The convergence of unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks and blockchain transforms the existing mobile networking paradigm. However, in the temporary hotspot scenario for intelligent connected vehicles (ICVs) in UAV-aided MEC networks, deploying blockchain-based services and applications in vehicles is generally impossible due to its high computational resource and storage requirements. One possible solution is to offload part of all the computational tasks to MEC servers wherever possible. Unfortunately, due to the limited availability and high mobility of the vehicles, there is still lacking simple solutions that can support low-latency and higher reliability networking services for ICVs. In this article, we study the task offloading problem of minimizing the total system latency and the optimal task offloading scheme, subject to constraints on the hover position coordinates of the UAV, the fixed bonuses, flexible transaction fees, transaction rates, mining difficulty, costs and battery energy consumption of the UAV. The problem is confirmed to be a challenging linear integer planning problem, we formulate the problem as a constrained Markov decision process. Deep Reinforcement Learning (DRL) has excellently solved sequential decision-making problems in dynamic ICVs environment, therefore, we propose a novel distributed DRL-based P-D3QN approach by using Prioritized Experience Replay strategy and the dueling double deep Q-network (D3QN) algorithm to solve the optimal task offloading policy effectively. Finally, experiment results show that compared with the benchmark scheme, the P-D3QN algorithm can bring about 26.24% latency improvement and increase about 42.26% offloading utility.

In 2013, China proposed the “Belt & Road Initiative” which aims to invest the “Belt & Road” countries so as to help them develop their infrastructure and economy. China consumes the largest part of fossil energy of the whole world, so it is China’s priority to consider its energy supplying security. Therefore, it becomes urgent for China to invest the “Belt & Road” countries’ energy facilities. There comes a question: how to evaluate the overseas energy investment risk? To answer this question, this paper proposes a deep learning method to assess such risk of the 50 “Belt & Road” countries. Specifically, this paper first proposes an indicator system in which 6 main factors are separated into 36 sub-factors. This paper makes use of hierarchical convolution neural networks (CNN) to encode the historical statistics. The hierarchical structure could help CNN handle the long historical statistics more effectively and efficiently. Afterward, this paper leverages the self-attention layer to calculate the weights of each sub-factor. It could be observed that the resource potential is the most important indicator, while “years of China’s diplomatic relations” is the most important sub-indicator. Finally, we use a conditional random field (CRF) layer and softmax layer to compute the assessment scores of each country. Based on the experimental results, this paper suggests Russia, United Arab Emirates (UAE), Malaysia, Saudi Arabia, Pakistan, Indonesia, and Kazakhstan to be China’s most reliable choices for energy investment.

Image scene graph is a semantic structural representation which can not only show what objects are in the image, but also infer the relationships and interactions among them. Despite the recent success in object detection using deep neural networks, automatically recognizing social relations of objects in images remains a challenging task due to the significant gap between the domains of visual content and social relation. In this work, we translate the scene graph into an Attentive Gated Graph Neural Network which can propagate a message by visual relationship embedding. More specifically, nodes in gated neural networks can represent objects in the image, and edges can be regarded as relationships among objects. In this network, an attention mechanism is applied to measure the strength of the relationship between objects. It can increase the accuracy of object classification and reduce the complexity of relationship classification. Extensive experiments on the widely adopted Visual Genome Dataset show the effectiveness of the proposed method.

China’s “Belt & Road Initiative” has been proposed for several years, which has stimulated the economic and financial development of the countries alongside the “Belt & Road”. For a world’s leading energy consuming country, China tries to secure the energy supply from the resource-rich countries via oversea energy investment. In this paper, we propose a sequence to sequence (seq2seq) model to evaluate the energy investment risk of 50 countries alongside the “Belt & Road Initiative”. Specifically, we first build an indicator system mainly containing six factors. Then we adopt Bi-long-short term memory (Bi-LSTM) as encoder to process the historical statistics. Afterward, we use self-attention mechanism to assign the weights on the six factors of the indicator system. Finally we use a hierarchical convolution neural network decoder to generate the assessment results. Our findings indicate that resource potential and Chinese factor are the most important indicators. And through our thorough investigation, we find that Russia, Kazakhstan, Pakistan, United Arab Emirates, Saudi Arabia, Malaysia and Indonesia are the most recommended target countries for China’s oversea energy investment.

Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities with external tools in solving real-world tasks. However, there are limitations in the data construction of tool learning such as high data structuring, symbolization, and privacy. This makes annotations costly and time-consuming, which is unsuitable for vertical deployment of tool-augmented model in real-world scenarios. Therefore, in this paper, we propose AuToGen, an automated tool learning data generation approach with domain-specific structured data. AuToGen leverages structured database table structures for keyword extraction. Then utilizes state-of-the-art LLMs for initial seed set generation and expands these sets for enriched tool-assisted model training data. Our experiment demonstrate that the high-quality of the data generated by AuToGen. Compared with the data generated by manually written seed sets, the model trained using AuToGen generated data has higher performance, proving that our method can efficiently assist in the deployment of real-world models.