Chinese integral sentence generation method and device

Abstract

The present invention discloses a Chinese complete sentence generating method and device. The method of the present invention includes: a candidate word generated the last time and a candidate in a pinyin string are obtained; a candidate directed graph is constructed and a candidate with a biggest conditional probability is selected which corresponds with the candidate generated the previous time from candidates which correspond with the initial arc of the directed graph. Based on the candidate with the biggest conditional probability, a complete sentence result of the pinyin string is obtained. The embodiment of the present invention also provides a corresponding device. When computing probability of the candidate which corresponds with the initial arc of the candidate word directed graph, the embodiment of the present invention applies word frequency of the candidate combination and of the candidate word generated the previous time, that is, applies the context information to generalize a complete sentence, thus improving the complete sentence generating accuracy and the candidate word generating accuracy.

Description

technical field [0001] The invention relates to a Chinese input technology, in particular to a method and a device for generating a complete Chinese sentence. Background technique [0002] At present, most Chinese input software has the function of generating complete sentences. For example, if a user wants to input "People's Republic of China", then the user only needs to continuously input the pinyin string "zhonghuarenmingongheguo" in the input method software to get the correct complete sentence Generate results, see Figure 1. Please refer to Fig. 2, the flow chart of the Chinese whole sentence generation method provided by the prior art, including: [0003] Step 201: divide the pinyin string into syllables; [0004] Step 202: According to the result of syllable division, look up all the candidate words that appear in the pinyin string in the pinyin dictionary, and build a directed graph of candidate words, each arc of the directed graph corresponds to one or several c...

AI Technical Summary

Problems solved by technology

[0015] The defect of the prior art is: since the prior art only considers the candidate words with the highest word frequency when generating the entire sentence, when the user enters the entire sentence multiple times, the accuracy of the entire sentence generation result displayed in the first place of the candidate word window will Not high, the user needs to perform multiple selection operations to get the correct sentence generation result, which affects the user's input speed

Images