on the transportation path and resource allocation, and dynamically adjusting the transportation plan by using a distributed scheduling strategy; and S6, integrating the real-time state data, the path optimization model and the transportation scheduling decision, and providing a report for a user. The method has the advantages of high positioning precision, high data security, high transportation efficiency and good real-time performance.

Description

Technical Field

[0001] The present invention relates to the technical field of tracking management, and in particular to a container tracking management system and method. Background Art

[0002] With the rapid development of global trade and logistics industries, container transportation has become the main mode of international freight. However, the problems caused by the lack of efficient tracking and management mechanisms during the transportation and storage of containers have become increasingly prominent. For example, container loss, cargo damage, low transportation efficiency and data tampering are frequent, which seriously affect the overall efficiency and security of the logistics supply chain.

[0003] In the existing technology, traditional container tracking management methods mainly rely on a single technology or limited functional modules, such as simple GPS positioning systems and traditional barcode scanning technology. Although these methods meet the basic container tracking needs to a certain extent, they have significant shortcomings when facing the complexity and diversity of modern logistics environments: 1. Insufficient accuracy and coverage: Existing positioning technologies usually rely only on a single GPS or Beidou system, which cannot meet the high-precision and multi-environment adaptability requirements in complex transportation environments. Positioning errors are particularly serious in environments with obstruction or signal interference.

[0004] 2. Weak data security: Traditional container data recording and transmission systems lack a sound security mechanism and are vulnerable to data tampering or leakage, resulting in low data credibility and security during transportation.

[0005] 3. Insufficient monitoring methods: Traditional monitoring systems only support single parameter monitoring and are unable to comprehensively collect and process multiple environmental parameters (such as temperature, humidity, vibration, and tilt angle), which leads to obvious shortcomings in monitoring the quality of cargo transportation.

[0006] 4. Inefficient route and resource scheduling: Existing scheduling systems are mostly static planning, lacking real-time route optimization capabilities and intelligent resource allocation mechanisms, resulting in low transportation efficiency and serious waste of resources.

[0007] 5. Opaque data management: The lack of a multi-technology integrated data management system makes it difficult to achieve real-time sharing, verification and traceability of data, and abnormal events in the transportation process are often difficult to detect and handle in a timely manner.

[0008] Therefore, how to provide a container tracking management system and method is a problem that those skilled in the art need to solve urgently. Summary of the invention

[0009] One purpose of the present invention is to propose a container tracking management system and method. The present invention fully combines multi-band radio frequency identification, dual-mode high-precision positioning, the Internet of Things, blockchain and artificial intelligence optimization algorithm technology, and describes in detail the implementation method of dynamic monitoring, intelligent scheduling and safety management of the entire process of containers. It has the advantages of high positioning accuracy, strong data security, high transportation efficiency and good real-time performance.

[0010] A container tracking management method according to an embodiment of the present invention comprises the following steps: S1. Build a dynamic container identification system based on multi-band radio frequency identification technology. By dynamically encrypting and binding RFID chips and collecting multi-dimensional data, the unique identification information of the container is associated with the transportation network database to form an identity authentication mechanism with real-time update capabilities. S2, adopts a dual-mode high-precision positioning method that integrates the global positioning system and the Beidou navigation system, and realizes real-time location data collection of containers under different environmental conditions through multi-source signal fusion and error correction algorithm; S3. Deploy an intelligent sensor network based on the IoT edge computing architecture, install a variety of sensor modules inside and outside the container, collect temperature and humidity, vibration, tilt angle and environmental parameters, and use distributed edge nodes to filter, analyze and optimize the data before uploading it to the cloud through multi-protocol wireless communication; S4. Build a distributed data storage and verification system based on blockchain technology, store all data generated during the transportation process on the chain through hash encryption algorithm, and combine smart contracts to realize automatic data verification, status tracking and abnormal alarm; S5. Use an artificial intelligence optimization algorithm that integrates deep learning and reinforcement learning models to conduct real-time dynamic modeling and analysis of transportation routes and resource allocation, combine multivariate prediction to generate the optimal transportation route, and use distributed scheduling strategies to dynamically adjust the transportation plan; S6. A visual management platform based on the integration of IoT and blockchain technology, integrating real-time status data, path optimization models and transportation scheduling decisions, providing multiple users with a dynamic monitoring interface, remote control functions and data reports based on full life cycle analysis.

[0011] Optionally, the S1 specifically includes: S11. Adopt multi-band adaptive RFID chip, build a dynamic container identification system based on multi-band RFID technology through multi-frequency signal dynamic allocation algorithm, make the chip adapt to complex electromagnetic environment, and adopt anti-interference circuit design to optimize the stability of data interaction; S12. Encrypt the identity data generated by the RFID chip based on a dynamic hash encryption algorithm to generate dynamic identification information ,in Represents the initial identification, is the time-dependent factor, Encryption for dynamic hashing; S13. Build a two-way authentication mechanism based on the trusted device authentication protocol, using the authentication key generated by the chip Dynamic authentication parameters assigned by the server ,pass Implement two-way authentication, where is the authentication function, To verify the results; S14, using a distributed associated data structure to encrypt and bind the dynamic identification information with the container number, transportation status, and sensor collection data, and record them in a multi-layer encrypted database, where the database index includes time parameters, dynamic identification, and container status associated data; S15, using the real-time dynamic backtracking mechanism to periodically verify the dynamic identification information, by generating a verification value Verify the consistency between the current identifier and the database record, and trigger an abnormal alarm mechanism when the verification fails; ; in, Indicates a dynamic backtracking key, It is the backtracking verification function; S16. Through data aggregation and modeling technology, combined with dynamic identification, real-time status data and historical records, a multi-dimensional encrypted mapping table is generated, which contains a time series-based fast retrieval index, dynamic status mapping relationship and encrypted verification data.

