Construction of an Industrial Knowledge Graph for Unstructured Chinese Text Learning

Abstract

The industrial 4.0 era is the fourth industrial revolution and is characterized by network penetration; therefore, traditional manufacturing and value creation will undergo revolutionary changes. Artificial intelligence will drive the next industrial technology revolution, and knowledge graphs comprise the main foundation of this revolution. The intellectualization of industrial information is an important part of industry 4.0, and we can efficiently integrate multisource heterogeneous industrial data and realize the intellectualization of information through the powerful semantic association of knowledge graphs. Knowledge graphs have been increasingly applied in the fields of deep learning, social network, intelligent control and other artificial intelligence areas. The objective of this present study is to combine traditional NLP (natural language processing) and deep learning methods to automatically extract triples from large unstructured Chinese text and construct an industrial knowledge graph in the automobile field.

Information Fusion for Multi-Source Material Data: Progress and Challenges

“…Material industries need to obtain knowledge from a large amount of data, and the fusion of multi-source heterogeneous material data becomes an important prerequisite for further data mining and knowledge discovery. New computer technologies such as machine learning [76], data cubes [77], and knowledge graphs [78] can be used to help the development of new materials and improvements in existing material-making processes, has had a significant impact on the advancement of the materials industry. Some applications as phase mapper [79] help scientists filter worthless material structures in the research of new materials, which has greatly accelerated the research and development of new materials.…”

A Text-Generated Method to Joint Extraction of Entities and Relations

“…During training, given a batch of data with B sentences S = {s 1 , s 2 , ... , s b } with their corresponding target sequences Y = {y 1 , y 2 , ... , y b }, where y i = {w 1 i , w 2 i , ... , w T i } is the reference of i-th sentence. The loss function is defined as follows:…”

“…Entity-relation extraction is the core task and important segment in the fields of information extraction, knowledge graph, natural language understanding, etc. In recent years, knowledge graph [1] has been widely applied. Many achievements have also been made in the downstream tasks such as question answering and retrieval based on knowledge graph.…”

“…Therefore, it is necessary to extract overlapping relations from the perspective of practical application scenarios. The overlapping multi-relation extraction problem is more complex than single-relation extraction because the single-relation extraction scenario can be basically divided into the following two types: (1) for sentences with the given entity pairs, relation classification can be modeled as a text classification problem; (2) for sentences with non-annotated target entity pairs, the model assumes that sentence contains only one pair of entities and relation classification is performed after entity recognition; these two cases usually use the softmax function in the relation classification phrase, so only one relation can be extracted. In the multi-relation extraction situation, we need to find every complete relational triple.…”

Special Issue on New Industry 4.0 Advances in Industrial IoT and Visual Computing for Manufacturing Processes

“…deep learning) techniques A special mention should be given to the algorithmic contributions on inline inspection of warm-die forged revolution workpieces using 3D reconstruction (car component case), since it approaches some novel concepts with industrial impact in computational geometry [20], and to the new self-calibration approach of elliptic paraboloid arrays frequently used in precision measurement [21]. A contribution on how to build knowledge graphs for industrial terminology in the automotive sector is presented in [22].…”