首页>
外国专利>
MISSING LABEL CLASSIFICATION AND ANOMALY DETECTION FOR SPARSELY POPULATED MANUFACTURING KNOWLEDGE GRAPHS
MISSING LABEL CLASSIFICATION AND ANOMALY DETECTION FOR SPARSELY POPULATED MANUFACTURING KNOWLEDGE GRAPHS
展开▼
机译：稀疏型制造知识图的标签分类和异常检测
展开▼
页面导航
摘要
著录项
相似文献
摘要
Systems, methods, and computer-readable media are described for identifying missing or mislabeled information in a manufacturing knowledge graph. Example embodiments address the technical challenge of sparsity of information in the manufacturing domain by using a collection of prior stored manufacturing knowledge graphs to learn latent representations present within the stored graphs through localized traversals of the stored graphs using a graph traversal technique such as a random walk traversal. The latent representations of the stored manufacturing knowledge graphs correspond to an encoding of the stored manufacturing knowledge graphs as a collection of encoded manufacturing knowledge graphs, which are compared to an encoded new manufacturing knowledge graph to identify a stored manufacturing knowledge graph that is most structurally similar to the new manufacturing knowledge graph. This most similar manufacturing knowledge graph can then be used to identify missing or mislabeled information in the new manufacturing knowledge graph.
展开▼
