上海科技大学知识管理系统

随着制造系统的发展，系统构成日趋复杂， 数据信息的统一管理面临挑战：数据内容缺失、更新缓慢、指称不一致等问题导致信息覆盖、信息偏差。为应对挑战，首先，定义了智能制造背景下的知识图谱管理范式；随后，提出了针对多源异构数据的自顶而下与自底而上结合构建领域知识图谱的方法，利用自然语言处理技术抽取实体并实现多源异构数据的规范化与标准化；接着，通过实例结合大语言模型展示数据处理、图谱构建与信息查询的结果；最后，探讨了基于知识图谱进一步提升管理智能化的方向。

With the development of manufacturing system, its composition is becoming more and more complex, and the unified management of data and is facing challenges: the phenomena of data missing, slow updating and unclear relationships lead to the problems of information coverage and information bias. To cope with the challenges, a knowledge graph (KG) management paradigm in the context of smart manufacturing is firstly defined. Then, a top-down and bottom-up approach is proposed to construct the domain KG for multi-source heterogeneous data, using natural language processing (NLP) technologies to extract entities and achieve normalization and standardization of data. After that, the results of data processing, graph construction and information query combined with a large language model are demonstrated through examples. Finally, the directions of further improving management intelligence based on KG are discussed.