Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm

Abstract

Many electrical equipment malfunction text messages are collected during power system operation and maintenance procedures. These texts usually contain crucial information for maintenance and condition monitoring. Because these power system malfunction texts are characterized by multidomain vocabularies, complex-syntactic structures, and long sentences, it is challenging to for automated systems to capture their semantic meaning and essential information. To address this issue, we propose a hybrid natural language processing (hybrid-NLP) algorithm to extract entities that represent electrical equipment. This algorithm is composed of a dictionary-based method, a language technology platform (LTP) tool, and the bidirectional encoder representations from a transformers-conditional random field (BERT-CRF) model. Significantly, the softmax output layer of the bidirectional encoder representations from the transformers (BERT) model is replaced by the conditional random field (CRF) algorithm to strengthen the contextual relationships between words and thus solve the local optimization of the preferred word label. The effectiveness of the proposed hybrid-NLP method is verified on a realistic dataset. Moreover, a statistical analysis is conducted to provide a reference for the operation and maintenance of power systems. INDEX TERMS electrical equipment malfunction text, natural language processing, entity extraction, BERT-CRF model.

Text Classification Based on Machine Learning and Natural Language Processing Algorithms

“…To verify the effectiveness of our method, we use and conduct experiments on two benchmark datasets: TREC2007 (TR07) and Enron-spam (ES) [19,20]. It contains spam and legitimate mail as shown in Table 1.…”

Construction of Mental Health Knowledge Service Model Based on Online Medical Community

“…The traditional online medical community simply achieves simple keyword link matching. Psychological Q & A personalized recommendation is based on the ontology knowledge base of patient and psychological expert question and answer for query and retrieval [ 29 , 30 ], and using Protégé-OWL Extension Tool Semantic Web Rule Language SWRL Reasoning Rules provides psychological illness guidance and personalized knowledge services. It can recommend the prevention and treatment of mental illness and meet the needs of individualized guidance of mental health.…”

Multi-Feature Extraction Method of Power Customer’s Portrait based on Knowledge Map and Label Extraction

“…Therefore, the determination of vocabulary weight is very important for the extraction of multiple features of the sensitive customer's portrait in power grid. Statistical knowledge is used to determine the vocabulary weights that have been transformed into vectors in the text of sensitive customer's portrait labels in power grid, that is, the vocabulary weights are determined according to the text statistical information such as word frequency [15]. The above statistical process is based on Shannon's informatics theory: assuming that a certain word in all texts has a high word frequency, its information entropy is small; On the contrary, the lower the word frequency of a word in all texts is, the greater the information entropy is, that is, the inverse relationship between the word frequency and its information entropy.…”

“…Recall rate= (15) The harmonic mean of precision and recall is defined as F1 value, and its expression is:…”