[0012] Optionally, the S2 specifically includes: S21. Build a dual-mode positioning receiving module, receive and decode satellite signals through independent global positioning system signal processing units and Beidou navigation system signal processing units, and generate timestamps and , and the initial positioning coordinates and ,in and Represents independent time references for the two systems; S22, using a multi-source fusion algorithm based on dynamic weight allocation to fuse the decoded initial positioning coordinates to obtain a fused positioning result : ; in, and A weighting factor that is adjusted in real time based on signal quality and geographical environment; S23, combined with multiple environmental parameter correction model to fusion positioning results To perform error correction: ; in, represents the final positioning result after error correction, represents the error estimation function based on environmental variables, For air pressure, For temperature, is the terrain slope; S24, construct a dynamic correction module, input the ground base station auxiliary signal and multi-sensor data into the dynamic correction module, and use the adaptive iterative algorithm to update the error correction parameters , optimize the real-time and accuracy of positioning results in rapidly changing environments; S25, adopt the continuity verification mechanism based on trajectory prediction to correct the final positioning result after error With predicted trajectory Perform difference calculation: ; in, To verify the deviation, if When the preset threshold is exceeded, the relocation process is triggered and a data anomaly alert is issued; S26. Bind and record the final corrected positioning result, timestamp and corresponding container identification information in the distributed database, and upload them to the visualization management platform in real time through the encrypted communication interface.

[0013] Optionally, the S3 specifically includes: S31. Install multiple types of sensor modules inside and outside the container, including high-precision digital temperature sensors for collecting temperature. , Capacitive humidity sensor for monitoring humidity , a three-axis accelerometer for detecting vibrations , Gyroscope sensor for measuring tilt angle , and an absolute pressure sensor for collecting air pressure , real-time generation of raw data matrix through multi-sensor synchronous acquisition technology : ; in, Represents the raw data of the nth sensor at the mth time point; S32, based on the distributed edge computing architecture, using edge nodes to calculate the original data matrix Perform preprocessing, which includes signal noise suppression, outlier correction and data normalization, to generate a preprocessed data matrix : ; in, Represents the data processing function of the edge node; S33, using a multi-edge node collaborative aggregation algorithm based on a dynamic time weighted model, aggregate and analyze the pre-processed data returned by each edge node to generate a dynamic aggregation vector : ; in, It is The edge nodes at time The processed data matrix part, Indicates at time Moment, The weight coefficient of the edge node, Indicates the total number of edge nodes participating in the aggregation; S34, through the wireless communication module supporting multi-protocol switching, the dynamic aggregation vector Real-time transmission to the cloud data center to adapt to data transmission requirements under different network conditions; S35. Construct an analysis module based on big data analysis and time series modeling in the cloud data center to perform trend analysis, anomaly detection and multi-dimensional parameter modeling on the data transmitted to the cloud, generate comprehensive analysis results including historical trend graphs, environmental status predictions and abnormal alarm records, and store them in association with the unique identification information of the container; S36. The analysis results are pushed to the user terminal device in real time through the cloud management platform. The terminal device provides a real-time monitoring interface, data backtracking function and abnormal alarm notification. The monitoring content includes temperature and humidity change curves, vibration intensity distribution, real-time trend of tilt angle, air pressure change records and abnormal status warning information.

[0014] Optionally, the S4 specifically includes: S41. Build a distributed data storage system based on blockchain technology. The block structure includes the block header , data body and node signature , where the block header contains a timestamp , previous block hash , current block hash , Node ID And data summary ; S42. Apply the dynamic hash encryption algorithm to the full amount of data generated during the transportation process to obtain the encryption result : ; in, Represents the original data, is an encryption key dynamically generated based on time. It is a multi-input hash encryption function; S43, encrypted data through blockchain network nodes Packaged with additional metadata and stored in the block data body Additional metadata includes a timestamp , Node ID and data summary , and generate a complete block ; S44. Use the smart contract-based block verification module to verify the generated complete block. The smart contract logic includes verifying the current block hash. Whether the following calculation is satisfied, if the verification is passed, the block is linked to the main chain, if the verification fails, the abnormal status is recorded and broadcasted to other nodes: ; in, is the blockchain verification function, Indicates the hash value of the previous block; S45. Build an on-chain anomaly detection module to monitor the on-chain block generation rate, node data consistency, and latency indicators in real time. ,in, represents the anomaly detection result, represents the anomaly detection function, Indicates the block generation rate, Indicates node data consistency, Indicates the node's latency indicator, determines whether there are potential abnormal nodes and records the results in the chain; S46. Through the data query interface based on smart contracts, users are allowed to access the query results stored in the blockchain, including hash values, through node authority authentication. , Timestamp , Node ID And data summary , and automatically verifies the authenticity and integrity of the returned data through smart contracts.

[0015] Optionally, the S5 specifically includes: S51. Build a transportation path optimization model based on deep learning and reinforcement learning and define the state space , Action Space And the reward function ,in Represents the transportation system at time status, including traffic conditions, weather data and resource utilization, represents possible path selection and resource allocation actions, represents the immediate reward, which is used to evaluate the comprehensive benefits of path selection and resource scheduling; S52. Use deep neural networks to extract features and model historical transportation data to generate a route prediction model ,in represents a set of input variables, including real-time traffic flow, environmental changes, and transportation resource status, and output The predicted probability of optimal path selection; S53, dynamically optimize path decisions through reinforcement learning algorithms, maximize long-term benefits through value iteration-based strategy update modules, and iterative update strategy functions are: : ; in, is the objective function, Represents the value function of the current state and action, It represents the expected operation, which means to seek the expectation for all possible states and actions; S54. Build a multivariate prediction model for future traffic flow , meteorological conditions and transportation resource supply and demand Perform dynamic predictions, and the prediction results are used to update the reward function in real time Parameter distribution of ; S55. Design a distributed resource scheduling module, combine the optimal path decision generated by the reinforcement learning strategy, and calculate the resource allocation plan : ; in, Indicates time The distribution of transportation demand, Indicates time The availability of resources, Allocate functions for distributed resources; S56. Synchronize the path optimization results and resource scheduling plan to the transportation management system, and dynamically update the transportation plan through the real-time monitoring module. The monitoring content includes path status, resource allocation progress and abnormal event feedback, and provides adjustment suggestions for the path and resource plan.

