RESUMEN

Effective information extraction of pharmaceutical texts is of great significance for clinical research. The ancient Chinese medicine text has streamlined sentences and complex semantic relationships, and the textual relationships may exist between heterogeneous entities. The current mainstream relationship extraction model does not take into account the associations between entities and relationships when extracting, resulting in insufficient semantic information to form an effective structured representation. In this paper, we propose a heterogeneous graph neural network relationship extraction model adapted to traditional Chinese medicine (TCM) text. First, the given sentence and predefined relationships are embedded by bidirectional encoder representation from transformers (BERT fine-tuned) word embedding as model input. Second, a heterogeneous graph network is constructed to associate words, phrases, and relationship nodes to obtain the hidden layer representation. Then, in the decoding stage, two-stage subject-object entity identification method is adopted, and the identifier adopts a binary classifier to locate the start and end positions of the TCM entities, identifying all the subject-object entities in the sentence, and finally forming the TCM entity relationship group. Through the experiments on the TCM relationship extraction dataset, the results show that the precision value of the heterogeneous graph neural network embedded with BERT is 86.99% and the F1 value reaches 87.40%, which is improved by 8.83% and 10.21% compared with the relationship extraction models CNN, Bert-CNN, and Graph LSTM.

Asunto(s)

RESUMEN

Image super-resolution reconstruction can reconstruct low resolution blurred images in the same scene into high-resolution images. Combined with multi-scale Gaussian difference transform, attention mechanism and feedback mechanism are introduced to construct a new super-resolution reconstruction network. Three improvements are made. Firstly, its multi-scale Gaussian difference transform can strengthen the details of low resolution blurred images. Secondly, it introduces the attention mechanism and increases the network depth to better express the high-frequency features. Finally, pixel loss function and texture loss function are used together, focusing on the learning of structure and texture respectively. The experimental results show that this method is superior to the existing methods in quantitative and qualitative indexes, and promotes the recovery of high-frequency detail information.

RESUMEN

This paper proposes a performance evaluation method of public administration departments based on the improved DEA algorithm, which solves the quality problem of performance evaluation of public administration departments and lays a foundation for the long-term development and performance improvement of public administration departments. The DEA model is the core to sort out the performance evaluation methods of public administration departments. From the perspective of DEA algorithm, whether DEA is effective is an important content that public administration departments must consider when carrying out performance administration, and public service satisfaction is the core parameter obtained by DEA algorithm. That is to say, by optimizing public services and improving service satisfaction, the public administration department can further improve the quality of performance evaluation. Therefore, we can carry out performance evaluation of public administration departments from the satisfaction of public services. The empirical research conclusion shows that according to the effective judgment theorem of DEA, it can be concluded that among the eight social security departments, there are five departments that can achieve DEA effectiveness, namely department 2, department 3, department 4, department 5, and department 6. There are three non-DEA valid ones, namely, department 1, department 7 and department 8. The public satisfaction and the total service cost will affect the performance quality to a certain extent, and only by balancing various influencing factors can the performance evaluation quality of the public administration department be maximized.

Asunto(s)