A Clustering Algorithm for Health Care Big Data Governance System

In order to optimize the cause of people's health and improve the quality of people's healthcare. Aiming at the current problem of health care big data governance, the author designs a medical information system information security detection method supported by improved K-means clustering algorithm, by conducting research and understanding more than 12 million pieces of health and medical big data from more than 10 medical institutions in S city, A province, and analyzing the diversity, multi-source, and heterogeneity of these data, consolidate and summarize into the same database, make preliminary preparations for data governance, establish a unified data storage mode, and convert wrong data, according to the unified encoding and matching of various heterogeneous data optimization standards, the data structure is stored in the Hive database, after simulation experiments, it is shown that: The detection method designed by the author generates a delay of around 0.1 seconds, which is compared to the other two detection methods, the security detection method designed by the author generates a shorter delay time, and the actual detection process requires the shortest detection time. Based on the above experimental results, it can be concluded that the detection method designed by the author has the highest actual detection rate, the lowest false alarm rate value, and the least actual detection delay time, making it suitable for use in the actual detection process. It has realized the special feature engineering of medical big data, solved the integration and fusion of multi-source heterogeneous data, improved the efficiency of information matching, and realized the multi regional data governance project of medical data quality management.