The invention discloses a semantic similarity calculation model DSSM technology based on a Transformer. The semantic similarity calculation model DSSM technology is based on the Transformer. The device comprises an input layer, a presentation layer and a matching layer, the input layer is used for respectively converting the map node names and the APP page characters into two-dimensional arrays represented by character vectors; the input is used as the input of the presentation layer; wherein the representation layer is an encoder part adopting Transformer, firstly, a node name feature vectorand an APP page character feature vector output by the input layer are encoded respectively, so that more abstract features of each word in a sentence are extracted, and the invention relates to the technical field of natural language processing. Thea semantic similarity calculation model DSSM technology based on Transformer is different from manual modification of graph node content which consumes a lot of time and energy, the method is simple; the semantic similarity calculation model DSSM technology based on Transformer can replace manual work to modify the map name in the application of the test map, realizes the function of automatically matching the new APP content, improves the test efficiency of the APP, and reduces a large amount of artificial redundant operations.