Receiving information real-time synchronization and abnormity early warning method and system

Abstract

The invention discloses a receiving information real-time synchronization and abnormity early warning method and system, and relates to the technical field of intelligent logistics information processing and data security, and the method comprises the steps: collecting logistics track data, constructing a space-time diagram model, and carrying out the track feature extraction through a space-time diagram convolution network; performing trajectory time sequence prediction by adopting a Transform model, and judging an abnormal event based on an abnormal detection threshold value; in combination with zero-knowledge proof and a block chain technology, encryption verification and evidence storage are performed on logistics data, and a logistics scheduling optimization and dynamic exception recovery strategy is constructed. According to the method, through space-time diagram modeling, ST-GCN trajectory feature extraction, Transform prediction analysis, block chain evidence storage and reinforcement learning scheduling optimization, a complete logistics information real-time synchronization and abnormity early warning system is constructed; by introducing the block chain and the ZKP technology, the integrity and privacy security of the data are guaranteed, and the risk of logistics fraud and information tampering is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent logistics information processing and data security technology, and specifically to a method and system for real-time synchronization of received information and abnormal warning. Background Art

[0002] With the rapid development of e-commerce and intelligent logistics, real-time synchronization of logistics information and abnormal warning have become one of the key technologies to improve logistics efficiency and user experience. At present, the logistics industry widely uses GPS positioning, RFID identification, wireless sensor networks (WSN), big data analysis and other technologies to monitor the transportation trajectory of express parcels, and uses machine learning or rule-based algorithms for anomaly detection. In recent years, the application of deep learning in the field of logistics has gradually increased. For example, anomaly detection methods based on long short-term memory networks (LSTM) and recurrent neural networks (RNN) can model the time series of logistics trajectories and provide certain prediction capabilities. In addition, blockchain technology has also been used in logistics tracking to improve the transparency and security of logistics information. However, although these technologies have improved the intelligence level of logistics trajectory monitoring to a certain extent, there are still problems such as data synchronization delays, insufficient anomaly detection accuracy, and lack of data security, which restrict the further development of intelligent logistics systems.

[0003] Existing logistics information synchronization and anomaly detection methods mainly rely on traditional time series modeling methods and rule-based anomaly detection, but there are many limitations in practical applications; time series prediction models based on RNN and LSTM are difficult to handle long time series dependencies, especially in logistics trajectory data. Due to the large transportation time span of packages, existing methods are difficult to accurately capture cross-regional and cross-time period anomaly patterns, resulting in a low anomaly recognition rate; the existing trajectory data processing method is relatively simple, lacking spatial relationship modeling of logistics paths, and most systems only rely on trajectory changes of GPS data, while ignoring the topological relationship between logistics nodes, resulting in low accuracy of path anomaly detection; data security issues are prominent, and traditional logistics data Data storage methods rely on centralized servers, which are prone to data tampering and forgery. In addition, most current blockchain evidence storage solutions can only provide static data traceability and cannot effectively combine privacy computing technology for security verification. For abnormal warnings, existing systems usually use fixed thresholds or statistical feature-based detection methods, which fail to achieve dynamic and adaptive abnormal warning strategies and cannot provide accurate scheduling optimization under the complex changes in the logistics environment. Based on the above problems, traditional methods are difficult to meet the needs of efficient, accurate and traceable logistics information synchronization and anomaly detection. An innovative solution that combines spatiotemporal modeling, deep learning and blockchain security evidence is urgently needed to solve the limitations of existing technologies and improve the intelligence level of logistics systems. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the logistics trajectory data modeling method lacks the ability of deep learning of spatiotemporal characteristics, has low anomaly detection accuracy, lacks the ability to predict long time series trajectories, insufficient logistics data security, and cannot prevent data tampering; and how to achieve accurate anomaly detection based on spatiotemporal graph neural networks and Transformer, and combine zero-knowledge proof and blockchain technology to ensure the security and traceability of logistics data.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for real-time synchronization and abnormal warning of receiving information, comprising collecting logistics trajectory data and constructing a spatiotemporal graph model, and extracting trajectory features through a spatiotemporal graph convolutional network; using a Transformer model to predict trajectory time series, and judging abnormal events based on anomaly detection thresholds; combining zero-knowledge proof and blockchain technology to encrypt, verify and store logistics data, and build logistics scheduling optimization and dynamic anomaly recovery strategies; trajectory feature extraction includes using a three-layer spatiotemporal graph convolutional network, the first layer performs local spatiotemporal feature extraction and processes short-term logistics path information; the second layer performs global information aggregation and learns long-term cross-regional logistics characteristics; the third layer performs abnormal pattern recognition, detects abnormal trajectories and provides explainable anomaly scores.

