Research Review of Time-Sensitive Query Auto-completion Technique

TIAN Xuan; ZHANG Xiao; MENG Xiang-guang; CHEN Zhi-bo

doi:10.3969/j.issn.0372-2112.2015.06.018

您当前的位置：

首页 >

文章列表页 >

Research Review of Time-Sensitive Query Auto-completion Technique

更新时间：2025-07-16

- Research Review of Time-Sensitive Query Auto-completion Technique
- Acta Electronica Sinica Vol. 43, Issue 6, Pages: 1160-1168(2015)
- 作者机构：
  
  北京林业大学信息学院,北京,100083
- 作者简介：
- 基金信息：
  
  supported by Fundamental Research Funds for the Central Universities (No.YX2014-19)
- DOI：10.3969/j.issn.0372-2112.2015.06.018
  CLC： TP391.1
- Published：2015
- 稿件说明：
移动端阅览
TIAN Xuan, ZHANG Xiao, MENG Xiang-guang, et al. Research Review of Time-Sensitive Query Auto-completion Technique[J]. Acta Electronica Sinica, 2015, 43(6): 1160-1168.
DOI：

TIAN Xuan, ZHANG Xiao, MENG Xiang-guang, et al. Research Review of Time-Sensitive Query Auto-completion Technique[J]. Acta Electronica Sinica, 2015, 43(6): 1160-1168. DOI： 10.3969/j.issn.0372-2112.2015.06.018.

摘要

搜索引擎的查询词补全技术给搜索用户提供了较好的用户体验.针对用户检索需求随时间变化而不同这一问题

时间敏感查询词自动补全成为研究热点.时间敏感查询词补全在生成查询词补全候选列表时拟合多种时间因素

呈现出与传统查询词补全不同的特点.本文首先介绍了时间敏感查询词补全的定义和分类

然后从查询词时间敏感类型判断、补全候选词权值计算、候选词排序计算三个步骤分析了关键技术

最后对技术评价方法和技术未来发展难点与热点进行了总结和展望.

Abstract

Query auto-completion of search engines provides good experience for the users.With the user's search intention changing over time

time-sensitive query auto-completion (TSQC) comes to be a research focus.Different from traditional query auto-completion

recommendation list of TSQC is made according to the attaching time features of the query words.First

the definition and classification of TSQC are introduced.Then the key steps of TSQC are presented and analyzed

which include type judgment of time-sensitive query

weight calculation of candidates and recommendation list ranking.Finally

technique evaluation and future development of TSQC are analyzed and summarized.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Pseudo-Relevance Feedback Query Expansion Based on the Fusion of Association Pattern Mining and Word Embedding Learning

Efficiently Reducing Transferring Cost of Skyline Queries over Distributed Networks

The Least Upper Approximation of Concept

Predicting Query Performance Using Semantic Chart

Related Author

HUANG Ming-xuan

ZHU Peng-hua

WANG Jun-xing

LIU Zi-yang

XUE Pu

LIN Chen

XIANG Yang

Related Institution

School of Information and Statistics， Guangxi University of Finance and Economics

Guangxi Key Laboratory of Cross-border E-commerce Intelligent Information Processing， Guangxi University of Finance and Economics

Cangzhou Normal University

School of Computer Science, North China Institute of Aerospace Engineering

Department of Computer Science and EnginneeringSourtheast UniversityNanjingJiangsu 210096China

⁰