Establish a repair call action prediction model, repair call action prediction method and related devices

Abstract

This application discloses a method for establishing a repair call action prediction model and a repair call action prediction method, based on diversified work source data such as repair call records, operator operation records, system fault records, and / or system key action records, to run machine learning A non-linear repair call action prediction model is established in a non-linear manner, so that the established repair call action prediction model can effectively reduce the impact on prediction accuracy caused by the gap in subjective judgment ability when predicting repair call actions. At the same time, the action sampling data of the medical equipment during the working time interval is obtained, and the action sampling data is input into the established repair action prediction model, which can effectively predict the repair action, thereby optimizing the operator's use and operation habits, prolonging the service life of the equipment, reducing After-sales cost overhead. The application also discloses a device for establishing a repair call action prediction model and a device for repair call action prediction.

Description

technical field [0001] The present application relates to the technical field of medical equipment, and in particular to a method for establishing a repair call action prediction model, a repair call action prediction method, and related devices. Background technique [0002] Large-scale medical imaging equipment, such as CT (Computed Tomography, computerized tomography) equipment, usually includes main working modules such as an operating software platform, an image scanning module, and a mechanical operation module. The work of large-scale medical imaging equipment can be completed by the operator through the software platform. The connection of each work link is partly completed automatically by the equipment, and the other part is realized by the operator's operation. [0003] From the perspective of the work type of large-scale medical imaging equipment, it can be divided into two states, one is the scanning state of image acquisition, and the other is the non-scanning ...

AI Technical Summary

Problems solved by technology

However, different usage scenarios, different operators operate the equipment in different ways, and the operating frequency is also different. In addition, the complexity of large-scale medical imaging equipment is relatively high.

Therefore, in addition to the normal life loss of equipment components, the operator's "improper operation" of the equipment may also cause abnormalities in the system that cannot be recovered for a short time. In this case, the operator will initiate a repair action for the equipment

[0004] Due to the uncertainty of the operator's operation, the operator's initiation of repair action is also uncertain. In the existing technology, it is impossible to accurately predict the generation of repair action, which will lead to the uncontrollable after-sales cost of large medical imaging equipment.

Images