[0007] As a preferred solution of the method for real-time synchronization of receipt information and abnormal warning described in the present invention, the construction of the spatiotemporal graph model includes using a graph data structure to construct an express transportation network, the nodes represent the logistics locations, the edges represent the transportation paths of the packages, and the edge weights are dynamically updated according to the transportation time and the package status.

[0008] As a preferred solution of the method for real-time synchronization of receiving information and abnormal warning of the present invention, wherein: the trajectory feature extraction includes extracting the temporal transportation mode and spatial path information of the package; Set the historical trajectory window, embed the time series information into the graph structure, and capture the abnormal patterns of different express routes.

[0009] As a preferred solution of the method for real-time synchronization of receiving information and abnormal warning described in the present invention, the trajectory time series prediction includes inputting the logistics trajectory features extracted by the spatiotemporal graph convolutional network into the Transformer model, and using the multi-head self-attention mechanism to analyze the historical trajectory pattern of the package; through the time series prediction capability of the Transformer, the normal trajectory distribution of the express package at the future time point is calculated.

[0010] As a preferred solution of the method for real-time synchronization of receipt information and abnormal warning described in the present invention, the method comprises: determining abnormal events including setting an abnormal detection threshold, and using a calculation method based on Euclidean distance or Mahalanobis distance to measure the deviation between the actual trajectory and the predicted trajectory; when it is detected that the trajectory deviation exceeds the set abnormal detection threshold, an abnormal event is triggered and an early warning signal is sent; when an abnormality occurs, an early warning message is sent to the delivery personnel and the management platform; different response strategies are triggered according to the type of abnormality; and a secondary inspection is performed on the express parcels marked as abnormal to confirm the authenticity of the abnormality.

[0011] As a preferred solution of the method for real-time synchronization of receiving information and abnormal warning described in the present invention, the encryption verification and storage of logistics data include using zk-SNARKs to encrypt and prove key logistics data; before the logistics data is stored, a zero-knowledge proof is generated, and the authenticity of the data does not need to be accessed when verifying the authenticity of the original logistics information; blockchain storage technology is used to store the hash value of the logistics event in a distributed ledger; the logistics data is organized using a Merkle tree structure, and the authenticity of the record is verified by the root hash; when an abnormal logistics event is detected, the abnormal trajectory is traced back based on the historical data stored in the blockchain, and it is verified whether the data has been tampered with during the storage process; the abnormal backtracking logic is automatically executed using smart contracts, and when data inconsistencies are found, warnings are sent to the relevant responsible parties and violations are recorded.

[0012] As a preferred solution of the method for real-time synchronization of receipt information and abnormal warning described in the present invention, the construction of logistics scheduling optimization and dynamic abnormal recovery strategy includes using reinforcement learning to optimize the redistribution path of abnormal packages to minimize delays when couriers re-plan routes; training RL models in combination with historical abnormal data to enable the platform to autonomously learn the optimal scheduling strategy; building a verifiable abnormal recovery process based on blockchain evidence storage, and performing abnormal processing based on logistics specifications.

[0013] Another object of the present invention is to provide a real-time synchronization and abnormal warning system for receiving information, which can perform trajectory time series prediction by adopting the Transformer model and judge abnormal events based on the abnormal detection threshold, thereby solving the problem that the current logistics trajectory data modeling technology lacks the ability to predict long time series trajectories.

