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

User interest graph sequence dynamic management method based on search keywords

A technology for searching keywords and user interests, applied in the field of dynamic management of user interest graph sequences based on search keywords, can solve problems such as inability to solve research challenges, and achieve the effect of enriching semantics

Inactive Publication Date: 2020-08-04
XI AN JIAOTONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In summary, for the problem of user interest modeling based on search keywords, there is still a blank in the applied research, and the above research challenges cannot be solved at the existing technical level.

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
  • User interest graph sequence dynamic management method based on search keywords
  • User interest graph sequence dynamic management method based on search keywords
  • User interest graph sequence dynamic management method based on search keywords

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Below in conjunction with accompanying drawing and specific embodiment the method of the present invention is described in further detail:

[0042] Such as figure 1 As shown, in this embodiment, a method for dynamically managing user interest graph sequences based on search keywords, taking online shopping interests as an example, the steps are as follows:

[0043] Step 1: Collect the user's keyword search history on Taobao. With the user's informed authorization, the crawler captures the user's search keyword and implicit interaction behavior, including search duration, number of search result page views, and result page average Browsing time;

[0044] Step 2: Use the graph sequence model to statically model user search behavior, as follows:

[0045] Such as Figure 2a As shown, the graph sequence model is composed of undirected complete graphs arranged on the time axis. Each undirected complete graph G=(N, E, [Ts, Te]) corresponds to a search interval of the user. ...

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 user interest graph sequence dynamic management method based on search keywords comprises the following steps: 1, collecting the user keyword search history, wherein the search keywords serve as potential interests; 2, mapping implicit interaction behaviors during searching into a graph sequence model; 3, based on the continuity of interest, reversely and dynamically updating the preamble sequence through subsequent user search, adaptively filtering noise search, and reserving real user interest. According to the method, a complete theoretical model framework is designed, user search and implicit interaction behaviors are modeled originally, behavior details are restored, real user interests are mined from search behaviors, high ecological effectiveness is reserved, and the model is verified on real data.

Description

technical field [0001] The invention relates to the technical fields of data mining and computer application, in particular to a method for dynamically managing user interest graph sequences based on search keywords. Background technique [0002] User interest mining analysis has important guiding significance for understanding user intentions, discovering similar users, and providing personalized recommendations and other services. So far, the modeling and analysis of user interest is mainly used in personalized product recommendation and advertisement delivery. The existing technology uses the specific product purchased by the user or the explicit rating of the product as the interest, rather than the abstract user's interest in the product. An interest in a certain topic or commodity. [0003] Taking shopping as an example, in fact, compared with the purchase behavior that only accounts for a small part of user data, the richer search and browsing behavior trajectories o...

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): G06F16/901G06F16/9535
CPCG06F16/9024G06F16/9535
Inventor 赵靓冯铃喻丰
Owner XI AN JIAOTONG UNIV