The invention discloses a method for constructing a traffic knowledge graph based on multi-source data fusion, and the method comprises the steps: obtaining traffic image modal data based on traffic image big data, obtaining traffic text modal data based on road network data, carrying out the entity definition according to the traffic image modal data and the traffic text modal data, and carrying out the construction of the traffic knowledge graph based on multi-source data fusion. The relationship between the entity attributes and the entities is matched to obtain a knowledge graph data layer; and performing classification processing on the knowledge graph data layer according to a vertical domain knowledge graph to obtain structured data and semi-structured data, and establishing a traffic knowledge graph according to the structured data and the semi-structured data. The problems that due to the fact that traffic data sources are diverse, storage modes and data formats are different, unified storage and utilization are difficult, data processing, data fusion and other operations are carried out on super-large-scale multi-mode heterogeneous graph data, the model migration efficiency between different cities is reduced, and the traffic data migration efficiency is high are solved. And the burden of data modeling is increased.
本发明公开了一种基于多源数据融合的交通知识图谱的构建方法,包括基于交通图像大数据获取交通图像模态数据,基于路网数据获取交通文本模态数据,根据交通图像模态数据与交通文本模态数据进行实体定义,并匹配实体属性与实体间的关系获取知识图谱数据层;根据垂直领域知识图谱对所述知识图谱数据层进行分类处理获取结构化数据和半结构化数据,并根据所述结构化数据和半结构化数据建立交通知识图谱。以克服由于交通数据来源多种多样,存储方式以及数据格式都不同,难以进行统一的存储和利用,面对超大规模多模态异构图数据,进行数据处理与数据融合等操作,导致不同城市之间的模型迁移效率降低,进而增加了数据建模的负担的问题。
Construction method of traffic knowledge graph based on multi-source data fusion
一种基于多源数据融合的交通知识图谱的构建方法
16.05.2023
Patent
Elektronische Ressource
Chinesisch
Holographic traffic state data set construction method based on multi-source information fusion
Europäisches Patentamt | 2023
|Multi-source traffic data fusion method based on PSO-BP fusion algorithm
Europäisches Patentamt | 2024
|