Research On Automatic Recognition Method Of Mongolian Code

With the rapid development of computer technology and network technology, the Mongolian information processing work has made great progress. But due to the relative lag of Mongolian international standard code promulgated, at present,the various software vendors in the market to take their own coding standard, make the various Mongolian information and website can not be compatible, the information can not be shared, which seriously affected the development of Mongolian information processing work. Mongolian code will therefore be different manufacturers into a unified coding standard has become an important work.For different code identification is identification work for the uncertain coding type of case, the preliminary work which belongs to the code conversion,is the basis for the next code conversion work.This paper focuses on the Zhineng, Mengkeli and Mingantu, three kinds of coding rules were analyzed by two methods to do the coding recognition. One method is based on the Mongolian letter belongs to the range and is represented in a different location words font and encoding different to do identification; another is the Mongolian characters recognition process using a Mongolian word to Latino syllable as.In the research process of concrete, respectively to Mongolia three kinds of coding’s range, three kinds of Mongolian code words’position in the word, the word, at the end of the term words and the independent form to do an in-depth study and make a preliminary division. In addition, in-depth study of the Mongolian transliteration rules and three kinds of Mongolian letter do Latin work. The article also points of Mongolian syllable theory done in-depth research, under the rules of the points of syllables, draw the Mongolian word syllabify divided flow chart, and according to the flow chart of three kinds of Mongolian code’s Latin form,do syllabify recognition work.