Supercharge Your Innovation With Domain-Expert AI Agents!

Word group recommendation method and system, storage medium and equipment

A recommendation method and phrase technology, applied in digital data information retrieval, special data processing applications, instruments, etc., can solve problems affecting user input efficiency, unable to recommend phrases, etc.

Pending Publication Date: 2022-03-25
江西软云科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, the purpose of the present invention is to provide a phrase recommendation method, system, storage medium and equipment, which is used to solve the problem that in the prior art, it is impossible to perform targeted phrase recommendation according to different computer window contents, which affects the user's input efficiency. technical issues

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
  • Word group recommendation method and system, storage medium and equipment
  • Word group recommendation method and system, storage medium and equipment
  • Word group recommendation method and system, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] see figure 1 , shows the phrase recommendation method in the first embodiment of the present invention, the method includes steps S101 to S103:

[0042] S101. Obtain the text information of the input text, divide the text information through the pre-trained phrase segmentation model to obtain a phrase set, the phrase set includes multiple text phrases, and identify the page environment of the currently input text according to the text information.

[0043] In this application, for different windows, the content attributes of the current window are obtained by acquiring the text information of different windows, thereby establishing a recommendation basis for the next phrase recommendation, and then segmenting the acquired text information into phrases , to get multiple text phrases, which is convenient for obtaining the text content of the input text in more detail.

[0044] S102. Obtain the letter information currently input, query and obtain the phrase options that m...

Embodiment 2

[0050] Please check figure 2 , shows the phrase recommendation method in the second embodiment of the present invention, the method includes steps S201 to S204:

[0051] S201. Acquire the text information of the input text, divide the text information through the pre-trained phrase segmentation model to obtain a phrase set, the phrase set includes multiple text phrases, and identify the page environment of the currently input text according to the text information.

[0052] As a specific example, when the user enters a phrase word c in a certain window, the system will perform the following calculation: through the stored historical data h of the input content of the window, h is a phrase set {T 1 , T 2 ,...,T n}. For example, if the user has entered "sports special students shine at the sports meeting" in a word, the system will store {"sports", "special talents", "sports meeting", "sports meeting"}.

[0053] Further, please refer to image 3 , step S201 specifically in...

Embodiment 3

[0083] see Figure 5 , showing the phrase recommendation system in the third embodiment of the present invention, the system includes:

[0084] The first obtaining module is used to obtain the text information of the input text, and divide the text information according to the phrase division rule to obtain a phrase set, and the phrase set includes a plurality of text phrases;

[0085] The second obtaining module is used to obtain the letter information currently input, query and obtain the phrase option conforming to the letter information according to the letter information, and the phrase option includes a plurality of pre-phrases;

[0086] The recommendation module is used to calculate the word vector correlation degree of each described pre-phrase group and the text phrase group by the word vector model of pre-training, and the pre-phrase group after the correlation degree calculation is carried out phrase sorting according to the degree of relevance, and the phrase sorti...

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 provides a phrase recommendation method and system, a storage medium and equipment, and the method comprises the steps: obtaining text information of an input text, and segmenting a text information phrase into a plurality of text phrases; obtaining currently input letter information, and querying and obtaining a plurality of pre-phrases conforming to the letter information; the word vector correlation degree of each pre-word group and the text word group is calculated, the pre-word groups after correlation degree calculation are subjected to word group sorting according to the correlation degree, and the pre-word groups after word group sorting are subjected to word group recommendation. According to the phrase recommendation method and system, the storage medium and the equipment, the multiple text phrases are obtained by obtaining and splitting the input text information, association is performed according to the multiple pre-phrases and the multiple text phrases, the word vector association degree of each pre-phrase and the text phrase is calculated, and the phrase recommendation efficiency is improved. And then the pre-phrases subjected to correlation degree calculation are subjected to phrase sorting according to the correlation degree, and the pre-phrases subjected to phrase sorting are subjected to phrase recommendation to obtain a recommendation result, so that the input efficiency of the user is improved.

Description

technical field [0001] The present invention relates to the technical field of phrase recommendation, in particular to a phrase recommendation method, system, storage medium and equipment. Background technique [0002] As there are more and more scenes where users input vocabulary on the terminal, when users input vocabulary on the terminal, they pay more and more attention to the input efficiency when inputting vocabulary. [0003] When inputting vocabulary at the terminal for text editing, it is usually necessary to use a computer input method to realize text input. In order to facilitate the user's input, the terminal may recommend candidate vocabulary when the user inputs the pinyin of the vocabulary, and the user selects the desired input vocabulary from the candidate vocabulary. In the prior art, when inputting different contents in different computer windows, it is generally impossible to perform targeted vocabulary recommendation according to the content of the user...

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): G06F40/284G06F40/289G06F16/335G06N20/00
CPCG06F40/284G06F40/289G06F16/335G06N20/00
Inventor 赵聪单志广黄希理
Owner 江西软云科技股份有限公司
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