A METHOD A DEVICE AN ELECTRONIC EQUIPMENT AND A STORAGE MEDIUM FOR DETERMINING RECOGNIZED TEXT WHICH IS DISPLAYED ON A DISPLAY DEVICE

摘要

An embodiment of the present invention discloses a method, apparatus, device, and storage medium for determining recognized text displayed on a display device, and relates to artificial intelligence technology fields such as speech recognition and natural language processing. The method includes the steps of: determining, according to the collected user recorded data stream, a data stream to be recognized; performing local recognition on the data stream to be recognized to obtain offline recognition text; performing online recognition on the data stream to be recognized to obtain online recognition text; and determining, from the online recognition text and the offline recognition text, a recognition text more suitable for characterizing a user's intention, as a recognition text displayed on a display device, based on the comparison result of the online recognition text and the offline recognition text. And by using the parallel method of offline recognition, not only the speed of offline recognition, but also the accuracy of online recognition, it is possible to not only solve the problem of the recognition text being displayed late on the screen, but also ensure the recognition effect.