Method for calculating semantic similarities between messages and conversations based on enhanced entity extraction

摘要

One embodiment of the present invention provides a system for estimating a similarity level between documents. During operation, the system receives (202) a number of documents, extracts (302) a number of semantic entities from the documents, calculates (306) the similarity level between the documents based on the extracted semantic entities, and produces (320) a result indicating similar documents based on the calculated similarity level.