Method and system for generating a voice recognition data bank for a mobile device, with the use of an image processing and optical character recognition

摘要

It is a method and a system for controlling a mobile device (120) of a head unit (100) of using a voice control. The head unit receives a graphic representation of a current user section points image screen (122, 222, 262) of the mobile device. The scanning head unit then reads the graphical representation of the current user section points image screen, the locations of potential input devices (124, 126, 128, 130, 224, 226, 228, 230, 232, 234, 264, 266, 268, 270, 272, 274) to determine. The potential input devices, with the use of an optical character recognition scanned and voice commands for the input devices are determined. The determined voice commands and their respective locations at the user section represent picture screens, in a speech recognition data bank (316) is stored, which is expressed by means of speech commands is interrogated during a speech recognition.