CN-121981464-A - E-commerce supply chain management system and method based on big data

CN121981464ACN 121981464 ACN121981464 ACN 121981464ACN-121981464-A

Abstract

The invention relates to the technical field of data processing and discloses an electronic commerce supply chain management system and method based on big data, wherein the system comprises a data standardization processing module, an intelligent risk assessment module, a dynamic decision optimization module, an execution effect monitoring module and an iteration optimization module, and performs data format verification on real-time transaction data and logistics data acquired by supply chain link points to obtain standard data; abnormal detection is carried out on the standard data through a supply chain risk analysis mechanism of the data terminal, and an interruption risk value is obtained; based on the interruption risk value, carrying out self-adaptive adjustment on real-time data of the supply chain node to obtain a supply chain optimization execution scheme; the method and the system for optimizing the supply chain risk analysis based on the electronic commerce supply chain management can improve the operation efficiency of the electronic commerce supply chain management based on big data.

Inventors

LI HAIQIANG
WANG NENG

Assignees

商丘悦盈语网络科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260121

Claims (10)

1. The electronic commerce supply chain management system based on big data is characterized by comprising a data standardization processing module, an intelligent risk assessment module, a dynamic decision optimization module, an execution effect monitoring module and an iteration optimization module, wherein: the data standardization processing module is used for carrying out data format verification on real-time transaction data and logistics data acquired by the supply chain node to obtain the standard data of the supply chain node; the intelligent risk assessment module is used for carrying out anomaly detection on the standard data through a supply chain risk analysis mechanism of the data terminal to obtain an interruption risk value of the supply chain node; the dynamic decision optimization module is used for adaptively adjusting the real-time data of the supply chain node based on the interruption risk value to obtain a supply chain optimization execution scheme of the supply chain node; The execution effect monitoring module is used for carrying out data monitoring on the execution effect of the supply chain node based on the supply chain optimization execution scheme to obtain the execution feedback data of the supply chain optimization execution scheme; and the iterative optimization module is used for optimizing and updating the supply chain risk analysis mechanism according to the execution feedback data to obtain a target risk analysis mechanism of the supply chain node.
2. The big data-based e-commerce supply chain management system of claim 1, wherein the data normalization processing module is configured to, when performing data format verification on real-time transaction data and logistics data collected by a supply chain node, obtain specification data of the supply chain node: carrying out structural analysis on real-time transaction data and logistics data of a supply chain node to obtain transaction data fields and logistics data fields of the supply chain node; performing data verification on the transaction data field and the logistics data field to obtain a standard transaction data field and a standard logistics data field of the supply chain node; And carrying out heterogeneous fusion on the standard transaction data field and the standard logistics data field to obtain the standard data of the supply chain node.
3. The big data-based e-commerce supply chain management system of claim 1, wherein the intelligent risk assessment module is configured to, when executing a supply chain risk analysis mechanism through a data terminal, perform anomaly detection on the canonical data to obtain an outage risk value of the supply chain node: based on the historical normal operation data of the supply chain node, carrying out multidimensional reference construction on the supply chain node to obtain a reference behavior mode of the supply chain node; Performing abnormal association comparison on the standard data and the reference behavior pattern to obtain an abnormal data sequence of the standard data; And carrying out multidimensional influence weight evaluation on the abnormal data sequence to obtain an interruption risk value of the supply chain node.
4. The big data based e-commerce supply chain management system of claim 3, wherein the intelligent risk assessment module is configured to, when executing the historical normal operation data based on the supply chain node, perform multidimensional benchmark construction on the supply chain node to obtain a benchmark behavior pattern of the supply chain node: Performing multidimensional feature extraction on the historical normal operation data of the supply chain node to obtain the historical operation feature data of the supply chain node; Carrying out fluctuation trend statistical analysis on the historical operation characteristic data to obtain reference statistical characteristics of the supply chain nodes; and performing modeling synthesis on the reference statistical features to obtain a reference behavior mode of the supply chain node.