[0014] As a preferred solution of the real-time synchronization and abnormal warning system of received information described in the present invention, it includes: a data processing module, an abnormal warning module, and an optimization and recovery module; the data processing module is used to collect logistics trajectory data and construct a spatiotemporal graph model, and extract trajectory features through a spatiotemporal graph convolutional network; the abnormal warning module is used to use a Transformer model to predict trajectory time series, and judge abnormal events based on anomaly detection thresholds; the optimization and recovery module is used to combine zero-knowledge proof and blockchain technology to encrypt, verify and store logistics data, and build logistics scheduling optimization and dynamic abnormal recovery strategies.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for real-time synchronization of received information and abnormal warning.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for real-time synchronization of received information and abnormal warning.

[0017] Beneficial effects of the present invention: The real-time synchronization and abnormal warning method of receipt information provided by the present invention constructs a complete real-time synchronization and abnormal warning system for logistics information through spatiotemporal graph modeling, ST-GCN trajectory feature extraction, Transformer prediction analysis, blockchain evidence storage and reinforcement learning scheduling optimization; compared with traditional logistics information processing methods, the present invention not only improves the accuracy of trajectory data and enhances the anomaly detection capability, but also optimizes logistics scheduling and improves the response speed of the system; by introducing blockchain and ZKP technology, the integrity and privacy security of the data are guaranteed, and the risk of logistics fraud and information tampering is reduced. The present invention achieves better results in terms of efficiency, reliability and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 This is an overall flow chart of a method for real-time synchronization of received information and abnormal warning provided in Example 1 of the present invention.

[0020] Figure 2 This is an overall flow chart of a system for real-time synchronization of received information and abnormal warning provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0022] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a method for real-time synchronization of received information and abnormal warning, comprising: S1: Collect logistics trajectory data and build a spatiotemporal graph model, and extract trajectory features through the spatiotemporal graph convolutional network.

[0023] Furthermore, constructing a spatiotemporal graph model includes constructing an express delivery network using a graph data structure, where nodes represent logistics locations, edges represent the delivery routes of packages, and edge weights are dynamically updated based on the delivery time and package status.

[0024] It should be noted that trajectory feature extraction includes extracting the temporal transportation mode and spatial path information of the package; setting the historical trajectory window, embedding the time series information into the graph structure, and capturing abnormal patterns of different express delivery paths.

[0025] It should also be noted that a preferred solution for constructing a spatiotemporal graph model specifically includes extracting GPS coordinates, timestamps, package status, distribution station numbers and other information from the express delivery system; filtering missing data. If the GPS coordinates at a certain moment are missing, linear interpolation of the previous and next data is used to supplement them; defining logistics nodes: each warehouse, distribution station, and recipient address is regarded as a node; calculating the two logistics nodes and The straight-line distance between , in meters; the exponential decay method is used to calculate the spatial proximity weight: if If the distance is less than 500 meters, a higher weight (close to 1) is set; if If the distance is greater than 5000 meters, a lower weight (close to 0) is set; between 500 meters and 5000 meters, the weight value is gradually reduced in an exponential manner; the time relationship weight is calculated to extract the time interval between adjacent nodes If the logistics flow time between two nodes is lower than the historical average, a higher time weight is assigned; if the time interval is more than twice the historical average, a lower time weight is assigned; construct a space-time graph using an adjacency matrix with time weights , where each element It is calculated by weighting the spatial relationship weight and the temporal relationship weight. =0.7×spatial weight+0.3×time weight; set a dynamic update mechanism to recalculate the adjacency matrix based on new express data every 10 minutes to adapt to the latest changes in logistics routes.

