APPARATUS OF INTERPRETING COMMUNICATIONS MESSAGE BASED ON RECURRENT NEURAL NETWORK AND BRANCH PREDICTION AND METHOD THEREOF

摘要

According to an embodiment of the present invention, a method of interpreting a communications message comprises the following steps of: receiving a stream including a plurality of input characters included in a transmitted communications message; calculating a first prediction result which is a result predicted according to a first character of the stream; comparing the calculated first prediction result with a second character of the stream; calculating a second prediction result branched from a point where the calculated first prediction result and the second character are not the same, if the calculated first prediction result and the second character are not the same, based on a comparison result with the first prediction result, and storing the first prediction result as a first stack; comparing the calculated second prediction result with the second character; and calculating a third prediction result branched from a point where the calculated second prediction result and the second character are not the same, if the calculated second prediction result and the second character are not the same, based on a comparison result with the second prediction result, and storing the second prediction result as a second stack.;COPYRIGHT KIPO 2020