EVALUATION OF THE IMPLEMENTATION EFFECT OF INTELLECTUAL PROPERTY POLICY BASED ON NAIVE BAYES ALGORITHM

As a core driving force for modern economic development, the scientific evaluation of the implementation effect of intellectual property policies has become an important topic for government decision-making and academic research. Traditional policy evaluation methods often rely on expert experience or simple statistical analysis, which are difficult to effectively handle the massive multidimensional data generated during the implementation of intellectual property policies. The Naive Bayes algorithm, as a machine learning method based on probability theory, can effectively identify key influencing factors in the implementation of intellectual property policies, providing a new technical path. This paper constructs an evaluation model for the implementation effect of intellectual property policies based on the Naive Bayes algorithm, integrating multi-source information such as policy text data, enterprise innovation data, and patent application data, and establishing a probabilistic mapping relationship between policy characteristics and implementation effects. Through analysis and verification of the model, the study shows that the algorithm demonstrates strong practical value in the evaluation of the effects of intellectual property policies, provides a scientific basis for policy optimization, and promotes the transformation of policy evaluation towards data-driven intelligentization. This research aims to provide methodological support for the scientific formulation and precise implementation of intellectual property policies, and to provide theoretical basis and practical guidance for the decision-making optimization of relevant government departments.