[0026] It should also be noted that a preferred solution for trajectory feature extraction through a spatiotemporal graph convolutional network specifically includes the number of layers and optimization parameter settings of the spatiotemporal graph convolutional network (ST-GCN), and the input data includes logistics nodes, each of which has the following characteristics: location coordinates (latitude and longitude); package status (in transit, has arrived at the distribution station, has been signed for); transportation time information (historical average, current transportation time) data dimensions such as (batch size, time step, number of nodes, feature dimension). The number of layers and functions of ST-GCN: The first layer (local trajectory feature extraction layer): calculates the path changes of the current express within 5 minutes; identifies the short-distance delivery mode within the same city, and extracts the trajectory features from the warehouse to the terminal delivery station; the second layer (global trajectory pattern learning layer): calculates the express flow within 24 hours; handles cross-regional delivery, extracts cross-provincial / cross-city transportation modes, and calculates the typical pattern of goods flow based on historical data; the third layer (anomaly detection layer): compares the deviation between the actual trajectory and the ST-GCN predicted trajectory; if the package path deviation exceeds 2 times the standard deviation, the trajectory is marked as abnormal; the optimization parameter setting includes adopting a three-layer GCN structure and normalizing the input data to improve the calculation stability; the Adam optimizer is used during training, the initial learning rate is set to 0.001, and it decays by 10% every 10 rounds; during the training process, L2 regularization is used to avoid overfitting, so that the model can better generalize to different express path modes.

[0027] It should also be noted that by constructing a spatiotemporal graph model, the dynamic characteristics of logistics trajectories can be accurately described; the dynamic adjacency matrix is ​​used to update the spatial and temporal weights between logistics nodes in real time, so that the model can adapt to changes in the logistics network; compared with the traditional method that only relies on GPS trajectory points, the present invention can more comprehensively capture the actual situation of the express delivery process, thereby effectively reducing the false alarm rate caused by factors such as path changes and courier detours, improving the credibility of trajectory data, and providing a more accurate data basis for subsequent anomaly detection. The present invention extracts trajectory features at three levels of short time, long time and global mode through a three-layer ST-GCN structure, and can identify abnormal patterns of different time scales; compared with traditional statistical analysis or rule-based methods, ST-GCN can effectively model the temporal and spatial relationship of logistics trajectories and improve the robustness of anomaly detection; for example, it can accurately identify problems such as courier detours, detentions, and abnormal deviations from expected trajectories, and reduce false alarms due to high path similarity but actual anomalies, thereby improving anomaly detection capabilities.

[0028] S2: Use the Transformer model to predict trajectory time series and judge abnormal events based on the anomaly detection threshold.

[0029] Furthermore, trajectory time series prediction includes inputting the logistics trajectory features extracted by the spatiotemporal graph convolutional network into the Transformer model, and using the multi-head self-attention mechanism to analyze the historical trajectory pattern of the package; through the Transformer's time series prediction capability, the normal trajectory distribution of the express package at future time points is calculated.

[0030] It should be noted that judging abnormal events includes setting an abnormal detection threshold and using a calculation method based on Euclidean distance or Mahalanobis distance to measure the deviation between the actual trajectory and the predicted trajectory; when it is detected that the trajectory deviation exceeds the set abnormal detection threshold, an abnormal event is triggered and an early warning signal is sent to the logistics management system; when an abnormality occurs, an early warning message is sent to the delivery personnel and the management platform; different response strategies are triggered according to the type of abnormality; and a secondary inspection is performed on the express parcels that have been marked as abnormal to confirm the authenticity of the abnormality.

[0031] It should also be noted that the express trajectory data processed by ST-GCN contains the trajectory feature vector for each time step. Since Transformer requires sequence input, the ST-GCN output data is formatted to ensure that the data is in the form of (batch size, number of time steps, trajectory feature dimension). Since Transformer itself does not have time information, a timestamp code is added to each express trajectory data point. The positional encoding method is used to convert the timestamp into a set of time features, so that Transformer can distinguish trajectory data at different time points. The trajectory pattern is calculated using the Transformer's multi-head self-attention mechanism: the importance weight of each time step in the historical trajectory is calculated, focusing on those historical trajectory points that cause abnormal situations. The similarity between the current express trajectory and the historical trajectory is calculated, and the trajectory deviation is scored. ST-GCN calculates the express trajectory features, and Transformer calculates the time pattern analysis results. The results of the two are weighted fused: if both believe that a certain trajectory deviates from the normal path, the anomaly score is increased. If only ST-GCN finds an anomaly, and Transformer believes that the trajectory pattern is normal, the anomaly score is reduced. Once the comprehensive score exceeds the preset anomaly detection threshold, the system sends an abnormal alert to the logistics management platform: an abnormal trajectory report is generated, marking possible abnormal causes (such as courier detours, delays). An early warning message is triggered to notify the delivery personnel to check the current delivery status. If the abnormal situation persists, a new courier is automatically assigned to remedy the situation.

