Word entry retrieval and wrong word detection methods and systems for pinyin input method

Abstract

The invention discloses word entry retrieval and wrong word detection methods and systems for a pinyin input method. The retrieval method comprises the steps of detecting whether a reference word entry exists before or after a currently input pinyin string; if the front or back reference word entry exists, performing matching in a word bank according to the front or back reference word entry and the current input pinyin string to obtain at least one back or front word entry; and if no reference word entry exists before or after the pinyin string, performing matching in the word bank according to the current pinyin string to obtain corresponding word entries or a word entry list. The wrong word detection method comprises the steps of obtaining at least one front or back word entry according to the reference word entry of the pinyin string currently input by a user; constructing a word graph; performing forward and reverse comparison, wrong key processing or wrong sequence processing; and judging whether the processed pinyin string meets a pinyin rule or not, and if yes, returning the word entry corresponding to the word graph to the user. According to the methods and systems, the word entry recommendation accuracy and the user input correction capability in the input method are improved.

Description

technical field [0001] The invention relates to a digital processing technology of keyboard input, in particular to a method and system for entry retrieval and wrong word detection of pinyin input method. Background technique [0002] Chinese is a language with a large proportion of usage in the Internet world. A series of Pinyin input methods represented by Sogou input method have quickly occupied the Chinese input method market. These input methods have a certain ability to discriminate wrong words entered by users, but their performance in some situations is not very satisfactory. [0003] Take the Sogou input method as an example. When the pinyin input by the user is wrong (the letters in the pinyin are wrongly written or the letters are out of order), for example, the user wants to spell apple (pingguo) but it is spelled as pungguo, the method of the Sogou input method is to take out the pinyin characters The initial consonants p and g in the string, and then find the ...

AI Technical Summary

Problems solved by technology

[0005] 2. The existing technology cannot obtain the entry that the user really wants to obtain in connection with the context, but only uses the pinyin input by the user to find the entry by using the hot word thesaurus

For example, if the user has never entered "health and lightness", the user actually enters jiankangyishneqing, even if the initials are not misspelled, the existing technology cannot detect the word the user originally wanted, and the result is "how about a healthy doctor?"

Images