CN-122022651-A - E-commerce logistics tracking system based on block chain

CN122022651ACN 122022651 ACN122022651 ACN 122022651ACN-122022651-A

Abstract

The invention relates to the technical field of E-commerce logistics management and discloses an E-commerce logistics tracking system based on a block chain. The system obtains the order identification through the distributed query module, retrieves the logistics records in the blockchain historical database and assembles a historical logistics record set. The event distinguishing module is used for carrying out event type distinguishing processing on the record set to generate a heterogeneous logistics event set. The feature extraction module performs feature extraction on each event set to obtain a logistic feature core value set and an associated time window set. The multi-scale analysis module uses the associated time window set as an analysis reference, and performs multi-level analysis on the logistics data sequence through the blockchain intelligent contract to produce a plurality of logistics feature groups. And the feature fusion module carries out inter-scale fusion processing on the feature set and outputs a final fusion logistics feature set as a logistics tracking result. The system improves transparency and credibility of the e-commerce logistics tracking, and achieves multi-dimensional and multi-scale analysis of the whole logistics process.

Inventors

FENG LIN
DiWu Weiqiang
HE CONGCONG
XIAO KUN

Assignees

陕西科技大学镐京学院

Dates

Publication Date: 20260512
Application Date: 20260127

Claims (10)

1. The block chain-based E-commerce logistics tracking system is characterized by comprising a distributed query module, an event distinguishing module, a feature extraction module, a multi-scale analysis module and a feature fusion module, wherein, The distributed query module is used for acquiring an order identifier of a target electronic commerce order, and executing distributed query operation in the blockchain historical database based on the order identifier to retrieve a historical logistics record so as to assemble a historical logistics record set; The event distinguishing module is used for distinguishing event types of the historical logistics record sets and generating a plurality of heterogeneous logistics event sets; the feature extraction module is used for executing feature extraction operation on each heterogeneous logistics event set to obtain a logistics feature core value set and an associated time window set; The multi-scale analysis module is used for utilizing the associated time window set as a multi-scale analysis reference, carrying out multi-level analysis on the logistics data sequence of the target order within the specified time range through a blockchain intelligent contract, and generating a plurality of logistics feature groups; and the feature fusion module is used for carrying out inter-scale fusion treatment on the plurality of logistics feature sets to obtain a final fusion logistics feature set, and outputting the final fusion logistics feature set as a logistics tracking result.
2. The electronic commerce logistics tracking system based on the blockchain is characterized in that feature extraction operation is performed on each heterogeneous logistics event set to obtain a logistics feature core value set and an associated time window set, the method comprises traversing each heterogeneous logistics event set to extract logistics data sequences to obtain a plurality of logistics data sequence groups, conducting key point detection on each logistics data sequence group to identify a plurality of key logistics data point sets, wherein each key logistics data point corresponds to the position with the largest gradient change in the logistics data sequence, conducting characterization processing on the plurality of key logistics data point sets to generate a key logistics feature set, conducting core value calculation on the key logistics feature set to determine a logistics feature core value set, conducting time window expansion analysis on each logistics data sequence group by taking the key logistics feature set as a reference, finding out data duration periods associated with each key logistics feature to form the key logistics feature time window set, and calculating the average value of each key logistics feature time window set to obtain the associated time window set.
3. The electronic commerce logistics tracking system based on the blockchain is characterized in that the key logistics feature set is subjected to core value calculation to determine the logistics feature core value set, the key logistics feature set is encoded by using a feature encoding network to obtain an encoded key logistics feature set, a feature average value of the encoded key logistics feature set is calculated to serve as an initial core value, iterative optimization is conducted on the initial core value in a preset step size, a better core value is searched in the encoded key logistics feature set, when the dispersion degree of the core value after the iterative optimization is smaller than or equal to that of the initial core value, the initial core value is taken as the logistics feature core value set, and when the dispersion degree of the core value after the iterative optimization is larger than that of the initial core value, iteration is continued until a stopping condition is met, and a final iterative result is taken as the logistics feature core value set.
4. The system of claim 3, wherein the performing a time window expansion analysis on each logistics data sequence set with the key logistics feature set as a reference to find a data duration period associated with each key logistics feature to form a key logistics feature time window set includes selecting a representative feature from the key logistics feature set as an anchor feature, locating a data segment matched with the anchor feature in the corresponding logistics data sequence set, centering on the anchor feature, expanding a time range to two sides according to a similarity threshold to determine an associated time window, and repeating the above process on all the key logistics features to generate the key logistics feature time window set.
5. The system for tracking the logistics of the electronic commerce based on the blockchain as claimed in claim 4, wherein the system is characterized in that the related time window set is used as a multi-scale analysis standard, the logistics data sequence of the target order in a specified time range is analyzed in a multi-level mode through the blockchain intelligent contracts, a plurality of logistics feature groups are produced, the system comprises the steps of configuring a plurality of analysis scales according to the length of the related time window set, deploying corresponding blockchain intelligent contracts for each analysis scale, inputting the logistics data sequence of the target order into each intelligent contract, carrying out scale specific analysis on the logistics data sequence by each intelligent contract, extracting logistics feature groups, and summarizing the output of all intelligent contracts to obtain a plurality of logistics feature groups.
6. The block chain-based e-commerce logistics tracking system of claim 5, wherein the step of performing inter-scale fusion processing on the plurality of logistics feature sets to obtain a final fusion logistics feature set comprises the steps of selecting an initial feature set and an adjacent feature set from the plurality of logistics feature sets, calculating a similarity matrix between the initial feature set and the adjacent feature set, performing normalization processing on the similarity matrix to obtain a normalized similarity value, fusing the normalized similarity value with the adjacent feature set by using convolution operation to generate a preliminary fusion feature set, fusing the remaining feature sets with the preliminary fusion feature set in sequence, gradually updating fusion results, and obtaining the final fusion logistics feature set when all feature sets are processed.
7. The system of claim 6, wherein the generating the preliminary fusion feature set by fusing the normalized similarity value with the neighboring feature set using a convolution operation comprises preparing a training data set comprising the sample similarity value and the sample feature set, training a convolutional neural network using the training data set to obtain a trained convolutional model, inputting the normalized similarity value and the neighboring feature set into the trained convolutional model, and outputting the preliminary fusion feature set.
8. The system of claim 7, wherein the processing the historical logistics record set to distinguish event types to generate a plurality of heterogeneous logistics event sets includes randomly sampling a plurality of logistics records from the historical logistics record set, pairing and combining the plurality of logistics records to generate a record pair set, calculating a similarity value of each record pair, classifying the record pairs into homogeneous or heterogeneous based on a similarity threshold, and classifying the historical logistics record set into a plurality of heterogeneous logistics event sets according to classification results.
9. The system of claim 8, wherein the acquiring the order identification of the target e-commerce order and performing a distributed query operation in the blockchain historian based on the order identification to retrieve historic logistics records to assemble a set of historic logistics records comprises receiving the order identification via the e-commerce platform interface, retrieving related historic logistics records in the blockchain network using a distributed query protocol, and sorting the retrieved records in chronological order to assemble the set of historic logistics records.
10. The blockchain-based e-commerce logistics tracking system of claim 9, wherein outputting the final fused logistics feature set as a logistics tracking result comprises converting the final fused logistics feature set into a readable format, generating a tracking report comprising logistics status and events, and outputting the tracking report through a designated interface.