[0032] It should also be noted that the use of the Transformer model for trajectory time series prediction can effectively solve the shortcomings of traditional LSTM in dealing with long-term dependencies; the Transformer's multi-head self-attention mechanism can identify key points in the historical logistics trajectory and predict future trajectory deviations, so that intervention can be made before the abnormality occurs; for example, when the courier does not arrive at a distribution node as expected, it can issue an early warning and adjust the delivery plan, rather than waiting for the abnormality to occur before passively handling it; this mechanism helps to reduce logistics delivery delays and improve logistics timeliness and operational efficiency.

[0033] S3: Combine zero-knowledge proof and blockchain technology to encrypt, verify and store logistics data, and build logistics scheduling optimization and dynamic abnormality recovery strategies.

[0034] Furthermore, the encryption verification and storage of logistics data include the use of zk-SNARKs to encrypt and prove key logistics data; before the logistics data is stored, a zero-knowledge proof is generated to verify the authenticity of the data without accessing the original logistics information; the blockchain storage technology is used to store the hash value of the logistics event in a distributed ledger; the Merkle tree structure is used to organize the logistics data, and the authenticity of the record is verified by the root hash; when an abnormal logistics event is detected, the abnormal trajectory is traced back based on the historical data stored in the blockchain, and it is verified whether the data has been tampered with during the storage process; the smart contract is used to automatically execute the abnormal backtracking logic, and when the data is found to be inconsistent, a warning is sent to the relevant responsible party and the violation is recorded.

[0035] It should also be noted that a preferred implementation scheme of zero-knowledge proof (ZKP) includes: using zk-SNARKs (Zero-Knowledge Succinct Non-Interactive Argument of Knowledge) to generate proofs for key logistics data, the generator (logistics company) performs hash operations on the timestamp, transportation path, and status information of the express, and converts them into mathematical proofs; the verifier (regulatory system) can verify whether the proof is correct without accessing the original data to ensure that the data has not been tampered with. The Groth16 proof system is used to calculate proofs off-chain to reduce the computational burden on the chain. The specific steps include: parameter setting: in the initial stage, a set of security parameters is generated by a trusted third party and stored in the database of the logistics system; proof generation: when a logistics event occurs (such as the express arrives at the distribution station), the hash value of the event is input into the zk-SNARKs proof circuit to calculate a verifiable proof; proof verification: the regulator or third party can use the pre-set verification key to quickly verify the generated proof without accessing the original information of the express; storage and update: the results of the zero-knowledge proof are uploaded to the blockchain and compared with historical records to ensure the integrity of the data chain. The computational complexity optimization scheme of zero-knowledge proof (ZKP) includes: using a layered proof structure to reduce the computational burden: the first layer performs local pre-calculation, and the courier's device calculates part of the proof in advance when signing or scanning the package to reduce the computing pressure on the server; the second layer performs batch proof calculation, and the logistics server batch calculates the ZKP proofs of multiple couriers every 5 minutes, rather than calculating the proof of each courier individually, to reduce the computing time; the third layer performs fast verification, and the verifier can compare multiple proofs through the Merkle tree root hash to verify multiple logistics records at one time. Optimization measures to reduce proof generation time: adopt an optimized version of the Groth16 proof system, use the curve 25519 elliptic curve to accelerate calculations and reduce multiplication overhead; adopt parallel computing, use multi-threaded parallel proof generation, split the calculation into multiple independent tasks, and improve ZKP computing efficiency; adopt offline computing mode, perform partial proof calculations on logistics events in advance, and directly call them when data verification requests occur to avoid server overload during peak hours; it should also be noted that zk-SNARKs is the abbreviation of "Zero-Knowledge Succinct Non-Interactive Argument of Knowledge", which can be translated into Chinese as "zero-knowledge succinct non-interactive knowledge proof". It is a cryptographic technology that allows one party (prover) to prove to another party (verifier) ​​that a statement is true without revealing any other information.

