Phase level forecast inputting method based on personal corpus

Abstract

The invention provides a phase level forecast inputting method based on a personal corpus, comprising the following steps: collecting previous input of a user as the personal corpus; performing word segmentation on the previous input of the user by taking a sentence as a unit, and segmenting into characters and words having independent meanings; calculating the occurrence frequency of words or phases formed by words before and after, and calculating the conditional probability of the words or the phases occurring next to the previous words to form a probability file reflecting the unique language habit of the user; and forecasting the subsequent words, phrase or sentences expected to be input by the user after the words or the phrases at the beginning are input according to the probability file when the user input subsequently so as to facilitate selection and rapid input for the user. Therefore, the subsequent possible candidate words, phrases or sentences can be obtained when the user only inputs the beginnings of characters or words according to the probability file, thus improving input efficiency.

Description

technical field [0001] The present invention relates to a method for predicting input, and more specifically, relates to a method for performing phrase-level predictive input based on a personal corpus. Background technique [0002] Since there is no division between words in Chinese written sentences (different from English input, words are separated by spaces) and there is no clear definition of Chinese word division, so the earliest Chinese input method is to input with a single Chinese character. [0003] Most of the existing input methods can input words, but need to key in the corresponding pinyin or strokes, and then the input method prompts out corresponding alternative words or words for the user to choose. The problem that brings thereby is, when carrying out Chinese character word input, needs to key in too much information, and does not possess the associative function between words or phrases. [0004] Even if there are some improved input methods that have the...

AI Technical Summary

Problems solved by technology

[0006] 2. Some input methods support the association of idioms or idioms, that is, after the user enters the first few characters of an idiom or idiom, the input method can provide the complete idiom or idiom as a candidate for the user, but this type of input The idiom or idiom library provided by the law can only be a common language habit of all users, and there are problems such as small idiom or idiom library vocabulary, poor flexibility, and difficult to expand

[0007] 3. Some input methods support the function of caching and matching the complete sentences entered by the user in the past, that is, to record a certain number of complete sentences entered by the user in the past. When the user enters the first few words of the sentence again, the input method can save The complete historical sentence is provided to the user as a candidate, but this type of input method is only a cache of the user's personal input history, and there is also the problem of poor flexibility

[0008] 4. From the above description, it can be seen that the existing technology can only provide a language habit (or input habit) common to all users or a cache of personal input history, rather than a unique input habit of the user.

Images