A candidate word list generation method and device
A candidate word and word segmentation technology, applied in the field of input method, can solve problems such as low input efficiency, difficulty in recommending new words and hot words to users, and achieve the effect of improving input efficiency and input experience
Pending Publication Date: 2019-05-10
BEIJING KINGSOFT INTERNET SECURITY SOFTWARE CO LTD
View PDF8 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] For this reason, the first object of the present invention is to propose a method for generating a candidate word list, which is used to solve the problem that the input method application in the prior art is difficult to recommend new words and hot words to users, resulting in low input efficiency
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0067] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.
[0068] The method and device for generating a candidate word list in the embodiments of the present invention are described below with reference to the accompanying drawings.
[0069] figure 1 It is a schematic flowchart of a method for generating a candidate word list provided by an embodiment of the present invention. like figure 1 As shown, the candidate word list generation method includes the following steps:
[0070] S101. Obtain the text input in the input box.
[0071] The subject of execution of the candidate word li...
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
Login to View More Abstract
The invention provides a candidate word list generation method and device. The method comprises the steps of obtaining an input text in an input box; performing word segmentation on the text to obtainthe last segmented word; inquiring a hot search lexicon according to the segmented words, and judging whether target hot search entries matched with the segmented words exist or not; if the target hot search entry exists, obtaining a target word behind the segmented word in the target hot search entry; adding the target word to a preset position in a candidate word list corresponding to the text,according to the method and the device, the processed candidate word list is obtained after the input method application is input, so that hot words or hot search entries in a short time period appear in the candidate word list, more reasonable candidate words are provided for a user, the input efficiency of the input method application is improved, and the input experience of the user using theinput method application is improved.
Description
technical field [0001] The invention relates to the technical field of input methods, in particular to a method and device for generating a candidate word list. Background technique [0002] In the current input method application, the generation process of the candidate word list is to obtain the text in the input box, input the text into the N-gram model, obtain the candidate words that may appear after the text, and the occurrence probability of each candidate word; Occurrence probability, generate a list of candidate words. Among them, the N-gram model is generated based on the word segmentation lexicon and training data for a long period of time before the current moment. For a long period of time, such as 3 months, 6 months, 1 year, etc., while hot words in a short period of time Or the weight of popular search terms in the word segmentation thesaurus is very low, resulting in the short-term hot words or hot search terms generally not appearing in the candidate word l...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F3/023G06F17/27
Inventor 王培娜
Owner BEIJING KINGSOFT INTERNET SECURITY SOFTWARE CO LTD