With the rapid expansion of the Internet, intelligent question answering for information retrieval has once again gained widespread attention. However, current question answering models mainly focus on the general and common-sense questions in open domains and are incapable to effectively solve more complex professional domain questions. This paper proposed an integrated framework for Chinese intelligent question answering in restricted domains. The proposed model fused convolutional neural network and bidirectional long short-term memory network which performs efficient semantic analysis on the question pairs to extract more effective features of the text. Meanwhile, the coattention mechanism and attention mechanism were combined to obtain the semantic interaction and feature representation of the question pair for providing complete information for subsequent calculations. In addition, we introduced the method of question pair matching to implement the Chinese intelligent question answering in a restricted domain. Experiments were tested and evaluated on the open-source CCKS2018 dataset and our private self-built inverted pendulum control question answering (IPC-QA) dataset for automation control virtual learning environment. Experimental results confirm that the proposed models are efficient and achieve a high precision of 0.86042 and 0.8031 on CCKS2018 and IPC-QA respectively.

No abstract

The paper proposes the farmers credit optimization decision model and applications based on common risk guarantee fund. By considering two conditions of with default risk and without default risk, the individual rationality of bank and farmer is designed, respectively, and the mathematical formulas for calculating the risk loss ratio of bank loans under the guarantee fund are established and discussed innovatively, respectively. A nonlinear optimal model based on risk compensation fund is established in the paper. By mathematical proof, the optimal bank credit decision mechanism is studied. By the analysis of numeric experiments of two cases of with default risk and without default risk, the expected income and invest income are varied by the changing of farmer project success probability and default probability, and the relationship of loan interest, farmer expected income and invest income is studied. The research has scientific guiding significance and practical application value for farmers' credit decision making.Keywords Farmers credit optimization decision model Á Common risk guarantee fund Á Individual rationality Á Loan risking lost rate

No abstract

This paper gives a new method to resolve the problem of extracting fault characteristics in electro motor. It is proved that the fault information is plentiful in instantaneous power by theory illation, and the fundamental component transforms to the DC component which can be filtrated easily; analyze the signal via wavelet packet decomposition, the root mean square of the node coefficients and it's change rate used as the symptom of bearing fault is calculated. Simulation result accords with the theory illation, which indicates that this method can be used in bearing fault diagnosis.