In the context of current tourism informatization, with the rapid development of Internet, artificial intelligence and other technologies, tourism data mining technology has been widely used. To solve the problem of insufficient depth in tourism data analysis, Apriori and strong association rule algorithms are studied to design tourism data mining techniques. Based on the traditional Apriori algorithm, this study analyzes its shortcomings in processing large amounts of data and proposes the use of correlation to fuse frequent itemsets in the Apriori algorithm, in order to improve the effectiveness of strong association rules. Meanwhile, parallelization is introduced to continue optimization, and the practical application value is analyzed and judged. The experiment outcomes indicate that when using the Apriori algorithm and strong association rule extraction for efficiency and accuracy experiments, the implementation time is reduced by 359%. The generated association rules account for 25.67% of the total, with an efficiency 2.6 times faster than other algorithms. The maximum and minimum correlation values are 1.3 and 1.1, respectively, with a range error of no more than 0.3. The changes in support and credibility are more stable and reliable than other algorithms. The data show that the optimized Apriori strong association rule mining algorithm designed has significantly improved computational efficiency and accuracy. The research results are of great significance for the data mining and development of tourism systems.