Model training method and device, feature classification method and device and computer equipment

Abstract

The invention relates to a model training method and device, a feature classification method and device and computer equipment. The method comprises the steps that computer equipment determines the contribution degree of each disease feature to each department according to historical disease feature data of multiple users, determines a sample data set according to the contribution degree of historical disease features, and trains an initial classification model according to the sample data set to obtain a target classification model; wherein the contribution degree is the occurrence frequency of the disease feature for the department, the initial classification model comprises a first-layer classification model and a second-layer classification model, the second-layer classification model is a least square double support vector machine element classification model, and the target classification model is used for performing department classification according to the disease feature of the user. According to the target classification model involved in the scheme, a least square double support vector machine is adopted as a second-layer element classifier of Stacking ensemble learning, the learning difficulty of the model in the training process is reduced, and the solving efficiency of model training is improved.

Description

technical field [0001] The present application relates to the field of medical technology, in particular to a model training method, feature classification method, device and computer equipment. Background technique [0002] The traditional department triage is divided into two parts: manual and expert system. Due to the large number of patients in the manual way, it is difficult to receive a large number of patients in a short period of time only by manual department triage, which may easily cause dissatisfaction among patients; based on the expert system The method requires a large number of professionals to build a medical knowledge base, which is expensive to produce and difficult to maintain in the later stage. Moreover, there is no medical knowledge base that includes all diseases at this stage, and it is easy to fail to triage, resulting in the inability to continue the patient's medical treatment process. [0003] Aiming at the above two traditional departmental tria...

AI Technical Summary

Problems solved by technology

[0004] However, the Boosting algorithm is easy to overfit during the training process, reducing the efficiency of model training

Images