A method for identifying defective products in e-commerce based on transfer learning

A technology of transfer learning and recognition method, applied in the field of e-commerce data analysis, can solve the problems of difficult recognition, low recognition accuracy, high cost, etc., to achieve the effect of ensuring accuracy and reducing costs

CN111402012BActive Publication Date: 2020-08-25江苏省质量和标准化研究院
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2020-08-25

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention provides a method for identifying defective products in e-commerce based on transfer learning, comprising the following steps: S30 Encoding text information, encoding the text information into vector form to obtain encoded data, and using words in the text information in the current paragraph The co-occurrence in , to obtain a distributed representation; S40 feature extraction, input the encoded data into the algorithm module, and generate domain-independent features through the migration learning algorithm based on confrontational domain adaptation; and S50 defective product identification, domain-independent The feature is used as input, through a multi-channel convolutional neural network, and then connected to multiple layers of fully connected layers to identify defective products. A method for identifying defective products in e-commerce based on transfer learning of the present invention aims at the difference between product data distributions on different e-commerce platforms, uses the transfer learning method to greatly reduce the cost of identifying defective products on different e-commerce platforms, and improves The accuracy of defective product identification is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of e-commerce data analysis, in particular to a method for identifying defective e-commerce products based on transfer learning. Background technique

[0002] With the development of the Internet and the advent of the era of artificial intelligence, information exchange has become increasingly frequent, resulting in a huge increase in the total amount of information. In the context of the widespread application of e-commerce, the massive data of the major e-commerce platforms behind it will have inestimable mining value. Although e-commerce is developing rapidly, there are still many problems. One of the important issues is the quality of e-commerce products.

[0003] With the emergence of various e-commerce platforms, how to realize defective product identification on different e-commerce platforms is a challenge. Different e-commerce platforms have differences in product descriptions and buyer reviews. ...

Examples

Embodiment Construction

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0022] In this embodiment, a method for identifying defective e-commerce products based on transfer learning is provided, such as figure 1 As shown, the following steps are included: S10 data collection, obtaining product text data of multiple e-commerce platforms. S20 data preprocessing, preprocessing the product text data by product category to obtain text information, the preprocessing includes text segmentation and filtering stop words. S30 Encoding text information, enco...