[0016] Optionally, the S6 specifically includes: S61. Adopt a visual management platform based on the integration of IoT and blockchain technology. The platform receives real-time data streams of containers through IoT terminal devices, including real-time status data. , location information , Environmental parameters , and verification information obtained through the blockchain network ; S62. Use the data integration module to integrate real-time status data from different sources , location data and environmental parameters Clean and standardize to generate a unified integrated data set : ; in, Represents multi-source data cleaning and integration functions; S63. Design a dynamic visual monitoring interface and integrate data through real-time rendering algorithms Visualization: the interface displays real-time status, real-time status data, location information, environmental parameters, abnormal alarm status, and estimated arrival time; S64, combined with the blockchain smart contract module, verifies and stores real-time data and scheduling decisions, and generates data hash values and compare it with the timestamp and node identifier The association is stored in the blockchain: ; in, To verify the logic result, It is the blockchain verification function; S65, through the remote control module, allows authorized users to view location data in real time and resource allocation ; S66. Build a data report generation module based on full life cycle analysis, integrate historical data, real-time data and forecast data, and generate reports including status change trends, resource utilization statistics, transportation efficiency evaluation and abnormal event records.

[0017] A container tracking management system, comprising: Radio frequency identification module, which generates unique identification and performs dynamic identity authentication for containers through multi-band radio frequency identification chips; The dual-mode positioning module integrates the global positioning system and the Beidou navigation system to achieve high-precision real-time positioning of containers through multi-source data fusion and error correction algorithm; The sensor network module consists of multiple types of sensors distributed inside and outside the container, including temperature and humidity sensors, acceleration sensors, gyroscope sensors, and air pressure sensors, to collect container environmental parameters and status information; Edge computing nodes are deployed around the sensor network to filter noise, correct anomalies, and preprocess data collected by the sensor, and upload them to the cloud through wireless communication modules; The blockchain storage module includes a distributed blockchain network and smart contract system to perform hash encryption, on-chain storage, and automated data verification on all data generated during the transportation process; The AI ​​optimization module uses an algorithm that integrates deep learning and reinforcement learning models to dynamically optimize transportation routes and resource allocation, and generates transportation plans in combination with multivariate prediction models; Visual management platform, including IoT access module and dynamic monitoring interface, integrating real-time status data, route optimization results and transportation scheduling plan, and providing user-operable monitoring interface and remote control function; The report generation module generates transportation reports based on the full life cycle analysis, including historical data analysis, status trend charts, transportation efficiency evaluation and abnormal event records, and displays the report content in a visual form.

[0018] The beneficial effects of the present invention are: (1) The present invention solves the problems of insufficient positioning accuracy, weak data security and single monitoring means in traditional logistics management by combining multi-band radio frequency identification technology, dual-mode positioning technology integrating the global positioning system and the Beidou navigation system, the edge computing architecture of the Internet of Things and blockchain technology. It realizes dynamic tracking, data security protection and real-time anomaly detection of the entire process of container transportation, and greatly improves the intelligence and safety of logistics management.

[0019] (2) The present invention adopts artificial intelligence optimization algorithms, combines deep learning and reinforcement learning models to perform path optimization and resource scheduling, dynamically adapts to complex logistics network environments, significantly improves transportation efficiency, and reduces operating costs. At the same time, it provides accurate scheduling decisions through multivariate prediction models, solving the problems of resource waste and planning delays in traditional logistics systems.

[0020] (3) The present invention integrates the Internet of Things and blockchain technology to build a highly transparent visual management platform that integrates real-time data monitoring, remote control and full life cycle analysis functions, providing multiple users with a dynamic monitoring interface and data traceability capabilities, effectively solving the problems of information asymmetry and opaque data management in traditional logistics management, and significantly improving the efficiency and accuracy of transportation decision-making.

[0021] (4) The container tracking and management system of the present invention integrates multiple advanced technologies through a modular architecture, achieving full process coverage from identification, positioning to scheduling and data analysis. It not only improves the coordination and scalability of the logistics system, but also promotes the comprehensive transformation of the logistics industry towards digitalization and intelligence, and provides an efficient, safe and intelligent solution for the modern logistics system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is an overall framework diagram of a container tracking management method and system proposed by the present invention. DETAILED DESCRIPTION

[0023] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0024] refer to Figure 1 , a container tracking management method and system, comprising the following steps: S1. Build a dynamic container identification system based on multi-band radio frequency identification technology. By dynamically encrypting and binding RFID chips and collecting multi-dimensional data, the unique identification information of the container is associated with the transportation network database to form an identity authentication mechanism with real-time update capabilities. In this implementation, S1 specifically includes: S11. Adopt multi-band adaptive RFID chip, build a dynamic container identification system based on multi-band RFID technology through multi-frequency signal dynamic allocation algorithm, make the chip adapt to complex electromagnetic environment, and adopt anti-interference circuit design to optimize the stability of data interaction; S12. Encrypt the identity data generated by the RFID chip based on a dynamic hash encryption algorithm to generate dynamic identification information ,in Represents the initial identification, is the time-dependent factor, Encryption for dynamic hashing; S13. Build a two-way authentication mechanism based on the trusted device authentication protocol, using the authentication key generated by the chip Dynamic authentication parameters assigned by the server ,pass Implement two-way authentication, where is the authentication function, To verify the results; S14, using a distributed associated data structure to encrypt and bind the dynamic identification information with the container number, transportation status, and sensor collection data, and record them in a multi-layer encrypted database, where the database index includes time parameters, dynamic identification, and container status associated data; S15, using the real-time dynamic backtracking mechanism to periodically verify the dynamic identification information, by generating a verification value Verify the consistency between the current identifier and the database record, and trigger an abnormal alarm mechanism when the verification fails; ; in, Indicates a dynamic backtracking key, It is the backtracking verification function; S16. Through data aggregation and modeling technology, combined with dynamic identification, real-time status data and historical records, a multi-dimensional encrypted mapping table is generated, which contains a time series-based fast retrieval index, dynamic status mapping relationship and encrypted verification data.

