Supercharge Your Innovation With Domain-Expert AI Agents!

A Recurrent Neural Network Based Query Term Weight Learning Method

A recurrent neural network and learning method technology, applied in the fields of data mining and search engines, can solve problems such as difficult integration, and achieve the effect of automatic and efficient prediction

Active Publication Date: 2019-04-19
DALIAN UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But its shortcomings are also obvious, that is, the assumption of independence between terms is implied. Even if many studies try to use the overall information of the query to consider this dependency in a disguised form, they only stay at the level of feature construction. Integrate it organically at the model 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
  • A Recurrent Neural Network Based Query Term Weight Learning Method
  • A Recurrent Neural Network Based Query Term Weight Learning Method
  • A Recurrent Neural Network Based Query Term Weight Learning Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] A kind of query item weight learning method based on recurrent neural network Concrete steps of the present invention are as follows:

[0046] 1. Search for the optimal term weight: use the intelligent search algorithm to obtain the optimal term weight value in combination with the collected public and labeled real data sets. The steps are as follows:

[0047] For the query "international organized crime", the number of query terms is 3, given by Get, the maximum evolutionary algebra T=100; Set query word weight precision to be 0.1, namely ε=1, by S=10*2 ε-1 Population capacity S=10; divide the interval [0, 1] into 10 intervals, 2 3 4 , use a 4-bit binary sequence to represent a number, which can represent 11 numbers such as 0, 0.1, ..., 0.9, 1, that is, the chromosome length is 4×3=12; 10 individuals are randomly generated as the initial population G(0), and the experiment The result is as follows:

[0048] (1) 010001011101, the first four digits 0100 correspond to...

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 method for learning query term weights based on a recurrent neural network, including S1, searching for optimal term weights, S2, constructing query term feature vectors, S3, constructing query term weight learning models, S4, using query term weights The learned model predicts query term weights. The present invention converts the query term weight prediction problem into a sequence labeling problem, and innovatively proposes a query term weight learning method based on a recurrent neural network, which realizes automatic and efficient prediction of the query term weight. The main evaluation index MAP on the set is increased by 16.8% (Robust04) and 11.8% (GOV2), which verifies the effectiveness of the method of the present invention for the task of learning the weight of query terms.

Description

technical field [0001] The invention relates to the technical fields of data mining and search engines, in particular to a method for learning weights of query terms based on a cyclic neural network. Background technique [0002] The performance of current information retrieval models or systems is highly dependent on query comprehension. Therefore, query comprehension technology has become an important research direction in the field of contemporary information retrieval, and one of the key issues is the analysis and prediction of the importance of each term in the query. Since the weight of query terms plays a very important role in the correlation score calculation formula of mainstream information retrieval models, assigning appropriate weight values ​​to each query term can greatly improve the accuracy of retrieval results. The weight prediction of query terms is closely related to the understanding and representation of queries, and involves technologies such as seman...

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): G06N3/04G06N3/08G06N3/12G06F16/951
CPCG06F16/951G06N3/084G06N3/126G06N3/045
Inventor 田利云马云龙林鸿飞
Owner DALIAN UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com