| The current medical service is entering the age of big data. Big data promotes the medical model from physician-centric to patient-centered from many aspects such as the production of new knowledge, improving medical quality, individual medical treatment and clinical decision-making. Health care knowledge is the core of the medical industry. Medical health knowledge that the doctor or industry experts have is the foundation to provide medical service to patients. With the rapid development of modern technology and medical science, medical and health service mode has also undergone historic changes. The current medical service model is shifting from the traditional face-to-face artificial service model to intelligent knowledge service model based on the new big data analysis. In this transformation, one of the problems facing the healthcare industry is "how the rapid growth of medical big data turns into computer understandable, available medical knowledge."In view of this situation, this paper presents a semantic knowledge acquisition and personalized intervention program pushing system based on semantic health knowledge.The main research content includes:(1) Combined with specific domain knowledge and application requirement, we construct a healthcare domain ontology construction method.(2) We study the improved rules-based and collaborative filtering-based personalized recommendation model adding ontology, and study the ontology similarity calculation algorithm suitable for the medical health field.(3) To achieve active personalized knowledge recommendation, and integration of Semantic Web technologies and health knowledge base, we realize a personalized health knowledge push system based on semantic rules and case reasoning.In a word, this paper constructs a medical ontology library, and use TDB storage method to improve the access efficiency. For the medical domain ontology, we achieve a personalized medical and health knowledge semantic search, which enables the computer to understand knowledge and inquiry goals better, so as to improve the retrieval precision and recall. That provides the users with more accurate health information inquiry service. We achieve recommendation services in the field of medical and health, namely, personalized exercise prescription recommendation system based on semantic rules and case reasoning. At the same time, we study and verify the recommendation model and similarity algorithm in the medical and health field. |