[0025] This implementation method establishes a dynamic identity authentication model by combining a dynamic encryption algorithm with multi-band RFID technology. It not only greatly improves the identification security of containers, but also supports efficient identity retrieval and historical data tracing through multi-dimensional data indexing, solving the risks of data forgery and tampering in traditional identity authentication methods. At the same time, it enhances the scalability and data processing capabilities of the system to meet the needs of various logistics scenarios.

[0026] S2, adopts a dual-mode high-precision positioning method that integrates the global positioning system and the Beidou navigation system, and realizes real-time location data collection of containers under different environmental conditions through multi-source signal fusion and error correction algorithm; In this implementation, S2 specifically includes: S21. Build a dual-mode positioning receiving module, receive and decode satellite signals through independent global positioning system signal processing units and Beidou navigation system signal processing units, and generate timestamps and , and the initial positioning coordinates and ,in and Represents independent time references for the two systems; S22, using a multi-source fusion algorithm based on dynamic weight allocation to fuse the decoded initial positioning coordinates to obtain a fused positioning result : ; in, and A weighting factor that is adjusted in real time based on signal quality and geographical environment; S23, combined with multiple environmental parameter correction model to fusion positioning results To perform error correction: ; in, represents the final positioning result after error correction, represents the error estimation function based on environmental variables, For air pressure, For temperature, is the terrain slope; S24, construct a dynamic correction module, input the ground base station auxiliary signal and multi-sensor data into the dynamic correction module, and use the adaptive iterative algorithm to update the error correction parameters , optimize the real-time and accuracy of positioning results in rapidly changing environments; S25, adopt the continuity verification mechanism based on trajectory prediction to correct the final positioning result after error With predicted trajectory Perform difference calculation: ; in, To verify the deviation, if When the preset threshold is exceeded, the relocation process is triggered and a data anomaly alert is issued; S26. Bind and record the final corrected positioning result, timestamp and corresponding container identification information in the distributed database, and upload them to the visualization management platform in real time through the encrypted communication interface.

[0027] This implementation method achieves high-precision positioning in complex environments through the dual-mode positioning technology of the Global Positioning System and the Beidou Navigation System combined with error correction and multi-source data fusion algorithms. It not only improves the global coverage capability of container transportation, but also enhances the robustness of the system under changing environmental conditions through a real-time dynamic correction mechanism. It solves the problem that traditional positioning technology cannot cope with scenarios such as occlusion and signal interference, and provides technical support for precise logistics.

[0028] S3. Deploy an intelligent sensor network based on the IoT edge computing architecture, install a variety of sensor modules inside and outside the container, collect temperature and humidity, vibration, tilt angle and environmental parameters, and use distributed edge nodes to filter, analyze and optimize the data before uploading it to the cloud through multi-protocol wireless communication; In this implementation, S3 specifically includes: S31. Install multiple types of sensor modules inside and outside the container, including high-precision digital temperature sensors for collecting temperature. , Capacitive humidity sensor for monitoring humidity , a three-axis accelerometer for detecting vibrations , Gyroscope sensor for measuring tilt angle , and an absolute pressure sensor for collecting air pressure , real-time generation of raw data matrix through multi-sensor synchronous acquisition technology : ; in, Represents the raw data of the nth sensor at the mth time point; S32, based on the distributed edge computing architecture, using edge nodes to calculate the original data matrix Perform preprocessing, which includes signal noise suppression, outlier correction and data normalization, to generate a preprocessed data matrix : ; in, Represents the data processing function of the edge node; S33, using a multi-edge node collaborative aggregation algorithm based on a dynamic time weighted model, aggregate and analyze the pre-processed data returned by each edge node to generate a dynamic aggregation vector : ; in, It is The edge nodes at time The processed data matrix part, Indicates at time Moment, The weight coefficient of the edge node, Indicates the total number of edge nodes participating in the aggregation; S34, through the wireless communication module supporting multi-protocol switching, the dynamic aggregation vector Real-time transmission to the cloud data center to adapt to data transmission requirements under different network conditions; S35. Construct an analysis module based on big data analysis and time series modeling in the cloud data center to perform trend analysis, anomaly detection and multi-dimensional parameter modeling on the data transmitted to the cloud, generate comprehensive analysis results including historical trend graphs, environmental status predictions and abnormal alarm records, and store them in association with the unique identification information of the container; S36. The analysis results are pushed to the user terminal device in real time through the cloud management platform. The terminal device provides a real-time monitoring interface, data backtracking function and abnormal alarm notification. The monitoring content includes temperature and humidity change curves, vibration intensity distribution, real-time trend of tilt angle, air pressure change records and abnormal status warning information.

[0029] This implementation method deploys multiple types of sensor networks inside and outside the container, and combines edge computing nodes for data preprocessing and aggregation analysis, thereby achieving efficient collection and processing of environmental parameters such as temperature, humidity, vibration, and tilt angle. It not only improves the real-time and accuracy of monitoring data, but also reduces cloud data processing pressure through a distributed architecture, providing an intelligent means for full-process environmental monitoring and ensuring the quality of cargo transportation.

