Model generation method and device based on federated learning

The invention discloses a model generation method and device based on federated learning. One specific embodiment of the method comprises the steps of performing data splicing on acquired data of multiple users to obtain spliced data; according to a preset cooperation protocol of the multi-party users, performing resource configuration on the multi-party users; and taking the spliced data as inputdata, and performing distributed training on the initial model of the multi-party user constructed based on the configured resources to obtain a target model. According to the embodiment, the high-quality target model is obtained through data training of multiple users, so that the accuracy of the target model is improved; moreover, the multi-party users do not need to exchange data, so that thedata security of the multi-party users is ensured. 本申请公开了一种基于联邦学习的模型生成方法及装置。方法的一具体实施方式包括：对获取的多方用户的数据，进行数据拼接，得到拼接数据；根据多方用户的预设合作协议，对多方用户进行资源配置；以拼接数据作为输入数据，对基于所配置的资源构建的多方用户的初始模型进行分布式训练，得到目标模型。本实施方式通过多方用户的数据训练得到优质的目标模型，提高了目标模型的准确性