5. The big data based e-commerce supply chain management system of claim 3, wherein the intelligent risk assessment module is configured to, when performing multidimensional impact weight assessment on the abnormal data sequence to obtain an outage risk value for the supply chain node: Carrying out multidimensional risk quantitative evaluation on the abnormal data sequence to obtain a dimensional risk evaluation value of the abnormal data sequence; Performing weight distribution on the dimension risk assessment value to obtain a weight coefficient of the dimension risk assessment value; And carrying out weighted fusion on the dimension risk evaluation value and the weight coefficient to obtain an interruption risk value of the supply chain node, wherein the calculation formula of the interruption risk value is as follows: ; In the formula, Is the first The outage risk values for each of the supply chain nodes, For the total number of evaluation dimensions selected, In the first dimension risk assessment value The weight coefficients of the individual dimensions are such that, At the first supply chain node The original anomaly index value for each dimension, The dimension risk assessment value is in the historical state The average value of the individual dimensions is calculated, The dimension risk assessment value is in the historical state The standard deviation of the dimensions of the sample, As a function of the natural index of refraction, Is a nonlinear amplification factor in the function.
6. The big data based e-commerce supply chain management system of claim 1, wherein the dynamic decision optimization module is configured to, when executing the supply chain optimization execution scheme based on the interruption risk value, adaptively adjust the real-time data of the supply chain node to obtain the supply chain optimization execution scheme of the supply chain node: dynamically adjusting the real-time data of the supply chain node based on the risk level corresponding to the interruption risk value to obtain an execution scheme of the supply chain node; Performing flow strategy optimization on the execution scheme to obtain a preliminary execution scheme of the supply chain node; And performing comprehensive efficiency check on the preliminary execution scheme to obtain a supply chain optimization execution scheme of the supply chain node.
7. The big data based e-commerce supply chain management system of claim 6, wherein the dynamic decision optimization module is configured to dynamically adjust the real-time data of the supply chain node to obtain the execution scheme of the supply chain node when executing the risk level corresponding to the interruption risk value: Generating a response strategy of the risk level according to the risk level corresponding to the interruption risk value; performing strategy response on the real-time data of the supply chain node based on the response strategy to obtain adjusted data of the supply chain node; And carrying out collaborative verification on the adjusted data, and carrying out content adjustment conversion on the verified data to obtain an execution scheme of the supply chain node.
8. The big data based e-commerce supply chain management system of claim 1, wherein the execution effect monitoring module is configured to, when executing the supply chain optimization execution scheme, monitor the execution effect of the supply chain node to obtain the execution feedback data of the supply chain optimization execution scheme, specifically: establishing a multi-dimensional monitoring index system through the supply chain optimization execution scheme; Performing association comparison on the multi-dimensional monitoring index system and the monitoring data of the execution effect to obtain a deviation analysis result of the supply chain node; and comprehensively judging the deviation analysis result to obtain the execution feedback data of the supply chain optimization execution scheme.
9. The big data based e-commerce supply chain management system of claim 1, wherein the iterative optimization module is configured to, when executing the optimization update of the supply chain risk analysis mechanism according to the execution feedback data to obtain the target risk analysis mechanism of the supply chain node: performing defect analysis on the execution feedback data to obtain a risk analysis defect report of the supply chain risk analysis mechanism; Based on the risk analysis defect report, optimizing and correcting the supply chain risk analysis mechanism to obtain an optimized risk analysis mechanism of the supply chain risk analysis mechanism; And backtracking verification is carried out on the optimized risk analysis mechanism to obtain a target risk analysis mechanism of the supply chain node.
10. An electronic commerce supply chain management method based on big data, characterized in that the method comprises the following steps: s1, performing data format verification on real-time transaction data and logistics data acquired by a supply chain node to obtain standard data of the supply chain node; S2, performing anomaly detection on the standard data through a supply chain risk analysis mechanism of a data terminal to obtain an interruption risk value of the supply chain node; S3, based on the interruption risk value, carrying out self-adaptive adjustment on the real-time data of the supply chain node to obtain a supply chain optimization execution scheme of the supply chain node; s4, based on the supply chain optimization execution scheme, performing data monitoring on the execution effect of the supply chain node to obtain the execution feedback data of the supply chain optimization execution scheme; and S5, optimizing and updating the supply chain risk analysis mechanism according to the execution feedback data to obtain a target risk analysis mechanism of the supply chain node.