[0030] S4. Build a distributed data storage and verification system based on blockchain technology, store all data generated during the transportation process on the chain through hash encryption algorithm, and combine smart contracts to realize automatic data verification, status tracking and abnormal alarm; In this implementation, S4 specifically includes: S41. Build a distributed data storage system based on blockchain technology. The block structure includes the block header , data body and node signature , where the block header contains a timestamp , previous block hash , current block hash , Node ID And data summary ; S42. Apply the dynamic hash encryption algorithm to the full amount of data generated during the transportation process to obtain the encryption result : ; in, Represents the original data, is an encryption key dynamically generated based on time. It is a multi-input hash encryption function; S43, encrypted data through blockchain network nodes Packaged with additional metadata and stored in the block data body Additional metadata includes a timestamp , Node ID and data summary , and generate a complete block ; S44. Use the smart contract-based block verification module to verify the generated complete block. The smart contract logic includes verifying the current block hash. Whether the following calculation is satisfied, if the verification is passed, the block is linked to the main chain, if the verification fails, the abnormal status is recorded and broadcasted to other nodes: ; in, is the blockchain verification function, Indicates the hash value of the previous block; S45. Build an on-chain anomaly detection module to monitor the on-chain block generation rate, node data consistency, and latency indicators in real time. ,in, represents the anomaly detection result, represents the anomaly detection function, Indicates the block generation rate, Indicates node data consistency, Indicates the node's latency indicator, determines whether there are potential abnormal nodes and records the results in the chain; S46. Through the data query interface based on smart contracts, users are allowed to access the query results stored in the blockchain, including hash values, through node authority authentication. , Timestamp , Node ID And data summary , and automatically verifies the authenticity and integrity of the returned data through smart contracts.

[0031] This implementation method uses blockchain technology to build a distributed storage and data verification system. Through hash encryption algorithms and smart contracts, it realizes the full-process security management of transportation data from generation to verification, solving the problem of data being easily tampered with in traditional centralized systems. At the same time, it monitors data status in real time through anomaly detection modules, effectively improving data security and transportation transparency, and providing reliable protection for data management in complex logistics networks.

[0032] S5. Use an artificial intelligence optimization algorithm that integrates deep learning and reinforcement learning models to conduct real-time dynamic modeling and analysis of transportation routes and resource allocation, combine multivariate prediction to generate the optimal transportation route, and use distributed scheduling strategies to dynamically adjust the transportation plan; In this implementation, S5 specifically includes: S51. Build a transportation path optimization model based on deep learning and reinforcement learning and define the state space , Action Space And the reward function ,in Represents the transportation system at time status, including traffic conditions, weather data and resource utilization, represents possible path selection and resource allocation actions, represents the immediate reward, which is used to evaluate the comprehensive benefits of path selection and resource scheduling; S52. Use deep neural networks to extract features and model historical transportation data to generate a route prediction model ,in represents a set of input variables, including real-time traffic flow, environmental changes, and transportation resource status, and output The predicted probability of optimal path selection; S53, dynamically optimize path decisions through reinforcement learning algorithms, maximize long-term benefits through value iteration-based strategy update modules, and iterative update strategy functions are: : ; in, is the objective function, Represents the value function of the current state and action, It represents the expected operation, which means to seek the expectation for all possible states and actions; S54. Build a multivariate prediction model for future traffic flow , meteorological conditions and transportation resource supply and demand Perform dynamic predictions, and the prediction results are used to update the reward function in real time Parameter distribution of ; S55. Design a distributed resource scheduling module, combine the optimal path decision generated by the reinforcement learning strategy, and calculate the resource allocation plan : ; in, Indicates time The distribution of transportation demand, Indicates time The availability of resources, Allocate functions for distributed resources; S56. Synchronize the path optimization results and resource scheduling plan to the transportation management system, and dynamically update the transportation plan through the real-time monitoring module. The monitoring content includes path status, resource allocation progress and abnormal event feedback, and provides adjustment suggestions for the path and resource plan.

[0033] This implementation method constructs a dynamically optimized transportation path decision model through the integrated application of deep learning and reinforcement learning algorithms, combines multivariable prediction technology to model and analyze the future transportation environment, and realizes real-time adjustment of paths and resource scheduling. It not only optimizes transportation efficiency and reduces logistics costs, but also improves the comprehensive utilization rate of resources, providing a highly intelligent decision support system for coping with complex transportation environments.

[0034] S6. A visual management platform based on the integration of IoT and blockchain technology, integrating real-time status data, path optimization models and transportation scheduling decisions, providing multiple users with a dynamic monitoring interface, remote control functions and data reports based on full life cycle analysis.

[0035] In this implementation, S6 specifically includes: S61. Adopt a visual management platform based on the integration of IoT and blockchain technology. The platform receives real-time data streams of containers through IoT terminal devices, including real-time status data. , location information , Environmental parameters , and verification information obtained through the blockchain network ; S62. Use the data integration module to integrate real-time status data from different sources , location data and environmental parameters Clean and standardize to generate a unified integrated data set : ; in, Represents multi-source data cleaning and integration functions; S63. Design a dynamic visual monitoring interface and integrate data through real-time rendering algorithms Visualization: the interface displays real-time status, real-time status data, location information, environmental parameters, abnormal alarm status, and estimated arrival time; S64, combined with the blockchain smart contract module, verifies and stores real-time data and scheduling decisions, and generates data hash values and compare it with the timestamp and node identifier The association is stored in the blockchain: ; in, To verify the logic result, It is the blockchain verification function; S65, through the remote control module, allows authorized users to view location data in real time and resource allocation ; S66. Build a data report generation module based on full life cycle analysis, integrate historical data, real-time data and forecast data, and generate reports including status change trends, resource utilization statistics, transportation efficiency evaluation and abnormal event records.

[0036] This implementation method builds a visual management platform through the integration of the Internet of Things and blockchain technology, realizes dynamic monitoring and remote control of the entire process of container transportation, supports intelligent scheduling and abnormal alarms through real-time data integration and analysis, and generates visual reports based on full life cycle analysis, providing users with a full range of information services from status tracking to decision support, greatly improving the transparency and intelligence level of transportation management.

