Value and path optimization of multi-data fusion algorithm to help sports tourism high-quality development

Abstract

This paper begins by analyzing the high-quality development of sports tourism and then characterizes the massive data in sports tourism with multi-source heterogeneous and heterogeneous data. The parallel data fusion platform is Hadoop, and the multi-data feature extraction algorithm is LSTM. To complete multi-source data fusion, a random forest model enhances the algorithm’s classification performance. It is verified that the information weight value H in the weight of high-quality development of sports tourism gradually increases and stabilizes at 9.87. The multi-source data fusion algorithm can help in the in-depth fusion and common sharing of data resources in sports tourism and promote the high-quality development of sports tourism.

Keywords

• sports tourism
• multi-source data fusion
• heterogeneous data characterization
• development weights
• random forests
• 68t05