MULTISOURCE MAIN-SUBSIDIARY ENTITY IDENTITY DISCRIMINATION AND DATA SELF-SUPPLEMENTATION PROCESSING METHOD

The invention discloses a multi-source primary and secondary entity identity discrimination and data self-complementing processing method, which is applied to the field of big data processing, and proposes that multi-source data entities are stripped according to primary and secondary entities, the same entity is discriminated according to the same scene, entity attribute classification, weight and the like, and discrimination probabilities are respectively processed and stored. According to the method, the identity probability calculation of the main entity and the affiliated entity, the index supplementation and data merging of the same entity, the entity directory item extraction and storage, the entity sub-directory item separation and other technical methods are adopted; the problems of respective processing and collection of main and auxiliary entities according to the identity probability, cross-source entity combination and data supplementation, unified storage of entity relationships, separation of entities as required and the like are systematically solved, and a feasible solution is provided for multi-source and large-scale data association operation.