Chinese characters input system integrating voice input and hand-written input function

Abstract

The invention discloses a Chinese character inputting system to integrate the voice input and hand-written input function in the applying technical domain of Chinese character inputting method, which comprises the following parts: hand-written / voice input mode, hand-written / voice signal character generating mode, hand-written / voice candidate Chinese character array generating mode, integrating mode, Chinese character identifying and displaying mode, hand-written / voice model exercising mode and hand-written / voice database. The invention improves the identifying rate of Chinese character during hand-written input with voice input as accessory, which accelerates the identifying step without changing the custom of user.

Description

technical field [0001] The invention belongs to the technical field of computer recognition, and is a Chinese character input system integrating voice input and handwriting input functions. The system can improve the recognition rate of input Chinese characters and help consumers more conveniently use mobile phones, computers and other input systems to input Chinese characters. Background technique [0002] With the rapid development of mobile communication technology, the number of mobile phone and computer users is also increasing rapidly, and the input methods applied on mobile phones and computers are also becoming more and more important. Due to the limited number of buttons on mobile phones and computers, it is often time-consuming and laborious to input information on the limited buttons. Usually, it is necessary to continuously search up and down the screen menu to obtain the information you want to input, which makes traditional manual input of text more cumbersome. ...

AI Technical Summary

Problems solved by technology

[0008] (1) The above-mentioned method proposes to distinguish between the first input and the second input, that is, the first input is one of a speech input and a handwriting input, and the second input is the other of the speech input and handwriting input, and it recognizes characters The method is to generate a character string according to the first input, then receive the second input, and extract the recognition character that best matches the second input from the character string generated by the first input according to the second input. Yes: if the first input is handwriting input, the user cannot complete the first input when encountering a word that he cannot write and a character sequence is generated; if the first input is voice input, when the user encounters a word that he cannot read It is also impossible to complete the first input to generate a character string; like this, it is impossible to generate a character string according to the first input, and it is also impossible to extract the most consistent with the second input from the character string generated by the first input according to the second input. Recognizing characters, so that the purpose of correct input cannot be achieved;

[0009] (2) The handwriting / speech model trainer that above-mentioned method proposes just works under the training pattern, promptly before using this system, it is specially trained in advance by the user, so just can reach setting up personal handwriting / speech model and be stored in handwriting The purpose in the / voice database, and in the process of use, the handwriting / voice database remains unchanged. This static training method is relatively simple, and it does not conform to the user's usage habits

Images