Unlock instant, AI-driven research and patent intelligence for your innovation.

A Two-layer Graph Structure Recommendation Method Based on Review Mining and Density Clustering

A density clustering and recommendation method technology, applied in the recommendation field, can solve the problems of slow operation efficiency, large parameter dependence, manual determination, etc., and achieve the goals of improved accuracy, low parameter sensitivity, good applicability and scalability Effect

Active Publication Date: 2020-05-05
ZHEJIANG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the disadvantages of low accuracy and slow operating efficiency of the existing recommendation methods, the cluster centers of most clustering algorithms need to be manually determined, the clustering accuracy is low, and the parameter dependence is large, the present invention provides a high-precision A two-layer graph structure recommendation method based on review mining and density clustering with high operating efficiency, high accuracy, and good real-time performance

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
  • A Two-layer Graph Structure Recommendation Method Based on Review Mining and Density Clustering
  • A Two-layer Graph Structure Recommendation Method Based on Review Mining and Density Clustering
  • A Two-layer Graph Structure Recommendation Method Based on Review Mining and Density Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] refer to Figure 1 to Figure 8 , a two-layer graph structure recommendation method based on comment mining and density clustering. For comment data, after part-of-speech tagging, the part-of-speech of all words in the comment sentence can be obtained. The part-of-speech tagging toolkit uses the Stanford Natural Language Processing Toolkit. For example, for the comment "I played here once and thought this spot was cool", the output is:

[0049] [('I','PRP'),('played','VBD'),('here','RB'),('once','RB'),('and','CC') ,('thought','VBD'),('this','DT'),('spot','NN'),('was','VBD'),('cool','JJ') ]

[0050] After filtering the stop words, extract the noun items whose occurrence frequency is greater than or equal to the threshold θ as frequent items. Create a list of partial features afterwards. For example, for restaurant reviews, some feature lists are shown in Tab...

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

A two-layer graph structure recommendation method based on comment mining and density clustering, comprising the following steps: 1) reading the comment data set, and extracting the features of items for clustering through feature extraction and sentiment analysis; 2) clustering center A fast-determined density clustering algorithm that outputs the optimal d c and optimal d c 3) Based on the recommendation of the graph structure, the n items with the highest energy value are output as the recommendation result. The invention provides a two-layer graph structure recommendation method based on comment mining and density clustering with high precision, high operating efficiency, high accuracy rate and good real-time performance.

Description

technical field [0001] The invention belongs to the technical field of recommendation and relates to a recommendation method. Background technique [0002] With the advent of the era of big data, there are more and more products available to consumers, and they may be overwhelmed by more choices. This phenomenon is called "information overload". How to use big data technology to recommend products that consumers expect has gradually become one of the hot issues in current research. The recommendation system is an effective method to solve information overload. It collects the user's personality, preferences and other information, and feeds back the appropriate recommendation results to the user. It has been widely used in digital business, social network, digital library and other fields. . Commonly used recommendation algorithms include: collaborative filtering, algorithms based on matrix decomposition, algorithms based on comment mining, algorithms based on clustering, e...

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 Patents(China)
IPC IPC(8): G06F16/9535G06F16/2458G06K9/62G06Q30/06
CPCG06F16/2465G06F16/9535G06Q30/0601G06F18/2321
Inventor 陈晋音陈一贤林翔吴洋洋
Owner ZHEJIANG UNIV OF TECH