Description

E-commerce supply chain management system and method based on big data Technical Field The invention relates to the technical field of data processing, in particular to an electronic commerce supply chain management system and method based on big data. Background In the field of e-commerce supply chain management, along with the continuous expansion of transaction scale and continuous extension of logistics network, each node of the supply chain can generate massive real-time transaction data and logistics data. However, the prior art generally lacks perfect data standardization processing capability, and is difficult to perform efficient format verification and heterogeneous fusion on multi-source and multi-format real-time data, so that the data often has problems of field non-standardization, format confusion and the like, and cannot be converted into high-quality standard data for subsequent analysis. The limitation of data processing directly causes the deviation of hysteresis and accuracy of information transmission, so that the data coordination efficiency among all nodes in the supply chain management process is low, and the overall response speed and operation smoothness of the supply chain are further restricted. Meanwhile, the existing supply chain risk assessment and decision optimization mechanism has significant defects. In the risk assessment link, the prior art relies on historical data with single dimension for analysis, and fails to construct a scientific reference behavior mode based on multidimensional features, so that abnormal data sequences cannot be identified with insufficient precision, interruption risk values of supply chain nodes cannot be calculated accurately, in the decision optimization and execution link, the existing scheme lacks dynamic adaptation capability of the interruption risk values, the generated execution scheme is difficult to carry out self-adaptive adjustment according to supply chain real-time data, and effective execution effect monitoring and mechanism iteration means are lacking. The series of problems enable the supply chain to not generate a targeted optimization scheme in time when the supply chain is at potential risk, the risk resistance is weak, the operation efficiency of the supply chain is low, the conditions of node interruption, resource waste and the like are easy to occur, and therefore how to improve the operation efficiency of the supply chain becomes a problem to be solved urgently. Disclosure of Invention The invention provides an electronic commerce supply chain management system and method based on big data, which are used for solving the problems in the background technology. In order to achieve the above purpose, the electronic commerce supply chain management system based on big data provided by the invention is characterized in that the system comprises a data standardization processing module, an intelligent risk assessment module, a dynamic decision optimization module, an execution effect monitoring module and an iterative optimization module, wherein: the data standardization processing module is used for carrying out data format verification on real-time transaction data and logistics data acquired by the supply chain node to obtain the standard data of the supply chain node; the intelligent risk assessment module is used for carrying out anomaly detection on the standard data through a supply chain risk analysis mechanism of the data terminal to obtain an interruption risk value of the supply chain node; the dynamic decision optimization module is used for adaptively adjusting the real-time data of the supply chain node based on the interruption risk value to obtain a supply chain optimization execution scheme of the supply chain node; The execution effect monitoring is used for carrying out data monitoring on the execution effect of the supply chain node based on the supply chain optimization execution scheme to obtain the execution feedback data of the supply chain optimization execution scheme; and the iterative optimization module is used for optimizing and updating the supply chain risk analysis mechanism according to the execution feedback data to obtain a target risk analysis mechanism of the supply chain node. In a preferred embodiment, the data normalization processing module is specifically configured to, when performing data format verification on real-time transaction data and logistics data collected by a supply chain node to obtain specification data of the supply chain node: carrying out structural analysis on real-time transaction data and logistics data of a supply chain node to obtain transaction data fields and logistics data fields of the supply chain node; performing data verification on the transaction data field and the logistics data field to obtain a standard transaction data field and a standard logistics data field of the supply chain node; And carrying out heterogeneous fusion on the standard transac