Similarity measurement method and system for complex landscapes

Abstract

The invention belongs to the field of tourism recommendation, and particularly relates to a similarity measurement method and system for complex landscapes, and the method comprises the steps: obtaining a multi-modal data time sequence of garden landscapes according to a landscape training data set, and converting the multi-modal data time sequence into a time sequence vector; training the feature extraction model according to the multi-modal time series data matrix to obtain an optimal feature extraction model, obtaining an optimal global vector according to the optimal feature extraction model and the multi-modal time series data matrix, performing decoupling mapping to obtain an attribute vector, and inputting the attribute vector into a similarity model in combination with a training data set to optimize the similarity model, so as to obtain a multi-modal feature extraction model; obtaining an optimal similarity model; and inputting actual landscape data into the optimal feature extraction model to obtain an actual global vector, and inputting the actual global vector into the optimal similarity model to obtain the similarity of different landscapes. The method has the advantages that the more accurate similarity between gardens can be obtained, a reasonable basis is provided for tourist route planning, and therefore the tourist route can be better planned.

Images