[0036] It should also be noted that the Merkle tree-based evidence structure, in which the hash value of each express data is used as a leaf node to construct a Merkle tree; the hash value of each layer is calculated and stored on the blockchain, so that the verifier only needs to store the root hash to verify the data integrity; if the express data is tampered with, its hash value changes, resulting in a mismatch in the Merkle tree root hash, thereby detecting anomalies. Smart contracts are used for data evidence and verification, in which the smart contract defines the express status storage rules. Whenever the logistics status is updated, the system automatically generates transactions and records them on the blockchain; the smart contract contains a data consistency check mechanism. When new express information is detected, it is compared with the historical evidence data. If the data is inconsistent, an alarm is triggered; the logistics company can call the verification interface of the smart contract to query the historical record of a specific express and verify whether it is consistent with the data on the blockchain. Distributed storage is used, and the blockchain only stores the hash value of the logistics data, while the actual express information is stored in a distributed storage system (such as IPFS) to ensure data integrity and privacy.

[0037] It should be noted that building logistics scheduling optimization and dynamic exception recovery strategies includes using reinforcement learning to optimize the redistribution path of abnormal packages to minimize delays when couriers re-plan routes; training RL models with historical exception data to enable the platform to autonomously learn the optimal scheduling strategy; and building a verifiable exception recovery process based on blockchain evidence storage to handle exceptions based on logistics specifications.

[0038] It should also be noted that the authenticity and immutability of logistics data are ensured by combining zero-knowledge proof (ZKP) and blockchain evidence storage; zk-SNARKs are used for data verification, so that third parties can verify the authenticity of logistics status without accessing the original data, thereby protecting privacy while ensuring data credibility; in addition, the Merkle tree evidence storage structure based on blockchain provides an efficient data integrity verification method to ensure that logistics companies, users and regulatory agencies can safely interact with data in an untrusted environment, fundamentally preventing data fraud or malicious tampering; the present invention uses reinforcement learning (RL) to optimize express scheduling and combines blockchain evidence storage to improve the transparency of exception handling; after an exception occurs, the express distribution plan can be automatically adjusted based on historical exception data to achieve intelligent and dynamic scheduling strategies and avoid reliance on human intervention; blockchain evidence storage ensures the traceability of the exception handling process, prevents human tampering with exception recovery records, and improves the fairness of express exception handling; by automatically optimizing the delivery route and dynamically adjusting the courier task allocation, our invention improves the efficiency of exception handling, reduces customer complaints caused by delivery exceptions, and enhances user experience.

[0039] Example 2 is an embodiment of the present invention, which provides a method for real-time synchronization of received information and abnormal warning. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0040] First, the experiment selected the express delivery data of a courier company in the past 30 days, covering delivery outlets in multiple cities. The experimental data included GPS trajectory, express status, logistics timestamp, express delivery time, anomaly detection results and other information; the data source included 10,000 actual delivery data, of which 8,000 were normal data and 2,000 were abnormal data, including path deviation, delay, package detention and other situations, and the integrity of the test data was ensured by simulating courier detours, express loss, system data tampering and other methods; the experiment used two schemes for comparison. Scheme 1 adopted the anomaly detection and evidence storage scheme of ST-GCN+Transformer+ZKP+blockchain, and Scheme 2 adopted the traditional scheme based on rule threshold and LSTM trajectory prediction, and stored logistics data in a centralized database; The experiment first analyzes the GPS trajectory data and constructs a dynamic adjacency matrix to adapt to the changes in the express network. Then, the logistics trajectory features are extracted through ST-GCN, and the historical trajectory window is set to capture short-term and long-term trajectory patterns. In the anomaly detection stage, Transformer is used to predict time series, calculate future trajectories and compare them with the current express trajectory deviation. If the anomaly score exceeds 0.75, it is judged as an anomaly. In the data storage stage, zk-SNARKs is used to calculate the zero-knowledge proof of logistics data, and the blockchain is used to record the hash value to ensure the authenticity of the data. Referring to Table 1, the experiment compares the anomaly detection accuracy, false alarm rate, logistics data tampering detection capability, computing overhead, storage consumption and warning response time of the two schemes, so as to evaluate the advantages of the present invention in logistics management.

