Business distribution method and device based on reinforcement learning, equipment and storage medium

The invention relates to the technical field of artificial intelligence, and provides a business distribution method and device based on reinforcement learning, equipment and a storage medium, which are used for improving the accuracy of service allocation. The business distribution method based on reinforcement learning comprises the following steps: carrying out selection probability predictionon feature vector information of mechanism private data based on a plurality of participation ends to obtain a selection probability; sampling the feature vector information through the selection probability to obtain sampling gradient information; updating model parameters of a preset service evaluation federation model according to the sampling gradient information to obtain an updated federation evaluation model, and calculating a reward value by updating the federation evaluation model; through a preset evaluator and a reward value, carrying out value evaluation on the feature vector information to obtain a participant contribution degree; and according to the contribution degree of the participant, carrying out business distribution on the plurality of participant ends to obtain participant business distribution information. In addition, the invention also relates to a blockchain technology, and the institution private data can be stored in the blockchain.