Research on Random Sampling Data Diffusion Technique in the Construction of Digital Object System Test Dataset

Digital object architecture is an important part of the future development of the Internet. It converts various elements such as processes, services and data into digital objects. This architecture promotes standardization and interoperability of information resources by assigning unique identifiers to each object. However, this field is still in its early stages and faces many challenges. This study introduces a data diffusion method based on random sampling to expand the small sample set and improve the coverage of test data. On this basis, the Bayesian network algorithm was optimized using expert prior knowledge, and a digital object generation model was developed to ensure high relevance and authenticity while meeting the standards. The effectiveness of the model was verified through case studies of situational events, where event data was successfully encapsulated into digital objects, generating a large amount of test data. Ultimately, this study demonstrates the successful integration of data, models, and algorithms in a loosely coupled management platform, providing important support for the further development of digital object systems.