A word association prompting method, device, equipment and computer storage medium for intelligent input

A technology of intelligent input and words, applied in the computer field, can solve the problems of no semantic association function and low recall rate, and achieve the effect of improving friendliness, good enlightenment and intuition, and improving the recall rate of recommendation.

Active Publication Date: 2020-03-06
郑敏杰
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of low recall rate and no semantic association function of existing search prompts, the purpose of the present invention is to provide a word association prompt method, device, equipment and computer storage medium for intelligent input

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 word association prompting method, device, equipment and computer storage medium for intelligent input
  • A word association prompting method, device, equipment and computer storage medium for intelligent input
  • A word association prompting method, device, equipment and computer storage medium for intelligent input

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Such as Figure 1-7 As shown, the word association prompting method for intelligent input provided in this embodiment may, but is not limited to, include the following steps.

[0066] S101. Acquire a corpus containing a large number of documents.

[0067] In the step S101, the corpus is used to provide a sufficient amount of training corpus for the training process of the LDA topic model, and the training corpus can be provided by the user or constitute various document data collected by existing acquisition software, each A document may, but is not limited to, consist of a part or several fields of title, abstract, keywords, text, attachment title, attachment content, and author information. In addition, the mass of documents is generally more than 10,000 documents, for example, 100,000 documents are selected to form the corpus.

[0068] S102. Perform numerical processing on the word sets of each document in the corpus, and then execute step S1031 and step S1032 sync...

Embodiment 2

[0093] Such as Figure 8As shown, this embodiment provides a hardware device for implementing the word association and prompting method for intelligent input described in Embodiment 1, including an acquisition module, a processing module, a training module, a search module and an output module that are sequentially connected by communication, wherein , the training module includes a Word2Vec model training submodule and an LDA topic model training submodule; the acquisition module is used to obtain a corpus containing a large number of documents; the processing module is used to collect words of each document in the corpus Perform numerical processing; the Word2Vec model training submodule is used to import the numerical processing results as training samples into the Word2Vec model for training, obtain the word vector of each word, and then obtain the set of related words of each word according to the word vector; The LDA topic model training submodule is used to import the n...

Embodiment 3

[0096] Such as Figure 9 As shown, this embodiment provides a hardware device for implementing the word association and prompting method for intelligent input described in Embodiment 1, including a memory and a processor connected by communication, wherein the memory is used to store computer programs, and the The processor is used to execute the computer program to realize the steps of the word association prompting method for intelligent input as described in the first embodiment.

[0097] For the working process, working details and technical effects of the word association prompting device provided in this embodiment, please refer to Embodiment 1, and details will not be repeated here.

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 the technical field of computers, and discloses a word association prompting method and device for intelligent input, equipment and a computer storage medium. Through the invention, a novel method capable of jointly introducing two theories of a Word2Vec model and an LDA theme model into a search intelligent association input engine is introduced, and candidate word recommendation is carried out by using a Word2Vec model and an LDA topic model together; The problem that traditional search input can only predict search candidate words according to one or two previous words can be avoided, the function of intelligent association input prompting is achieved, the candidate words have the semantic association effect, heuristic thinking can be provided for a user, and therefore the recommendation recall rate, the retrieval efficiency and the retrieval accuracy can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a word association prompting method, device, equipment and computer storage medium for intelligent input. Background technique [0002] As the most basic interactive tool of human-computer interaction, the importance of search prompt is self-evident. The working principle of the search prompt is to first transmit the user's input text information to the search server, and the search server engine will calculate the best search prompt word list, and display it to the user through the interface of the search engine for the user to choose and confirm . When the keyword in the current search input box changes, the system recommends the prompt information of the candidate search word that best matches the locale for the user. Whether it can quickly provide users with the correct prompt words, and whether it can gain insight into the user's real search intentions and gi...

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): G06F3/023G06F16/33
Inventor 郑敏杰
Owner 郑敏杰
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap