Blockchain is experiencing rapid development and has the full potential of revolutionizing the IoT platform in the industrial field. In this paper, a light-weighted Blockchain-based platform for IIoT is presented to address security, trust, and island connection problem in the process of IIoT ecosystem construction. BPIIoT is comprised of the on-chain network and the off-chain network. All transactions are processed in the on-chain network such as including digital signature based on access control and programmable permission. The off-chain network deals with the storage, complex data processing, and other problems that blockchain cannot solve. The smart contract is utilized as the service contract of consumers and manufacture resources, providing on-demand manufacturing service. Two smart application cases, manufacturing equipment data sharing and maintenance service sharing from smart manufacturing, are implemented to explain the smart contract for equipment maintenance service and status data sharing service throughout maintenance, repair, and operation service network by the BPIIoT.

The last two decades have witnessed an explosive growth of e-commerce applications. Existing online recommendation systems for e-commerce applications, particularly group-buying applications, suffer from scalability and data sparsity problems when confronted with exponentially increasing large-scale data. This leads to a poor recommendation effect of traditional collaborative filtering (CF) methods in group-buying applications. In order to address this challenge, this paper proposes a hybrid two-phase recommendation (HTPR) method which consists of offline preparation and online recommendation, combining clustering and collaborative filtering techniques. The user-item category tendency matrix is constructed after clustering items, and then users are clustered to facilitate personalized recommendation where items are generated by collaborative filtering technology. In addition, a parallelized strategy was developed to optimize the recommendation process. Extensive experiments on a real-world dataset were conducted by comparing HTPR with other three recommendation methods: traditional CF, user-clustering based CF, and item-clustering based CF. The experimental results show that the proposed HTPR method is effective and can improve the accuracy of online recommendation systems for group-buying applications.