Automatic detection and analysis of DPP entities in legal contract documents

Due to introduction of General Data Protection Regulation (GDPR) in EU; all the cloud hosted applications (span across multi geo location) wherein captures the personal data need to first identify data privacy protection (DPP) entities and handle it as per EU norms and regulations. The company's legal contracts or transactions in tie up with other parties (customers, partners, suppliers, etc.) are usually stored in to repository; on termination of the contracts either by agreement or mutual consent then the other parties' information are usually archived for historical reasons. The other parties are usually interested in knowing what all documents or transactions they were participated earlier and expects the data to be pruned on need basis. As these documents are unstructured in nature, this paper proposes a solution in identifying all DPP entities with in legal contract documents, index the corpus level accumulated knowledgebase, apply customized ranking algorithm for the retrieved legal contract documents based on DPP search query, derive DPP entities specific legal contract document dependency relation graph for which the parties are participating by using techniques from Information Retrieval, Information Extraction, Natural Language Processing (NLP) and Ontology.