The digital asset value and currency supervision under deep learning and blockchain technology

With the rapid development of digital currencies such as Bitcoin, it is difficult to extract the effective information from massive data and quantify the value of digital assets using current methods. As a key underlying technology, blockchain technology can no longer meet most of the needs of digital currency transactions. Based on this, the digital asset is taken as the research object and an analysis model for digital asset value is established with the deep learning technology in this study. Then, the authorization mechanism in the distributed position and orientation system (DPOS) algorithm is extracted and applied to the precise backward error tracking (PBET) algorithm based on the existing consensus algorithm in blockchain technology. Thus, a dynamic delegated practical byzantine fault tolerance (DDPBFT) algorithm that can be applied to the blockchain is proposed. Finally, a supervisable digital currency system is constructed based on the improved blockchain technology. After specific analysis, it is found that the analysis model for digital asset value based on the deep learning proposed in this study shows good stability and accuracy, and can help enterprises to analyze the value of digital assets. Compared with the existing consensus mechanism algorithms, the proposed DDPBFT algorithm shows better results in terms of throughput and delay. Finally, the supervisable digital currency model based on the improved blockchain technology can unite the public chains, alliance chains, and user wallets, and realize the traceability of transaction information. In short, the quantitative analysis of the value of digital assets has been realized and the supervision of digital currency transactions has been achieved by using the improved blockchain technology. (C) 2021 Elsevier B.V. All rights reserved.