[0037] A container tracking management system, comprising: Radio frequency identification module, which generates unique identification and performs dynamic identity authentication for containers through multi-band radio frequency identification chips; The dual-mode positioning module integrates the global positioning system and the Beidou navigation system to achieve high-precision real-time positioning of containers through multi-source data fusion and error correction algorithm; The sensor network module consists of multiple types of sensors distributed inside and outside the container, including temperature and humidity sensors, acceleration sensors, gyroscope sensors, and air pressure sensors, to collect container environmental parameters and status information; Edge computing nodes are deployed around the sensor network to filter noise, correct anomalies, and preprocess data collected by the sensor, and upload them to the cloud through wireless communication modules; The blockchain storage module includes a distributed blockchain network and smart contract system to perform hash encryption, on-chain storage, and automated data verification on all data generated during the transportation process; The AI ​​optimization module uses an algorithm that integrates deep learning and reinforcement learning models to dynamically optimize transportation routes and resource allocation, and generates transportation plans in combination with multivariate prediction models; Visual management platform, including IoT access module and dynamic monitoring interface, integrating real-time status data, route optimization results and transportation scheduling plan, and providing user-operable monitoring interface and remote control function; The report generation module generates transportation reports based on the full life cycle analysis, including historical data analysis, status trend charts, transportation efficiency evaluation and abnormal event records, and displays the report content in a visual form.

[0038] Embodiment 1: In order to verify the feasibility and practical effect of the present invention, the present invention is applied to the container transportation management of an international logistics company B. As a global logistics company, B manages tens of thousands of containers every day, involving multiple countries and regions. Due to the huge business volume and complex transportation environment, B faces multiple problems such as insufficient positioning accuracy, low transportation efficiency, data tampering and resource waste. In order to solve these problems, the company decided to deploy the container tracking management system of the present invention.

[0039] In the actual application scenario, Company B selected an important logistics node port X and three main transportation routes for testing. In these scenarios, Company B compared the system performance before and after the deployment of the present invention. The deployment content includes a multi-band radio frequency identification module, a fusion dual-mode positioning module, a sensor network module, a blockchain data management module, and an intelligent scheduling optimization platform to form a complete container tracking management system.

[0040] At Port X, the traditional management system mainly relies on single GPS positioning and barcode scanning technology. Tests have found that in the complex environment of the terminal cargo yard, GPS signal interference causes container positioning errors of up to 15 meters. At the same time, due to the uncontrollability of manual data input, the cargo status information recorded by the system is often delayed or even erroneous. By deploying the dual-mode positioning module of the present invention, combined with the error correction algorithm and multi-source data fusion technology, the positioning accuracy is improved to the sub-meter level. In addition, the multi-band radio frequency identification module dynamically authenticates each container, shortening the scanning time from the original 4 seconds to less than 1 second, greatly improving the yard operation efficiency.

[0041] During the transportation process, the sensor network module of the present invention monitors the container environment throughout the entire process. The temperature and humidity sensors in the container record the cargo environment data, and the acceleration sensor and gyroscope sensor capture abnormal changes in the container transportation status in real time. For example, the test results of a certain line showed that when passing through a rugged mountain road, the vibration intensity of the container once exceeded the set threshold. The system immediately corrects the abnormality through the edge computing node, and sends a real-time alarm to the monitoring center through the Internet of Things interface to guide the driver to adjust the driving method and avoid the risk of cargo damage.

[0042] In terms of data management, the present invention realizes the secure storage and verification of data during transportation through the blockchain module. During the test, multiple malicious tampering incidents were simulated. The blockchain system detected data anomalies through smart contracts and automatically locked nodes that may be attacked. At the same time, the data integrity was verified through the hash encryption algorithm to ensure that the transportation records were authentic and reliable.

[0043] In terms of intelligent scheduling, the present invention integrates deep learning and reinforcement learning models, combines historical transportation data and real-time environmental variables, and dynamically optimizes transportation routes and resource allocation plans. For example, during peak hours, the intelligent scheduling system predicts that a certain route may be congested and automatically recommends an alternative route, saving about 2 hours of transportation time and ensuring that the goods are delivered on time. During the three months of testing, the present invention significantly improved the transportation management efficiency of Company B. The specific data is shown in Table 1: Table 1. Data table of container transport management performance improvement of Company B ; As can be seen from Table 1 above, after deploying the system of the present invention, Company B has achieved significant improvements in multiple key performance indicators. In particular, in terms of positioning accuracy, the traditional system has a large error, which makes the accurate positioning of containers in the yard a major problem. By combining dual-mode positioning with an error correction algorithm, the positioning error is reduced to 0.8 meters, greatly improving the manageability and operating efficiency of the container. In addition, the complete elimination of abnormal data integrity events shows that the effectiveness of blockchain technology in data security protection and tampering prevention has been fully verified, providing strong support for the credibility of logistics data.

[0044] The significant reduction in transportation delays reflects the efficiency of the intelligent scheduling module. Through the dynamic optimization of traffic conditions and resource allocation by deep learning and reinforcement learning models, the present invention can adjust the transportation plan in time during peak hours or emergencies. For example, in a transportation route, due to congestion caused by sudden traffic control, the system recommended an alternative route in advance to avoid high delay costs. This type of intelligent processing method ensures the stability of transportation while improving customer satisfaction and the market competitiveness of enterprises.

[0045] The shortened response time reflects the technical advantages of the present invention in many aspects. Traditional systems rely on manual processing of abnormal events, resulting in long response times and prone to omissions. However, through the combination of edge computing nodes and smart contracts, abnormal events can be detected and processed quickly in real time. In a test, when the sensor detected that the tilt angle of the container exceeded the safety threshold, the system completed the entire process of alarm sending, driving adjustment suggestions, and risk recording within 6 minutes, avoiding cargo damage and additional transportation risks.

[0046] The significant reduction in the cargo damage rate demonstrates the comprehensiveness and real-time nature of the environmental monitoring during transportation by the present invention. Through the efficient collaboration of multiple types of sensor networks, environmental data inside and outside the container can be fully collected and monitored. When parameters such as temperature and humidity exceed the safe range, the system can promptly issue an alarm and guide operators to intervene, thereby effectively protecting the integrity of the cargo. Overall, the deployment of the present invention not only improves the overall efficiency of enterprise logistics management, but also demonstrates outstanding advantages in reducing operating costs, improving service quality, and ensuring transportation safety.

