Intelligent input method and system based on bone conduction vibration and machine learning

Abstract

The invention provides an intelligent input method and system based on bone conduction vibration and machine learning; the intelligent input method comprises the following steps: S1, gathering vibration signals of a user knocking on a hand back; S2, filtering, denoising and end point segmenting the gathered vibration signals; S3, aligning the end point segmented vibration signals; S4, extracting signal features of the aligned vibration signals; S5, using the extracted features to form a training set and sending same to a nerve network classification model for training, thus obtaining a trainednerve network classification model. The method takes the hand back as a vibration keyboard via bone conduction vibrations, and combines with the machine learning nerve network classification model, thus fast inputting texts with a high recognition rate; the method and system are fast in a response speed, can improve the text input efficiency of a wearable device, thus improving the user experiences; the interactive mode is novel, interesting, easy and fast, and wide in applications.

Description

technical field [0001] The present invention relates to an intelligent input method, in particular to an intelligent input method based on bone conduction vibration and machine learning, and to an intelligent input system using the intelligent input method based on bone conduction vibration and machine learning. Background technique [0002] At present, wearable smart sensing devices are developing rapidly, and hand-worn devices such as smart bracelets and smart watches are also quite popular. Users cannot type easily; and the main methods to solve this problem today include: traditional keyboard and speech recognition. Bringing a traditional keyboard will make it not light enough and bulky, and voice recognition is easily affected by the noise of the surrounding environment, and the speed is not fast enough. At the same time, due to the need to protect privacy and take into account the feelings of others, it is not easy to use voice input in public places, and now Although...

AI Technical Summary

Problems solved by technology

[0002] At present, wearable smart sensing devices are developing rapidly, and hand-worn devices such as smart bracelets and smart watches are also quite popular. users cannot easily type; the main solutions to this problem today include: traditional keyboards and voice recognition

Bringing a traditional keyboard will make it not light enough and bulky, and voice recognition is easily affected by the noise of the surrounding environment, and the speed is not fast enough. At the same time, due to the need to protect privacy and take into account the feelings of others, it is not easy to use voice input in public places, and now Although finger tracking and other technologies researched by many scientific research teams can also realize the typing function, but because the operation does not conform to the user's habits and has the defect of slow speed, it cannot solve the problem that the text input is not convenient enough.

Images