Chinese pinyin automatic generation method and device oriented to a setting strategy

Abstract

The invention relates to the technical field of pinyin generation, and particularly discloses a Chinese pinyin automatic generation method and device oriented to a setting strategy, and the method comprises the steps of constructing a polyphone phrase dictionary; constructing a universal and counterfeit word dictionary; inputting an article with a set strategy, and matching pinyin for Chinese characters in the article with the set strategy according to the Chinese dictionary; recognizing the polyphone and phrases in the initial file according to the polyphone phrase dictionary, and correcting the pinyin of the polyphone and phrases thereof to generate a first correction file; and identifying the counterfeit characters in the first correction file according to the counterfeit character dictionary, and correcting the pinyin of the counterfeit characters according to the preamble and the postamble of the counterfeit characters to generate a second correction file. According to the invention, the problem of conversion error rate of the polyphone and the kana is solved, the problem of low efficiency of manual auditing and error correction is solved, the content updating and self-learning functions of the polyphone phrase dictionary and the kana dictionary are also realized, the pinyin conversion accuracy is further improved, and the efficiency of manual auditing and error correction is also improved.

Description

technical field [0001] The invention relates to the technical field of pinyin generation, in particular to a strategy-oriented method and device for automatically generating Chinese pinyin. Background technique [0002] In order to popularize the classics of Chinese studies, people set up a column of classics of Chinese studies on the WeChat public account, collect all kinds of classic books of Chinese studies, provide reading and online recitation functions, and put pinyin on each Chinese character in the books. The core problem that needs to be solved is how to accurately convert the Chinese characters in the classics of Chinese studies to pinyin automatically. In view of this problem, the existing technology mainly uses the Chinese Pinyin dictionary to match the corresponding Pinyin, which has the following obvious defects: [0003] 1) When dealing with polyphonic characters, it is easy to make mistakes when converting to pinyin; [0004] 2) When dealing with fake chara...

AI Technical Summary

Problems solved by technology

[0005] In classic books or articles of Chinese studies, polyphonic characters and Tongjia characters are relatively common. Using the existing Chinese pinyin conversion technology will lead to a very high probability of spelling mistakes, which requires manual intervention, but the effect is not ideal:

[0006] 1) The workload of manual error correction is too large, and it is impossible to complete the processing of a large number of classic Chinese studies in a short period of time;

[0007] 2) The efficiency of manual error correction is extremely low, mainly reflected in the low efficiency of "error finding", which needs to be checked one by one

Images