[0047] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A container tracking management method, characterized in that: The steps include: S1. Build a dynamic container identification system based on multi-band radio frequency identification technology. By dynamically encrypting and binding RFID chips and collecting multi-dimensional data, the unique identification information of the container is associated with the transportation network database to form an identity authentication mechanism with real-time update capabilities. S2, adopts a dual-mode high-precision positioning method that integrates the global positioning system and the Beidou navigation system, and realizes real-time location data collection of containers under different environmental conditions through multi-source signal fusion and error correction algorithm; S3. Deploy an intelligent sensor network based on the IoT edge computing architecture, install a variety of sensor modules inside and outside the container, collect temperature and humidity, vibration, tilt angle and environmental parameters, and use distributed edge nodes to filter, analyze and optimize the data before uploading it to the cloud through multi-protocol wireless communication; S4. Build a distributed data storage and verification system based on blockchain technology, store all data generated during the transportation process on the chain through hash encryption algorithm, and combine smart contracts to realize automatic data verification, status tracking and abnormal alarm; S5. Use an artificial intelligence optimization algorithm that integrates deep learning and reinforcement learning models to conduct real-time dynamic modeling and analysis of transportation routes and resource allocation, combine multivariate prediction to generate the optimal transportation route, and use distributed scheduling strategies to dynamically adjust the transportation plan; S6. A visual management platform based on the integration of IoT and blockchain technology, integrating real-time status data, path optimization models and transportation scheduling decisions, providing multiple users with a dynamic monitoring interface, remote control functions and data reports based on full life cycle analysis.

2. A container tracking management method according to claim 1, characterized in that: The S1 specifically includes: S11. Adopt multi-band adaptive RFID chip, build a dynamic container identification system based on multi-band RFID technology through multi-frequency signal dynamic allocation algorithm, make the chip adapt to complex electromagnetic environment, and adopt anti-interference circuit design to optimize the stability of data interaction; S12. Encrypt the identity data generated by the RFID chip based on a dynamic hash encryption algorithm to generate dynamic identification information ,in Represents the initial identification, is the time-dependent factor, Encryption for dynamic hashing; S13. Build a two-way authentication mechanism based on the trusted device authentication protocol, using the authentication key generated by the chip Dynamic authentication parameters assigned by the server ,pass Implement two-way authentication, where is the authentication function, To verify the results; S14, using a distributed associated data structure to encrypt and bind the dynamic identification information with the container number, transportation status, and sensor collection data, and record them in a multi-layer encrypted database, where the database index includes time parameters, dynamic identification, and container status associated data; S15, using the real-time dynamic backtracking mechanism to periodically verify the dynamic identification information, by generating a verification value Verify the consistency between the current identifier and the database record, and trigger an abnormal alarm mechanism when the verification fails; ； in, Indicates a dynamic backtracking key, It is the backtracking verification function; S16. Through data aggregation and modeling technology, combined with dynamic identification, real-time status data and historical records, a multi-dimensional encrypted mapping table is generated, which contains a time series-based fast retrieval index, dynamic status mapping relationship and encrypted verification data.

3. A container tracking management method according to claim 1, characterized in that: The S2 specifically includes: S21. Build a dual-mode positioning receiving module, receive and decode satellite signals through independent global positioning system signal processing units and Beidou navigation system signal processing units, and generate timestamps and , and the initial positioning coordinates and ,in and Represents independent time references for the two systems; S22, using a multi-source fusion algorithm based on dynamic weight allocation to fuse the decoded initial positioning coordinates to obtain a fused positioning result : ； in, and A weighting factor that is adjusted in real time based on signal quality and geographical environment; S23, combined with multiple environmental parameter correction model to fusion positioning results To perform error correction: ； in, represents the final positioning result after error correction, represents the error estimation function based on environmental variables, For air pressure, For temperature, is the terrain slope; S24, construct a dynamic correction module, input the ground base station auxiliary signal and multi-sensor data into the dynamic correction module, and use the adaptive iterative algorithm to update the error correction parameters , optimize the real-time and accuracy of positioning results in rapidly changing environments; S25, adopt the continuity verification mechanism based on trajectory prediction to correct the final positioning result after error With predicted trajectory Perform difference calculation: ； in, To verify the deviation, if When the preset threshold is exceeded, the relocation process is triggered and a data anomaly alert is issued; S26. Bind and record the final corrected positioning result, timestamp and corresponding container identification information in the distributed database, and upload them to the visualization management platform in real time through the encrypted communication interface.

4. A container tracking management method according to claim 1, characterized in that: The S3 specifically includes: S31. Install multiple types of sensor modules inside and outside the container, including high-precision digital temperature sensors for collecting temperature. , Capacitive humidity sensor for monitoring humidity , a three-axis accelerometer for detecting vibrations , Gyroscope sensor for measuring tilt angle , and an absolute pressure sensor for collecting air pressure , real-time generation of raw data matrix through multi-sensor synchronous acquisition technology : ； in, Represents the raw data of the nth sensor at the mth time point; S32, based on the distributed edge computing architecture, using edge nodes to calculate the original data matrix Perform preprocessing, which includes signal noise suppression, outlier correction and data normalization, to generate a preprocessed data matrix : ； in, Represents the data processing function of the edge node; S33, using a multi-edge node collaborative aggregation algorithm based on a dynamic time weighted model, aggregate and analyze the pre-processed data returned by each edge node to generate a dynamic aggregation vector : ； in, It is The edge nodes at time The processed data matrix part, Indicates at time Moment, The weight coefficient of the edge node, Indicates the total number of edge nodes participating in the aggregation; S34, through the wireless communication module supporting multi-protocol switching, the dynamic aggregation vector Real-time transmission to the cloud data center to adapt to data transmission requirements under different network conditions; S35. Construct an analysis module based on big data analysis and time series modeling in the cloud data center to perform trend analysis, anomaly detection and multi-dimensional parameter modeling on the data transmitted to the cloud, generate comprehensive analysis results including historical trend graphs, environmental status predictions and abnormal alarm records, and store them in association with the unique identification information of the container; S36. The analysis results are pushed to the user terminal device in real time through the cloud management platform. The terminal device provides a real-time monitoring interface, data backtracking function and abnormal alarm notification. The monitoring content includes temperature and humidity change curves, vibration intensity distribution, real-time trend of tilt angle, air pressure change records and abnormal status warning information.

