Serialized sketch generation and reconstruction model training method, reconstruction method and device

The invention provides a serialized sketch generation and reconstruction model training method and device, and a reconstruction method and device, and the method comprises the steps: obtaining a freehand sketch data set, selecting graph nodes from an incomplete freehand sketch according to a preset method, enabling each graph node to be connected with adjacent graph nodes according to a drawing stroke time sequence through employing a time-based nearest neighbor algorithm, forming an adjacent matrix; taking the obtained graph nodes, the adjacent matrix and the vectorized time series data of the complete freehand sketch as samples to construct a training sample set; obtaining an initial neural network model, wherein the model comprises an encoder module, a hidden layer and a decoder module which are connected in sequence; and training the initial neural network by adopting the training sample set, constructing a loss function between the reconstructed sketch and the complete freehand sketch, iterating paramete