Untouched technology big data analysis is a product of targeted collection of network information, which can collect and update website data set by users, achieve flexible network data collection goals, and provide a basis for Internet data analysis. Text mining tool refers to the computer processing technology to extract valuable information and knowledge from text data, including text classification, text clustering, information extraction, entity recognition, keyword indexing, abstract and so on. The text mining software based on Hadoop MapReduce can realize the mining and analysis of massive texts. An important application field of CKM is intelligent comparison, which is widely used in patent novelty retrieval, scientific novelty retrieval, document duplicate retrieval, copyright protection, manuscript traceability and other fields.