5. A container tracking management method according to claim 1, characterized in that: The S4 specifically includes: S41. Build a distributed data storage system based on blockchain technology. The block structure includes the block header , data body and node signature , where the block header contains a timestamp , previous block hash , current block hash , Node ID And data summary ; S42. Apply the dynamic hash encryption algorithm to the full amount of data generated during the transportation process to obtain the encryption result : ； in, Represents the original data, is an encryption key dynamically generated based on time. It is a multi-input hash encryption function; S43, encrypted data through blockchain network nodes Packaged with additional metadata and stored in the block data body Additional metadata includes a timestamp , Node ID and data summary , and generate a complete block ; S44. Use the smart contract-based block verification module to verify the generated complete block. The smart contract logic includes verifying the current block hash. Whether the following calculation is satisfied, if the verification is passed, the block is linked to the main chain, if the verification fails, the abnormal status is recorded and broadcasted to other nodes: ； in, is the blockchain verification function, Indicates the hash value of the previous block; S45. Build an on-chain anomaly detection module to monitor the on-chain block generation rate, node data consistency, and latency indicators in real time. ,in, represents the anomaly detection result, represents the anomaly detection function, Indicates the block generation rate, Indicates node data consistency, Indicates the node's latency indicator, determines whether there are potential abnormal nodes and records the results in the chain; S46. Through the data query interface based on smart contracts, users are allowed to access the query results stored in the blockchain, including hash values, through node authority authentication. , Timestamp , Node ID And data summary , and automatically verifies the authenticity and integrity of the returned data through smart contracts.

6. A container tracking management method according to claim 5, characterized in that: The S5 specifically includes: S51. Build a transportation path optimization model based on deep learning and reinforcement learning and define the state space , Action Space And the reward function ,in Represents the transportation system at time status, including traffic conditions, weather data and resource utilization, represents possible path selection and resource allocation actions, represents the immediate reward, which is used to evaluate the comprehensive benefits of path selection and resource scheduling; S52. Use deep neural networks to extract features and model historical transportation data to generate a route prediction model ,in represents a set of input variables, including real-time traffic flow, environmental changes, and transportation resource status, and output The predicted probability of optimal path selection; S53, dynamically optimize path decisions through reinforcement learning algorithms, maximize long-term benefits through value iteration-based strategy update modules, and iterative update strategy functions are: : ； in, is the objective function, Represents the value function of the current state and action, It represents the expected operation, which means to seek the expectation for all possible states and actions; S54. Build a multivariate prediction model for future traffic flow , weather conditions and transportation resource supply and demand Perform dynamic predictions, and the prediction results are used to update the reward function in real time Parameter distribution of ; S55. Design a distributed resource scheduling module, combine the optimal path decision generated by the reinforcement learning strategy, and calculate the resource allocation plan : ； in, Indicates time The distribution of transportation demand, Indicates time The availability of resources, Allocate functions for distributed resources; S56. Synchronize the path optimization results and resource scheduling plan to the transportation management system, and dynamically update the transportation plan through the real-time monitoring module. The monitoring content includes path status, resource allocation progress and abnormal event feedback, and provides adjustment suggestions for the path and resource plan.

7. A container tracking management method according to claim 6, characterized in that: The S6 specifically includes: S61. Adopt a visual management platform based on the integration of IoT and blockchain technology. The platform receives real-time data streams of containers through IoT terminal devices, including real-time status data. , location information , Environmental parameters , and verification information obtained through the blockchain network ; S62. Use the data integration module to integrate real-time status data from different sources , location data and environmental parameters Clean and standardize to generate a unified integrated data set : ； in, Represents multi-source data cleaning and integration functions; S63. Design a dynamic visual monitoring interface and integrate data through real-time rendering algorithms Visualization: the interface displays real-time status, real-time status data, location information, environmental parameters, abnormal alarm status, and estimated arrival time; S64, combined with the blockchain smart contract module, verifies and stores real-time data and scheduling decisions, and generates data hash values and compare it with the timestamp and node identifier The association is stored in the blockchain: ； in, To verify the logic result, It is the blockchain verification function; S65, through the remote control module, allows authorized users to view location data in real time and resource allocation ; S66. Build a data report generation module based on full life cycle analysis, integrate historical data, real-time data and forecast data, and generate reports including status change trends, resource utilization statistics, transportation efficiency evaluation and abnormal event records.

8. A container tracking management system, applied to a container tracking management method according to any one of claims 1 to 7, characterized in that: include: Radio frequency identification module, which generates unique identification and performs dynamic identity authentication for containers through multi-band radio frequency identification chips; The dual-mode positioning module integrates the global positioning system and the Beidou navigation system to achieve high-precision real-time positioning of containers through multi-source data fusion and error correction algorithm; The sensor network module consists of multiple types of sensors distributed inside and outside the container, including temperature and humidity sensors, acceleration sensors, gyroscope sensors, and air pressure sensors, to collect container environmental parameters and status information; Edge computing nodes are deployed around the sensor network to filter noise, correct anomalies, and preprocess data collected by the sensor, and upload them to the cloud through wireless communication modules; The blockchain storage module includes a distributed blockchain network and smart contract system, which performs hash encryption, on-chain storage, and automated data verification on all data generated during the transportation process; The AI ​​optimization module uses an algorithm that integrates deep learning and reinforcement learning models to dynamically optimize transportation routes and resource allocation, and generates transportation plans in combination with multivariate prediction models; Visual management platform, including IoT access module and dynamic monitoring interface, integrating real-time status data, route optimization results and transportation scheduling plan, providing user-operable monitoring interface and remote control function; The report generation module generates transportation reports based on the full life cycle analysis, including historical data analysis, status trend charts, transportation efficiency evaluation and abnormal event records, and displays the report content in a visual form.

Images