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

Keyword extraction model training method and device, keyword extraction method and device and storage medium

An extraction method and keyword technology, which is applied in character and pattern recognition, semantic analysis, instruments, etc., can solve problems such as the inability to extract keywords, and achieve the effects of improving user search experience, good generalization performance, and improving accuracy

Active Publication Date: 2019-09-13
TENCENT TECH (SHENZHEN) CO LTD
View PDF7 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The embodiment of the present application also provides a keyword extraction method, device and storage medium to make full use of the semantic relationship between the text and the title, and solve the problem that accurate keywords cannot be extracted for short texts

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
  • Keyword extraction model training method and device, keyword extraction method and device and storage medium
  • Keyword extraction model training method and device, keyword extraction method and device and storage medium
  • Keyword extraction model training method and device, keyword extraction method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0050] For the sake of brevity and intuition in description, the solution of the present application is described below by describing several representative embodiments. Numerous details in the examples are only used to assist in understanding the scheme of the present application. However, obviously, the technical solution of the present application may not be limited to these details when implemented. In order to avoid unnecessarily obscuring the solution of the present application, some implementations are not described in detail, but only a framework is given. Hereinafter, "including" means "including but not limited to", and "according to..." means "at least according to, but not limited to only based on...". When the quantity of a component is not specifically indicated below, it means that ...

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 embodiment of the invention provides a keyword extraction method, which comprises the following steps of: carrying out word segmentation processing on a text to obtain a plurality of candidate words; segmenting a title with the same semantics as the text by taking a character as a unit to obtain a plurality of characters; sequentially inputting the plurality of candidate words into a keyword extraction model to obtain attention weights of the candidate words relative to the characters, the attention weights being used for representing semantic association degrees of the candidate words andthe characters respectively; selecting candidate words appearing in the title from the candidate words; determining an extraction threshold value according to the attention weight of the selected candidate word relative to each character; and according to the extraction threshold, determining keywords of the text from the candidate words. The embodiment of the invention further provides a training method and device of the keyword extraction model and a storage medium.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a keyword extraction model training method, keyword extraction method, device and storage medium. Background technique [0002] A keyword is a word that represents the core semantics of a document. When a user enters a keyword, the search engine can return corresponding search results based on the keyword entered by the user. For example, the user can search Moments, articles, official accounts, and novels based on keywords. , music, expressions, etc. [0003] For example, TF-IDF (term frequency–inverse document frequency) model or textrank model can be used to extract keywords. Among them, the TF-IDF model calculates the weight of words in the text by multiplying the word frequency by the inverse document frequency, and the word frequency It measures the importance of the word in the current text, and the inverse document frequency measures the common degree 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): G06F17/27
CPCG06F40/289G06F40/30G06F40/284G06V30/414
Inventor 郑文豪康烈颜强
Owner TENCENT TECH (SHENZHEN) CO LTD