[0041] Table 1 Logistics experiment results

[0042] Comparison of experimental data shows that the logistics anomaly detection and data storage method of the present invention is significantly superior to traditional solutions in multiple key performance indicators; the anomaly detection accuracy of the present invention reaches 96.8%, which is 14.3% higher than the 82.5% of the traditional method, mainly because ST-GCN combined with Transformer can accurately identify various anomaly types such as path detours and delivery anomalies, while the traditional rule-threshold-based method is limited by the set fixed mode and is difficult to adapt to complex logistics environments; in addition, the false alarm rate of the present invention is only 2.3%, which is much lower than the 12.5% ​​of the traditional solution. This is due to the Transformer's ability to predict trajectory patterns, which can effectively reduce false alarms caused by path changes and traffic fluctuations; in terms of data security, the present invention combines ZKP with blockchain storage to achieve a 100% logistics data tampering detection rate, while traditional centralized storage solutions cannot detect data tampering and have data security risks; in terms of computing performance, the computing overhead of the present invention is 68ms / time, which is 23.6% lower than the traditional method's 89ms / time, due to The detection efficiency is greatly improved by adopting ST-GCN trajectory feature extraction and Transformer parallel calculation; in addition, the storage consumption of the present invention is 0.12MB / time, which is 62.5% lower than the traditional method of 0.32MB / time, mainly due to the Merkle tree structure adopted in blockchain evidence storage, which only needs to store hash values ​​instead of complete logistics data; finally, in terms of warning response speed, the warning response time of the present invention is 1.2 seconds, while the traditional solution is 5.6 seconds, which is improved by 366%. Since Transformer has time series modeling and pattern recognition capabilities, the system can analyze possible abnormal patterns based on historical trajectory data, improve the accuracy of abnormal detection, and provide early warning before abnormal trends are formed; overall, the present invention is superior to the existing technology in terms of detection accuracy, false alarm rate, data security, computing overhead, storage optimization, etc., especially in terms of data security, computing efficiency and abnormal detection accuracy, providing a modern logistics system with an efficient, accurate and verifiable logistics information management solution.

[0043] Example 3, reference Figure 2 , which is an embodiment of the present invention, provides a system for real-time synchronization and abnormal warning of received information, including a data processing module, an abnormal warning module, and an optimization and recovery module.

[0044] The data processing module is used to collect logistics trajectory data and build a spatiotemporal graph model, and extract trajectory features through the spatiotemporal graph convolutional network; the anomaly warning module is used to use the Transformer model to predict trajectory time series and judge abnormal events based on the anomaly detection threshold; the optimization and recovery module is used to combine zero-knowledge proof and blockchain technology to encrypt, verify and store logistics data, and build logistics scheduling optimization and dynamic anomaly recovery strategies.

[0045] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0046] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0047] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0048] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logical function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0049] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for real-time synchronization of received information and abnormal warning, characterized in that: include: Collect logistics trajectory data and build a spatiotemporal graph model, and extract trajectory features through the spatiotemporal graph convolutional network; The Transformer model is used to predict trajectory time series and abnormal events are judged based on the anomaly detection threshold; Combining zero-knowledge proof and blockchain technology, the logistics data is encrypted, verified and stored, and logistics scheduling optimization and dynamic abnormal recovery strategies are built; Trajectory feature extraction includes the use of a three-layer spatiotemporal graph convolutional network. The first layer extracts local spatiotemporal features and processes short-term logistics path information; The second layer aggregates global information and learns long-term cross-regional logistics characteristics; The third layer performs abnormal pattern recognition, detects abnormal trajectories and provides interpretable anomaly scores.