Description

E-commerce logistics tracking system based on block chain Technical Field The invention relates to the technical field of E-commerce logistics management, in particular to an E-commerce logistics tracking system based on a block chain. Background The rapid development of modern electronic commerce places higher demands on the real-time, accuracy and transparency of logistic tracking systems. The traditional electronic commerce logistics system stores logistics information by adopting a centralized database, and has the problems of easy data tampering, opaque information, cross-system data island and the like. When consumers inquire the logistics state, only limited node information can be obtained, and complete and credible transportation chain data cannot be obtained. In the prior art, partial logistics systems attempt to improve the data sharing problem by applying a distributed database technology, but the problems of data authenticity and credibility are not fundamentally solved. The centralized stored logistics records are in risk of being tampered by a single mechanism, and data exchange between systems depends on complex interface butt joint, so that information barriers are easily formed. When a loss or damage dispute of goods occurs, it is difficult for parties to obtain consistent, non-repudiatable evidence of the logistic process. The block chain technology provides a new technical path for improving the e-commerce logistics tracking system due to the characteristics of decentralization, non-tampering, traceability and the like. However, the direct application of the blockchain technology to the logistics tracking scene still faces a plurality of challenges such as the problem of storage cost of massive logistics data, the problem of extraction efficiency of multi-dimensional logistics features, the problem of analysis accuracy of different time scale logistics modes and the like. The existing logistics scheme based on the block chain focuses on simple position record uplink, lacks the capability of carrying out deep analysis and feature fusion on logistics data, and is difficult to meet the requirements of modern E-commerce logistics on intelligent analysis and prediction. Disclosure of Invention The invention aims to provide an electronic commerce logistics tracking system based on a block chain, which is used for solving the problems in the background technology. In order to achieve the aim, the invention provides a block chain-based E-commerce logistics tracking system which comprises a distributed query module, an event distinguishing module, a feature extraction module, a multi-scale analysis module and a feature fusion module, wherein, The distributed query module is used for acquiring an order identifier of a target electronic commerce order, and executing distributed query operation in the blockchain historical database based on the order identifier to retrieve a historical logistics record so as to assemble a historical logistics record set; The event distinguishing module is used for distinguishing event types of the historical logistics record sets and generating a plurality of heterogeneous logistics event sets; the feature extraction module is used for executing feature extraction operation on each heterogeneous logistics event set to obtain a logistics feature core value set and an associated time window set; The multi-scale analysis module is used for utilizing the associated time window set as a multi-scale analysis reference, carrying out multi-level analysis on the logistics data sequence of the target order within the specified time range through a blockchain intelligent contract, and generating a plurality of logistics feature groups; and the feature fusion module is used for carrying out inter-scale fusion treatment on the plurality of logistics feature sets to obtain a final fusion logistics feature set, and outputting the final fusion logistics feature set as a logistics tracking result. Preferably, the feature extraction operation is performed on each heterogeneous logistics event set to obtain a logistics feature core value set and an associated time window set, the method comprises traversing each heterogeneous logistics event set to extract a logistics data sequence to obtain a plurality of logistics data sequence groups, conducting key point detection on each logistics data sequence group to identify a plurality of key logistics data point sets, wherein each key logistics data point corresponds to a position with the largest gradient change in the logistics data sequence, conducting characterization processing on the plurality of key logistics data point sets to generate a key logistics feature set, conducting core value calculation on the key logistics feature set to determine the logistics feature core value set, conducting time window expansion analysis on each logistics data sequence group by taking the key logistics feature set as a reference to find out data dur