Machine learning-based reimbursement process auditing method and device

The invention provides a reimbursement process auditing method and device based on machine learning, and the method comprises the steps: extracting feature data from each process node of a reimbursement process initiated by a user, inputting the feature data into a pre-constructed machine learning model for auditing, obtaining an auditing result, and if the auditing result indicates that the auditing is passed, executing the auditing process. If the auditing result indicates that auditing is not passed, archiving information corresponding to the reimbursement process is generated and stored, and if the auditing result indicates that auditing is not passed, the feature data is displayed so that the reimbursement process can be audited manually. In the scheme, the machine learning model is established by using the machine learning technology from each node of the reimbursement process, and then whether the reimbursement process passes is automatically checked based on the feature data extracted from the reimbur