2. The method for real-time synchronization of received information and abnormal warning according to claim 1, characterized in that: The construction of the spatiotemporal graph model includes constructing an express transportation network using a graph data structure, where nodes represent logistics locations, edges represent transportation paths of packages, and edge weights are dynamically updated according to transportation time and package status.

3. The method for real-time synchronization of received information and abnormal warning according to claim 2, characterized in that: The trajectory feature extraction includes extracting the temporal transportation mode and spatial path information of the package; Set the historical trajectory window, embed the time series information into the graph structure, and capture the abnormal patterns of different express routes.

4. The method for real-time synchronization of received information and abnormal warning according to claim 3, characterized in that: The trajectory time series prediction includes inputting the logistics trajectory features extracted by the spatiotemporal graph convolutional network into the Transformer model, and using the multi-head self-attention mechanism to analyze the historical trajectory pattern of the package; Through the time series prediction capability of Transformer, the normal trajectory distribution of express packages at future time points is calculated.

5. The method for real-time synchronization of received information and abnormal warning according to claim 4, characterized in that: The determining of abnormal events includes setting an abnormality detection threshold and using a calculation method based on Euclidean distance or Mahalanobis distance to measure the deviation between the actual trajectory and the predicted trajectory; When the detected trajectory deviation exceeds the set abnormal detection threshold, an abnormal event is triggered and an early warning signal is sent; Send early warning information to delivery personnel and management platform when an abnormality occurs; Trigger different response strategies based on the type of exception; Carry out secondary inspection on express parcels that have been marked as abnormal to confirm the authenticity of the abnormality.

6. The method for real-time synchronization of received information and abnormal warning according to claim 5, characterized in that: The encryption verification and storage of logistics data includes using zk-SNARKs to encrypt and prove key logistics data; Before the logistics data is stored, a zero-knowledge proof is generated to verify the authenticity of the data without accessing the original logistics information; Using blockchain evidence storage technology, the hash value of logistics events is stored in a distributed ledger; The Merkle tree structure is used to organize logistics data, and the authenticity of the records is verified through the root hash; When an abnormal logistics event is detected, the abnormal track is traced back based on the historical data stored in the blockchain, and it is verified whether the data has been tampered with during the storage process; Smart contracts are used to automatically execute abnormal backtracking logic. When data inconsistencies are found, warnings are sent to the relevant responsible parties and violations are recorded.

7. The method for real-time synchronization of received information and abnormal warning according to claim 6, characterized in that: The said construction of logistics scheduling optimization and dynamic abnormal recovery strategy includes using reinforcement learning to optimize the redistribution path of abnormal packages and minimize delays when couriers re-plan routes; Combine historical abnormal data to train the RL model, so that the platform can autonomously learn the optimal scheduling strategy; Based on blockchain evidence storage, a verifiable exception recovery process is constructed to handle exceptions based on logistics specifications.

8. A system using the method for real-time synchronization of received information and abnormal warning as claimed in any one of claims 1 to 7, characterized in that: Including data processing module, abnormal warning module, optimization and recovery module; The data processing module is used to collect logistics trajectory data and construct a spatiotemporal graph model, and extract trajectory features through a spatiotemporal graph convolutional network; The abnormal warning module is used to use the Transformer model to predict trajectory time series and judge abnormal events based on the abnormal detection threshold; The optimization and recovery module is used to combine zero-knowledge proof and blockchain technology to encrypt, verify and store logistics data, and build logistics scheduling optimization and dynamic abnormality recovery strategies.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for real-time synchronization of received information and abnormal warning according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for real-time synchronization of received information and abnormal warning according to any one of claims 1 to 7 are implemented.

Images