Multi-source text information fusion system and method

The invention relates to the field of data processing, in particular to a multi-source text information fusion system and method.The method includes the steps that the rough set theory is applied to continuity index evaluation, the information similarity is calculated through a text similarity algorithm, weight assignment is conducted on messages according to message source credibility, and the reliability of the messages is improved. Carrying out weighted average on the similarity and integrity of the messages to calculate a comprehensive score of the messages, and fusing the multi-source messages by using a scoring method; the similarity calculation is as follows: sim is a text similarity function, n is the number of information sets, and xi is current information. Compared with the prior art, the method has the advantages that except for a data set, no priori knowledge (or information) is needed, and approximate evaluation of the information credibility is obtained through comprehensive comparison and calc