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

Mobile web service recommendation method and collaborative recommendation system based on user behavior analysis

A behavior analysis and business recommendation technology, applied in the recommendation field, can solve problems such as inability to provide users with business experience, low prediction accuracy, and sample noise

Active Publication Date: 2019-05-28
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some problems. This type of method generally weights and fuses the prediction results of all associated users, which will inevitably introduce sample noise from other users, resulting in low or even lower prediction accuracy, and cannot provide users with good business experience

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
  • Mobile web service recommendation method and collaborative recommendation system based on user behavior analysis
  • Mobile web service recommendation method and collaborative recommendation system based on user behavior analysis
  • Mobile web service recommendation method and collaborative recommendation system based on user behavior analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Below in conjunction with accompanying drawing and specific embodiment the technical solution of the present invention is described in further detail:

[0046] The present invention provides a mobile Web service recommendation method based on user behavior analysis, specifically as follows:

[0047] First, design the Web feature vector, extract the URL information of the web page, and establish a mapping table between the Web URL and the Web feature vector;

[0048] 1.1, analyze the domain name of the Web URL, extract the first and second feature values ​​corresponding to the Web, where the first feature value is the name of the enterprise or organization, and the second feature value is the business type; the resource path of the Web URL Analyze the name and extract the third eigenvalue corresponding to the Web, the third eigenvalue is the specific business form under the business type; thus obtain the Web eigenvector, and its elements are the first to third eigenvalue...

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 mobile Web service recommendation method and a collaborative recommendation system based on user behavior analysis. First, a Web service prediction model is constructed, and the user browsing data on the smart terminal side and user physiological data on the wearable device side are used to find the target user. The two optimally associated users with the most similar long-term habits and the most similar short-term emotions. Furthermore, the two optimal associated user data are used to enrich the sample library of the target user prediction model, and realize the sample enrichment mechanism of introducing noise minimization. Design a Web resource storage mechanism based on feature vectors, and realize accurate recommendation of mobile Web services according to the model prediction results. Through the interaction and cooperation between smart terminals and wearable devices, the solution reconstructs the application of physiological data on the wearable device side, analyzes user behavior from multiple perspectives and dimensions, realizes accurate business prediction and recommendation, and improves user experience.

Description

technical field [0001] The invention relates to a mobile Web service recommendation method and a collaborative recommendation system based on user behavior analysis, and belongs to the technical field of recommendation. Background technique [0002] In response to the explosive growth trend of mobile Internet services, the service recommendation engine, as an effective tool to solve the problems of user information overload and information confusion, can filter interested services for users from massive information by acquiring and predicting the potential preferences of mobile users, and Realize service pre-download, achieve the effect of balancing network load and reducing service delay. The premise of making accurate predictions for business recommendation engines requires a large number of user behavior samples as support. However, the number of samples limited to a single user is insufficient and the types are limited, resulting in low accuracy of business predictions a...

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): H04L29/08H04L12/24
CPCH04L41/145H04L41/147H04L67/02H04L67/51
Inventor 张晖毛小旺刘宝
Owner NANJING UNIV OF POSTS & TELECOMM