Self-encoding model training method, device and equipment and storage medium

Abstract

The invention discloses a self-encoding model training method, and the method comprises the following steps: obtaining a detection result in a report, and performing pre-encoding of the detection result; adding noise to the detection result subjected to precoding; inputting the detection result added with the noise into a preset self-encoding model, wherein the self-encoding model comprises an encoder and a decoder; optimizing the self-encoding model by using an optimizer; when the loss function of the optimized self-encoding model is stable, removing the decoder in the self-encoding model tooutput the self-encoding model with the decoder removed as a trained feature expression model. The invention further discloses a self-encoding model training device and equipment and a computer storage medium. By adopting the embodiment of the invention, the trained feature expression model can improve the exploration of the report detection result space, and solves the problems of incomplete coverage, low efficiency and the like of manually constructed medical examination report detection result feature variables.

Description

technical field [0001] The present invention relates to the field of data encoding, in particular to a self-encoding model training method, device, equipment and storage medium. Background technique [0002] At present, the result analysis corresponding to the medical test report mainly focuses on the analysis of the result value of the test items in a certain type of report, and compares the test result value with the statistical reference value to obtain the final report result. Most of the result values ​​of the report sheet have been corroborated by a large number of experiments and the clinical manifestations of patients during treatment, but there is still a lot of room for research and excavation of the result values ​​of the test report sheet. At a specific point in time, the subject is tested by multiple detection methods at the same time, which can not only provide the accuracy of the test results, but also provide a more comprehensive understanding of the current ...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a self-encoding model training method, device, equipment, and storage medium. The trained feature expression model can improve the exploration of the test result space of the report and solve the problem of manually constructing the test result features of the medical examination report. Problems such as incomplete coverage of variables and low efficiency

Images