Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training method for similarity model parameters, search processing method and corresponding apparatuses

A technology of model parameters and similarity, applied in special data processing applications, electrical digital data processing, instruments, etc., can solve problems such as application scene processing, and achieve the effect of improving experience and search efficiency

Inactive Publication Date: 2016-09-07
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF4 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current search engine does not have special processing for this application scenario, so users need to repeatedly search through keywords to find the term entry (Term) of the description

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
  • Training method for similarity model parameters, search processing method and corresponding apparatuses
  • Training method for similarity model parameters, search processing method and corresponding apparatuses
  • Training method for similarity model parameters, search processing method and corresponding apparatuses

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0084] Preferably, as an implementation of S11, the S11 includes:

[0085] S110, establishing a parameterized word vector matrix and a parameterized hidden layer transformation matrix.

[0086] In establishing a parameterized word vector matrix, it specifically includes:

[0087] (1) Segment each binary pair in the training data set.

[0088] The word segmentation technology is used to segment the description D of each binary pair entry in the training data set. For example, assume that the description D of the word entry in each binary pair is divided into text strings of length M. Then the description D of the word entry in each binary pair is expressed as (d 1 ,d 2 ... d M ), the word entry T in each binary pair is a text string with a length of 1, denoted by t.

[0089] (2) The word vector of each word obtained by parametric word segmentation.

[0090] The word vector emb(T) of the word entry of each binary pair is expressed as (emb_t), and the word vector emb(D) of...

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 training method for similarity model parameters, a search processing method and corresponding apparatuses. The method for the similarity model parameters comprises the steps of constructing a training data set; performing training by utilizing the training data set to obtain the similarity model parameters; obtaining statement description input by a user and obtaining all word entries from a pre-created word entry database; obtaining a word vector matrix corresponding to the statement description and a word vector of each word entry in the word entry database; determining the similarity between the statement description and each word entry in the word entry database according to the similarity model parameters and the word vector matrix corresponding to the statement description; and presenting a search result of the statement description to the user according to the similarity between the statement description and each word entry in the word entry database. According to the training method, the search processing method and the corresponding apparatuses, the word entry described by the user can be reversely searched for according to the description input by the user, so that the search experience and efficiency of the user are improved.

Description

【Technical field】 [0001] The invention relates to the field of computer application technology, in particular to a method for training similarity model parameters, a search processing method and a corresponding device. 【Background technique】 [0002] When a user uses a search engine, in addition to usually looking for a web page associated with a certain keyword, there is another application scenario. The user probably knows the meaning or use of a certain word or an item, but does not know the meaning or use of the word. Or the specific name of the item (such as non-trace nails), the user can enter the specific description of the word in the search engine (for example, a kind of thing used to hang photo frames, and will not affect the wall.) to reverse lookup the word ; Or when the user knows the general characteristics of a certain restaurant, but forgets the specific name of the restaurant, he hopes to be able to enter the description of the restaurant to find the name of...

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 张军
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com