Unsupervised relation extraction aims to extract the semantic relations between entities from unlabeled natural language text. Currently， unsupervised relation extraction models based on Variational Auto-Encoder （VAE） architecture provide supervised signals to train model through reconstruction loss， which offers a new idea to complete unsupervised relation extraction tasks. Focusing on the issue that this kind of models cannot understand contextual information effectively and relies on dataset inductive biases， a Prompt-based learning based Unsupervised Relation Extraction （PURE） model was proposed， including a relation extraction module and a link prediction module. In the relation extraction module， a context-aware Prompt template function was designed to fuse the contextual information， and the unsupervised relation extraction task was converted into a mask prediction task， so as to make full use of the knowledge obtained during pre-training phase to extract relations. In the link prediction module， supervised signals were provided for the relation extraction module by predicting the missing entities in the triples to assist model training. Extensive experiments on two public real-world relation extraction datasets were carried out. The results show that PURE model can use contextual information effectively and does not rely on dataset inductive biases， and has the evaluation index B-cubed F1 improved by 3.3 percentage points on NYT dataset compared with the state-of-the-art VAE architecture-based model UREVA （Variational Autoencoder-based Unsupervised Relation Extraction model）.

The problem of birth defects is one of the most important public health problems in the world, and the application of data mining method to improve the diagnostic accuracy for birth defects is a hot medical research issue. The authors proposed two emerging patterns for birth defects feature extraction: the defection contrast to normal and the normal contrast to defection. The Birth Defects Detection based on Emerging Patterns (BDD-EP) algorithm was implemented through combining the proposed patterns with C4.5 decision tree. The extensive experimental results show that the detection accuracy of BDD-EP is as high as 90.1%, the F-measure of normal samples is 93.9%, and the F-measure of defect samples is 741%. Compared with other famous classical classification algorithms, BDD-EP algorithm can get better results.

In order to discover the special behaviors of Sub Complex System (SCS) under intervention, the authors proposed the concept of contrast inequality, proposed and implemented the algorithm for mining the segmentwise intervention; by imposing perturbance intervention on SCS, the authors proposed and implemented the causality discovery algorithm. The experiments on the real data show that segmentwise intervention algorithm discovers new intervention rules, and the causality discovery algorithm discovers the causality relations in the air pollution data set, and both are difficultly discovered by traditional methods.