Optimizing the Assessment of the Implementation Effectiveness of Regional Ethnic Autonomy Laws and Regulations Using Data Mining Techniques

This paper evaluates the implementation effect based on the study of laws and regulations of national regional autonomy and optimizes the study and comprehension of laws and regulations based on personalized recommendation algorithms. Data mining technology is used to explore the relationship between the learning effect of users and the use of BLM-Rank model in the study of laws and regulations of national regional autonomy through the click rate and the behavior of users on the study of laws and regulations. The results show that the number of first-time users and effective users increased by 38.76% and 37.28%, and the number of silent users and lost users decreased by 75.37% and 76.62%, and the click rate of users in group A on the recommended contents of laws and regulations in seven aspects, such as “economy, politics, education, etc.”, was higher than that in group B, which was 70.37% and 76.62% respectively. The click rate of group A users on the recommended contents of laws and regulations in seven areas of “economy, politics, education, etc.” is higher than that of group B, which ranges from 70.05% to 96.41% and 39.17% to 75.58% respectively. Obviously, the construction of personalized recommendation systems can help users enhance their understanding of the laws and regulations related to regional ethnic autonomy. In addition, whether or not to use the BLM-Rank model has a great impact on the learning effect of Group A and Group B. The satisfaction of the former is above 75%, while that of the latter is <50%. It can be seen that the accurate recommendation of the BLM-Rank model can improve the learning efficiency of users on the laws and regulations of ethnic regional autonomy.