Construction And Application Of Medical Nursing Knowledge Graph

With the development of society and the improvement of living standards,people’s attention to nursing knowledge such as breast disease prevention and treatment,breastfeeding,and lactation has significantly increased,and the demand for nursing is also increasing year by year.However,in many cities,the educational level of medical and nursing staff is uneven,and they lack basic medical and nursing knowledge.Moreover,medical and nursing domain knowledge is highly professional,complex,and has a large amount of data.Existing nursing knowledge has problems such as single expression form,weak knowledge relevance,and can no longer meet the needs.Therefore,How to visualize nursing knowledge and accurately understand users’ intentions has become an urgent and in-depth issue to be addressed.Knowledge graph has made outstanding achievements in structured expression in multiple fields.Compared to traditional nursing knowledge Q&A systems,knowledge graph can display the core structure and semantic relationships of medical nursing knowledge in a more comprehensive visual form,providing an excellent solution for medical nursing Q&A.Aiming at the problem of large amount of medical nursing data and high accuracy requirements,combined with the data set support and guidance of relevant hospitals and chief physicians,this paper carried out the research on the construction and application of the medical and nursing knowledge map.The main contents are as follows:Firstly,a medical nursing entity relationship joint extraction method based on convolutional neural networks is proposed.This method is based on the traditional convolutional neural network as the network structure.By embedding a medical relationship corpus into the model and designing a segmented maximum pooling strategy,it effectively reduces the loss of some key medical entity features.Compared with the LSTM model,convolutional neural networks are more effective in processing local features and have strong generalization ability.The experiment shows that the method used for entity relationship extraction improves the accuracy of disease classification in the model.Second,the knowledge map of medical nursing was constructed.Through the acquisition of nursing data sets,knowledge extraction,knowledge fusion and reasoning,the accuracy of knowledge mapping can be significantly improved.This knowledge graph efficiently integrates data from different sources and types,and sorts out the complex semantic relationships between nursing data.After use,it can effectively provide services for nursing workers and patients.Thirdly,the development of a question and answer system based on medical nursing knowledge graph has been completed.The system is developed based on the nursing knowledge map,which realizes the question answering of nursing related knowledge,and can identify the user’s question intention according to the question answering model algorithm,update the knowledge base according to the user’s feedback information and other functions.Tested and used by relevant hospitals,the overall effect is good,with effective use value and promotion value.