Auxiliary registration method based on Bayes text classification model

Abstract

The invention provides an auxiliary registration method based on a Bayes text classification model. The method comprises the step of obtaining symptom chief complaint text data and preprocessing the data, the step of training the preprocessed data based on the Bayes text classifying algorithm, and the step of assessing auxiliary registration classification models on which training is carried out and applying the model with the performance meeting the requirement to the auxiliary network appointment registration. In the process of Bayes theory training, optimization is carried out from two aspects according to the characteristics of symptom main complaint data, and in one aspect, absolute weight is given based on a core symptom word list in the vector weight calculating process; in the other aspect, the layering Bayes model is used for carrying out training according to the illness large classes and characteristics. According to the auxiliary registration method, the auxiliary classification model is obtained by training the symptom chief complaint text data, and the processing capacity of patient input is improved under the disease consulting, registration consulting and other typical scenes.

Description

technical field [0001] The invention relates to an auxiliary registration method based on a Bayesian text classification model Background technique [0002] With the continuous improvement of the performance of computer software and hardware, people expect computers to provide more intelligent human-computer interaction methods, especially in the aspect of online reservation and user self-service registration. By mining text data in the medical field, it can assist network users to self-register. , improve outpatient efficiency. The realization of this machine-assisted registration function requires the support of text mining technology at the bottom layer. The quality of text mining technology directly determines the performance of the system and also determines the quality of human-computer interaction. [0003] In order to realize the auxiliary registration function, the core is a classification model based on the text data of the patient's symptom chief complaint. Feat...

AI Technical Summary

Problems solved by technology

[0015] The Naive Bayesian classification model has the advantages of simplicity, high efficiency, and strong stability, but it requires conditional attributes to meet the conditional independence assumption. Many scholars study the improvement method of the Naive Bayesian classification model, mostly by relaxing the conditional independence assumption. In order to improve the performance of classifiers, such as SNBC and TAN, the improvement of general-purpose models has a disadvantage, that is, the effect of such classification models in one field is very good, but the effect in another field is likely to be unsatisfactory, such as in finance. Models with high industry efficiency are often not up to the requirements when applied to the medical industry

Images