E-commerce logistics freight intelligent accounting system and method based on big data analysis

By constructing an intelligent freight cost calculation system based on big data analysis, and utilizing various technical means, we have achieved high accuracy, dynamic adjustment, and anomaly identification of e-commerce logistics freight costs. This has solved the problems of data inconsistency and calculation lag in existing technologies, and improved the accuracy and stability of freight cost calculation.

CN122453304APending Publication Date: 2026-07-24HEFEI HUIMENG CLOUD CHAIN INFORMATION TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610595596.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-30
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing e-commerce logistics freight calculation methods struggle to achieve accurate calculations when faced with inconsistencies in data formats between different platforms, warehousing systems, and carrier systems, as well as insufficient utilization of historical data. Furthermore, the lack of a continuous correction mechanism leads to inconsistent calculation standards and delayed anomaly identification.

Method used

An intelligent accounting system is constructed by employing mutual information measurement, freight correlation graph, kernel density estimation, random walk with restart, gradient boosting tree, Bayesian online change point detection, and recursive least squares method. Through correlation graph construction, reference sample screening, itemized accounting estimation, and feedback recursive update, the system achieves freight accounting with strong data adaptability, high accounting accuracy, and strong anomaly identification capability.

Benefits of technology

It improved the accuracy and stability of freight cost calculation, reduced calculation deviations, enhanced the ability to identify abnormal costs, reduced the pressure of manual review, and improved the stability of subsequent calculations through a feedback update mechanism.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an e-commerce logistics freight intelligent accounting system and method based on big data analysis. The method comprises the following steps of S1, obtaining multi-source data and performing preprocessing; s2, performing field dependency analysis, screening associated field combinations, performing sample aggregation, and constructing a freight association graph; s3, calculating distribution density weights of the associated nodes, spreading node weights along connection edges, screening high-weight associated nodes, and performing quantile interval division; s4, stratified sampling and feature binning are carried out, importance ranking is carried out, weight re-calibration is carried out on accounting features of different binning intervals, and sub-item accounting estimation is carried out; s5, identifying a residual abrupt change interval, inhibiting an abnormal residual point, and performing quantile regression reestimation to form a freight accounting result; and S6, obtaining feedback data, and updating the edge weight parameters. According to the method, the associated modeling of the e-commerce logistics freight can be realized, and the freight accounting accuracy and the abnormal expense identification capability are improved.
Need to check novelty before this filing date? Find Prior Art