The purpose of automated question answering is to let the machine understand natural language questions and give accurate answers in the form of natural language. This technology requires the machine to store a large amount of background knowledge. In recent years, the rapid development of knowledge graph has made the knowledge based question answering (KBQA) more and more popular. Traditional styles of KBQA methods mainly include semantic parsing, information extraction and vector modeling. With the development of deep learning, KBQA with deep learning has gradually become the mainstream method. This paper introduces the application of deep learning in KBQA mainly from the following aspects: the development history of KBQA, KBQA methods using deep learning, common datasets used in KBQA, the comparison of various methods and the future trend.

Thunderstorms are the most frequent type of severe convective weather, which pose great threats to buildings, power transmission, communication facilities, and air transportation. Their analysis and forecasting have long been challenges in meteorological operations. Currently, deep learning-based lightning forecasting has a short valid period, mostly relying on satellite imagery, radar echoes, and lightning location data, focusing on very-short-range forecasting. The longest valid period does not exceed 6 h, and the forecasting accuracy is not high. Based on the physical quantities of the ECMWF numerical prediction model and the actual observations of single-point thunderstorms, this paper constructs a single-point thunderstorm forecasting model with a long validity period (>6 h). The study integrates multi-dimensional parameters such as thermal, dynamic, water vapor, and stratification instability, introduces the second-order moist potential vorticity S as a comprehensive predictor, systematically compares the forecasting performance of eight models, such as 1D PreRNN and ConvLSTM, and verifies the actual operational capability of the model through independent cases. The results show that the 1D PreRNN model has the best overall performance in all periods, which can effectively capture the temporal evolution characteristics of meteorological physical quantities and still has stable generalization performance under unbalanced samples. The model performs well in the 1st, 2nd, and 4th periods, and especially still has significant operational reference value in the 4th period with the longest forecasting validity period; only the 3rd period is weakly affected by the small number of samples. The effect of second-order moist potential vorticity has significant time-dependent differences. Its overall improvement effect is limited in short-term forecasting, but it can provide key disturbance signals in the 4th period with the longest forecasting validity period, and the model forecasting performance drops significantly after removal. The original binary cross-entropy loss is most suitable for the unbalanced sample scenario in this study, and weighted losses are prone to overcorrection. The method in this paper can achieve stable and reliable single-point thunderstorm forecasting for more than 6 h, and can provide long-term fixed-point meteorological support for key scenarios such as aerospace and new energy stations.

Due to the factors such as the high velocity of vehicles, the limited communication range of vehicles, the data transmission reliability and stability of the VANET (Vehicular Ad Hoc Network) is susceptible to traffic conditions and the influence of driving environment. So the mobility model of vehicles plays an important role in the routing protocol design and performance evaluation of VANET. In this paper, we proposed an IDM_A mobility model which takes the collision avoidance behavior of vehicles into consideration based on the characteristics of real vehicle track. After the simulation using the network simulator NS, the results verify the feasibility and effectiveness of the model proposed.