多算法协同的医疗器械产品竞争情报知识库构建方法研究

Research on Construction Method of Medical Device Product Competitive Intelligence Knowledge Graph Based on Multi-algorithm Collaboration

医疗器械产品的复杂性以及医疗行业的特殊性,使得医疗器械产品竞争情报对医学领域知识的相关性以及情报的实效性有较高要求。因此,研究构建融合领域知识的医疗器械产品知识图谱并使构建过程实现智能化对于医疗器械产品竞争情报研究具有重要的意义。在充分分析产品竞争情报数据源特点及领域知识的基础上,提出一种多算法协同的知识图谱构建模型,模型算法模块应用Bilstm、Metamap、BM25算法等实现中英文数据筛选、实体识别、关系识别、知识融合、图谱构建的关键任务,并具备自动化情报感知扩展功能。最后以软组织扩张器类产品为例,构建了该产品的知识图谱,证明多方法协同的知识图谱构建方法能够实现多源数据融合和情报感知,是对智慧情报建设的有益尝试。

The complexity of medical device products and the particularity of the medical industry make the competitive intelligence of medical device products have high requirements on the relevance of medical knowledge and the effectiveness of intelligence.Therefore,it is of great significance to study the construction of medical device product knowledge graph that integrates domain knowledge and to make the construction process intelligent.On the basis of fully analyzing the characteristics of product competitiveness information data sources and domain knowledge,this paper proposes a multi-collaborative knowledge graph model,which using adgorithm of Bilstm,Metagraph,BM25,etc.to realize key tasks such as Chinese and English data filtering,entity and relationship recognition,knowledge fusion,knowledge graph construction and perception.Finally,the paper takes soft tissue expander products as an example,and builds its knowledge graph.The experiment proves that the multi-method collaborative knowledge graph construction method can realize multisource data fusion and intelligence perception,which is a beneficial attempt for smart intelligence construction.