Research and Design of Blockchain-based Propagation Algorithm for IP Tags Using Local Random Walk in Big Data Marketing

In the field of cultural and creative IP marketing empowered by big data, the integration of blockchain technology offers a new dimension for optimizing IP dissemination. However, traditional label propagation-based community detection algorithms, which primarily rely on direct neighbor nodes for label updates, often fall short in accurately identifying fan communities within blockchain-enabled IP dissemination networks, leading to unstable community partitioning. To overcome these challenges, this paper presents a Local Random Walk Based Label Propagation Algorithm (LRW-LPA) tailored for blockchain-based IP marketing scenarios. Leveraging big data analytics, the proposed algorithm first evaluates the local importance index of nodes within a k-step neighborhood, then determines the local neighborhood range through a local random walk process with restart. By selecting the label with the highest occurrence frequency and influence value within this local neighborhood to update the starting node, LRW-LPA can more accurately identify user communities. Comparative experiments on real-world cultural and creative IP marketing datasets demonstrate that the proposed algorithm outperforms traditional methods in terms of community detection accuracy and stability, providing a robust solution for precise IP marketing strategies in the era of big data and blockchain.