Commodity comment public opinion-based cross-border product quality risk fuzzy prediction method

A product quality and product review technology, applied in neural learning methods, biological neural network models, special data processing applications, etc., can solve problems such as insufficient inspection and quarantine personnel

Active Publication Date: 2018-11-02
ZHEJIANG UNIV CITY COLLEGE
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Under such fast-growing e-commerce and frequent domestic and foreign commodity trade, the national inspection and quarantine personnel are far from enough, so under such circumstances, the inspection of import and export trade has brought great pressure

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Commodity comment public opinion-based cross-border product quality risk fuzzy prediction method
  • Commodity comment public opinion-based cross-border product quality risk fuzzy prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0020] A method for fuzzy prediction of cross-border product quality risk based on commodity review public opinion, comprising the following steps:

[0021] 1. Data collection and data preprocessing. Multi-threaded collection: The collected data is product information and comment information in cross-border e-commerce platforms such as JD.com, Tmall, and Kaola, stored in relational databases and text databases, using redis, and mongodb's NoSql unst...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a commodity comment public opinion-based cross-border product quality risk fuzzy prediction method. The method comprises the steps of collecting data; preprocessing the data, wherein the data preprocessing comprises text analysis and data conversion; establishing a commodity sub-word bank and a product quality comment word bank; establishing a commodity classification library; carrying out reference risk grade labeling on a product according to sampling inspection report data of inspection and quarantine and risk evaluation standards; analyzing commodity comment publicopinions, and extracting negative comments in comment information; analyzing negative comment quality relevancy, and calculating the number of quality negative comments of commodities in the same category; building a risk prediction model, wherein the risk prediction model comprises a membership function and a BP neural network; and outputting a prediction risk grade, and predicting a product quality risk according to the prediction risk grade. According to the prediction method, through the judgment of a user to quality evaluation contents of a type of commodities, the quality of the commodities and the commodities in a big-class commodity catalogue can be known from the side.

Description

technical field [0001] The invention belongs to the field of data mining, and in particular relates to a method for fuzzy prediction of cross-border product quality risk based on commodity review public opinion. Background technique [0002] Due to the globalization of commodity circulation, coupled with the rapid development of China's e-commerce, resulting in the rapid development of China's foreign trade, the demand for entry-exit inspection and quarantine is increasing. In 2016, the total value of my country's import and export trade was 25 trillion yuan. From the total value of import and export trade that broke one trillion yuan in 2005 to 25 trillion yuan ten years later, the reason for this rapid development momentum is that e-commerce With rapid development, the sudden emergence of cross-border e-commerce on a global scale has not only changed the traditional operation methods of foreign trade enterprises, but also profoundly affected the layout of China's foreign tr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06N3/08
CPCG06N3/084
Inventor 金苍宏吴明晖戴知君刘泽民朱凡微赵品通
Owner ZHEJIANG UNIV CITY COLLEGE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products