Head word extraction method and device, computer equipment and storage medium

An extraction method and a technology of central words, which are applied in the field of information processing, can solve problems that are not suitable for large-scale network applications, time-consuming and labor-intensive, etc.

Pending Publication Date: 2022-06-24
GUANGZHOU LIZHI NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Need to manually mark the training set, which is time-consuming and

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
  • Head word extraction method and device, computer equipment and storage medium
  • Head word extraction method and device, computer equipment and storage medium
  • Head word extraction method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] figure 1 A flowchart of a method for extracting a central word provided in Embodiment 1 of the present invention, the method can be performed by a central word extraction device, and the central word extraction device can be implemented by software and / or hardware, and can be configured in computer equipment, For example, servers, PCs, smartphones, smart watches, etc. The method for extracting the central word can be applied to a voice query scene, and the method for extracting the central word specifically includes the following steps:

[0076] Step 101: Obtain the query text input by the user, the click behavior data of the query result corresponding to the query text by the user, and the text data of the sound clicked by the user.

[0077] In the sound data retrieval scenario, when the user enters the retrieval content in the retrieval column, clicks the query button, and clicks to select the corresponding sound content according to the content displayed in the quer...

Embodiment 2

[0121] figure 2 A schematic structural diagram of a central word extraction device provided in Embodiment 2 of the present invention, the central word extraction device may specifically include the following modules:

[0122] The obtaining module 201 is used for obtaining the query text input by the user, the click behavior data of the query result corresponding to the query text by the user, and the text data of the sound clicked by the user;

[0123] The query node data generation module 202 is configured to, according to the query text, click on the text data of behavior data and voice to generate query node data;

[0124] The target word segmentation determination module 203 is used to perform word segmentation processing on the query text, and determine the target word segmentation of the query text according to the obtained word segmentation;

[0125] The word vector generation module 204 is used to input the target word segmentation into a word vector generation model...

Embodiment 3

[0140] image 3 This is a schematic structural diagram of a computer device according to Embodiment 3 of the present invention. image 3 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. image 3 The computer device 12 shown is only an example, and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0141] like image 3 As shown, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16 , system memory 28 , and a bus 18 connecting various system components including system memory 28 and processing unit 16 .

[0142] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus ...

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 relates to a head word extraction method and device, computer equipment and a storage medium. In the embodiment of the invention, word segmentation processing is performed on a query text to determine target segmented words; identifying a query intention according to the query text; determining the weight of the target segmented word in the corresponding intention category based on the occurrence frequency of the target segmented word in all the query texts of the corresponding intention category, the number of all the query texts of the corresponding intention category and the occurrence frequency of the target segmented word in all the query texts; performing weighted summation on the word vectors corresponding to all the target segmented words in the query text to obtain vector representation of the query text; performing part-of-speech tagging processing on the target segmented word to determine a candidate head word; and extracting the head word based on the cosine similarity represented by the word vector of the candidate head word and the vector of the query text. The extraction effect of the query head word is improved, the cold start problem of the head word is solved, and meanwhile the Mortai effect of the head word is weakened.

Description

technical field [0001] The present invention relates to the technical field of information processing, and in particular, to a central word extraction method, device, computer equipment and storage medium. Background technique [0002] With the development of computer technology and the wide application of query engines, users have higher and higher requirements for query accuracy. In order to improve the query accuracy, when querying according to the sentence input by the user, the central word that can accurately express the meaning of the sentence can be extracted from the sentence, and the query according to the central word can avoid the problem of fewer query results caused by querying according to the sentence . [0003] Related technologies are based on topic model (Topic Model), based on supervised learning. Among them, the topic model (Topic Model) is a statistical model for clustering the implicit semantic structure of documents in an unsupervised learning manne...

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): G06F16/332G06F16/35G06F40/284G06F40/289G06F40/216
CPCG06F16/3322G06F16/35G06F40/284G06F40/289G06F40/216
Inventor 谭又伟丁宁
Owner GUANGZHOU LIZHI NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products