Model training method, map generation method, equipment and storage medium

• Main Authors: XIAO XU, YAO YI, SONG XIANGBO, FAN MIAO
• Format: Patent
• Language: Chinese; English
• Published: 16.04.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The embodiment of the invention provides a model training method, a map generation method, equipment and a storage medium, and the method comprises the steps: obtaining the model parameters of a first model, the first model is obtained through the training of a plurality of first local vectorized maps, the first model is used for completing the local vectorized maps, and obtaining a corresponding global vectorized map, constructing a second to-be-trained model according to the model parameters of the first model, obtaining a plurality of second local vectorization maps corresponding to the plurality of second global vectorization maps, training the second to-be-trained model according to the plurality of second local vectorization maps, and obtaining a second model, the second model is used for fusing the multiple target local vectorization maps of the target area to generate a target global vector map of the target area. According to the method provided by the embodiment of the invention, the efficiency can