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

Middle and small website-oriented user access intention acquisition method and system

An acquisition method, small and medium-sized technology, applied in the field of retrieval, which can solve problems such as large workload

Inactive Publication Date: 2018-03-13
CENT SOUTH UNIV
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If website developers want to implement a recommendation system that considers user access intentions in small and medium-sized websites, a large workload is required

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
  • Middle and small website-oriented user access intention acquisition method and system
  • Middle and small website-oriented user access intention acquisition method and system
  • Middle and small website-oriented user access intention acquisition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] figure 1 The framework of the ICFR system is shown, which mainly includes three parts: the acquisition of client information, the realization of the server-side recommendation process, and the incremental update of data.

[0032] In the ICFR model, we first need to obtain user information (such as user account information, client physical address, etc.) from the client to uniquely identify the user. When a user visits a website, the user's browsing behavior, such as saving bookmarks, number of page visits, page stay time, etc., will be recorded in the server's access log, and the user's browsing information will be calculated using a normalization algorithm to obtain a A value within a certain range is used as the user's rating for the item. Using all the above information, a user-item matrix (UIM) can be constructed. Then, a collaborative filtering-based recommendation process is implemented. A user-user similarity matrix (user-user similarity matrix, UUSM) can be o...

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 middle and small website-oriented user access intention acquisition method and system. The method adopts a relatively widely applied collaborative-filtering recommendation algorithm to analyze access intention of users and carry out recommendation for the users. However, compared with traditional recommendation algorithms, the method uses an improved Pearson correlation coefficient calculation method when similarity between the users is calculated. Theoretical analysis and experiment prove that the method in the invention achieves higher precision. By adopting a method of updating of an independent type between the users, calculation is not carried out for all the users at every turn, and an updating operation is carried out only on history data of the user with an access behavior at every turn according to situations of accessing the website by the user. According to the method, the calculation amount of updating at every turn is greatly decreased, time consumption is reduced, and the website is also enabled to have relative real-time performance for a recommendation result of the user.

Description

technical field [0001] The invention relates to the field of retrieval, in particular to a method and system for acquiring user access intentions for small and medium-sized websites. Background technique [0002] In the past two decades, recommender systems have become a research focus in the retrieval field, and are widely used in travel, virtual industrial goods, social networks, etc. Large corporate websites, such as Amazon and Netflix, have successfully applied recommender systems to their websites. The current mainstream recommendation systems are mainly divided into four categories: content-based recommendation methods, association rule-based recommendation methods, knowledge-based recommendation methods, and collaborative filtering-based recommendation methods. [0003] The content-based recommendation method extracts the features of the content of the recommended items, and selects items with similar features from the recommended items as the recommendation results ...

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): G06F17/30
CPCG06F16/9535
Inventor 郭克华张瑞芳
Owner CENT SOUTH UNIV