Model acquisition method and device, user processing method and device and electronic equipment

The embodiment of the invention provides a model acquisition method and device, a user processing method and device and electronic equipment; in the method, training data is input into a preset to-be-trained model, wherein the training data comprises multiple sub-training data corresponding to a sample user, and different sub-training data correspond to different themes; based on a first self-attention layer included in the to-be-trained model, according to the feature representation of each piece of sub-training data, a topic weight corresponding to each piece of sub-training data is determined, and according to the feature representation of each piece of sub-training data and the corresponding topic weight, the feature representation of the training data is obtained; and the to-be-trained model is trained according to the feature representation of the training data to obtain a user processing model. Therefore, a plurality of sub-models do not need to be split and trained, and the sub-training data under the