Dictionary learning method, and devcie for using same, input method and user terminal device for using same

Abstract

The method includes steps: model of learning thesaurus and statistical language from word data not labeled; integrating model of thesaurus, statistical language, and coding information of assistant word into dictionary in small size. Moreover, the invention also discloses an input method in use for user terminal device, and a kind of user terminal device. A dictionary with information of part of speech and dual model of part of speech is loaded to the terminal device. Thus, the user terminal device can give prediction of sentence and word. Using Patricia tree index in dictionary index searches dictionary so as to speed up inputting.

Description

technical field [0001] The present invention relates to a natural language processing, and more specifically, to a dictionary learning method and a device using the dictionary learning method, an input method and a user terminal device using the input method. Background technique [0002] With the widespread use of computers, PDAs, and mobile phones in China, it can be seen that an important feature of these devices is the ability to enable users to input Chinese. In China's current mobile terminal market, almost every mobile phone provides an input method using a numeric keypad. Currently the most widely used input methods are T9 and iTap. With this input method, the user can use the ten-key numeric keypad to input pinyin or strokes of Chinese characters. 8A-8B illustrate example keyboards for pinyin and stroke input. The input method gives predictions of Chinese characters according to the sequence of keys tapped by the user. When the user inputs the pinyin of a Chines...

AI Technical Summary

Problems solved by technology

However, this SLM uses a predetermined dictionary and stores a large number of word bigrams and word triplets in the dictionary, and the size of the dictionary will inevitably be too large to be installed on a mobile terminal.

In addition, the prediction speed on the mobile terminal platform is also very slow

[0008] Another disadvantage is that most input methods do not have dictionaries or only include predefined dictionaries

Therefore, it is not possible to continuously input multiple important words and phrases frequently used in the language, such as "this afternoon"

Images