The correctness of the procuratorial case handling has a significant impact on social fairness and justice, which makes it essential to review and supervise procuratorial cases. However, these cases often involve a variety of types of data items and activities and complex processing logic, which makes it difficult to check the source of the data and verify the compliance of the process. To solve this problem, we propose a provenance solution for the procuratorial case processing scenario in this paper. We first sort out four types of questions that need to be answered in the case of the procuratorate. Then we propose two kinds of provenance to give these explanations through a single instance or multiple instances. Besides, we choose graph database Neo4j as a storage plan and provide corresponding query plans for the provenance, then evaluate their performance with our prototype system and the data from procuratorial test cases. The result shows that the query efficiency of our solution will not fluctuate greatly due to the depth of the query or the amount of data, which is suitable for the work scene of the procuratorate.

Text matching is important for a variety of natural language processing tasks, such as paraphrase identification and natural language inference. Recent studies have achieved very promising results under the compare-aggregate framework. A limitation of previous approaches following this framework is that they solely conduct matching at word level. In this paper, we propose a multi-level compare-aggregate model (MLCA), which matches each word in one text against the other text at three different levels, word level (word-by-word matching), phrase level (word-by-phrase matching) and sentence level (word-bysentence matching). Then the results of these levels of matching are aggregated for making final matching decision. We evaluate our model on two different tasks: paraphrase identification and natural language inference. Experimental results show that our model achieves the state-of-the-art performance on both tasks.

Text matching aims to establish the matching relationship between two texts. It is an important operation in some information retrieval related tasks such as question duplicate detection, question answering, and dialog systems. Bidirectional long short term memory (BiLSTM) coupled with attention mechanism has achieved state-of-the-art performance in text matching. A major limitation of existing works is that only high level contextualized word representations are utilized to obtain word level matching results without considering other levels of word representations, thus resulting in incorrect matching decisions for cases where two words with different meanings are very close in high level contextualized word representation space. Therefore, instead of making decisions utilizing single level word representations, a multi-level matching network (MMN) is proposed in this paper for text matching, which utilizes multiple levels of word representations to obtain multiple word level matching results for final text level matching decision. Experimental results on two widely used benchmarks, SNLI and Scaitail, show that the proposed MMN achieves the state-of-the-art performance.

A reliable protection system is vital to power system. As the major equipment of protection system, protection relay plays a basilica role in power system. So searching for proper settings of relays to make them operate in a better way is significant. In this paper, a new optimization problem formulation is proposed to search the optimal relay setting of over current relays in power systems. Then, a new hybrid evolutionary algorithm based on tabu search (HEATS) is presented to solve this optimization problem, and results under different algorithm parameters are obtained Finally, comparisons among HEATS, one of particle swarm optimizations(PSO) and test evolutionary algorithm(TEA) shown in other literatures are given. Simulation results show the formulation of protection relay setting is feasible and effective, and the proposed algorithm HEATS exhibits a good performance.