Digital semantic annotate information processing method for e.g. extraction and prediction of characteristics in sucked resource description framework graphs, involves producing scheme, where relations are predicted on scheme

摘要

The method involves arranging an extracted path to a Boolean characteristic in the form of a tuple, where the tuple as an entry contains semantic resources (R1-R13) at an initial point of the extracted path and as another entry for a path type contains features (P1-P11) according to directed edges (T1, T2) in the path and for other path type contains features according to the directed edges in the path. Machine learning processes are used in the Boolean characteristic, and a prediction scheme is produced, where relations between entities are predicted on the prediction scheme. Independent claims are also included for the following: (1) a device for computer-aided prediction of relations between entities in digital semantic annotate information (2) a computer program product comprising a set of instructions to perform a method for computer-aided processing of digital semantic annotate information.