A Route Recommendation Algorithm Based on Multi-Dimensional Data Fusion and Analysis of its Social Utility

The current route recommendation algorithm has problems such as single data. This paper designs a route recommendation algorithm based on multidimensional data fusion, uses convolutional neural network (CNN) to extract the features of user behavior data, geographic location information and environmental factor data, and then uses the attention mechanism to realize the fusion processing of multidimensional data. Based on the fused multidimensional data features, collaborative filtering and content-based recommendation algorithms are used to generate personalized route recommendations in combination with user preferences and real-time traffic conditions. Experiments have shown that the recommendation accuracy of this algorithm can reach up to 100%under controlled test conditions. Compared with the Bellman-Ford algorithm, this algorithm takes an average of 5.46 minutes less time, and the adoption rate of the recommendation results of this algorithm is as high as 99.9%, which proves the effectiveness of the algorithm in the cultural and tourism route recommendation scenario.