Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

False comment automatic generation method and device based on deep learning

A deep learning, automatic generation technology, applied in the field of deep learning

Pending Publication Date: 2020-10-30
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, individual reviewers post many fake reviews due to interests, brand bias, etc.

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
  • False comment automatic generation method and device based on deep learning
  • False comment automatic generation method and device based on deep learning
  • False comment automatic generation method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementation methods described in the following exemplary embodiments do not represent all implementation methods consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with some aspects of the invention as recited in the appended claims.

[0036] A method for generating fake reviews based on deep learning, the specific steps include:

[0037] Step 1. Acquisition and arrangement of review training data

[0038] The comment data is crawled from the Dianping website. According to the different products of different merchants, the comments obtained are also varied. The specific process of obtaining is as follows:...

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 false comment automatic generation method and device based on deep learning. The method comprises three steps: obtaining real original comments, generating initial false comments according to the real comments, and marking mature false comments through screening and detection. Compared with a manual labeling method, the method is short in consumed time and high in efficiency, and a large number of human resources can be saved; compared with other false comment generation methods, the method belongs to an unsupervised deep learning method, and has the characteristics of high generation speed, high simulation degree and the like when facing massive data processing and multi-type target generation, so the method is more suitable for being applied to a real e-commerceenvironment. The device based on the method comprises an acquisition module, a generation module, a judgment module and a marking module, wherein the generation module and the judgment module respectively need two different deep learning modules.

Description

[0001] The invention belongs to the technical field of deep learning, and in particular relates to a method and device for automatically generating false comments. Background technique [0002] The rapid development of the Internet has enabled online platforms to play an important role in people's shopping, travel, dining, accommodation and other aspects. These online platforms have a lot of reviews. As a bridge to connect consumers and products, review information can not only influence consumers' decision-making, but also serve as feedback to promote merchants to improve product details. However, individual reviewers post many fake reviews due to interests, brand bias, and other reasons. They will even cooperate to post fake reviews and form fake review groups. According to the survey, the proportion of fake reviews on Yelp, the American version of public comment site, has risen from 5% in 2006 to 20% in 2013. Studying deep learning to generate fake reviews can take a hea...

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
IPC IPC(8): G06F40/289G06F40/30G06F40/253G06K9/62G06F16/9535G06N20/00
CPCG06F40/289G06F40/30G06F40/253G06F16/9535G06N20/00G06F18/24
Inventor 许娟李荣基
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products