Medical data classification and grading method, computer equipment and storage medium

A medical data and grading method technology, applied in the field of electronic digital data, can solve the problems of low accuracy of medical data classification results, large dimensions, and sparse data, so as to reduce interdependence, reduce the amount of calculation, and alleviate the disappearance of gradients Effect
CN113571199AInactive Publication Date: 2021-10-29成都健康医联信息产业有限公司
4 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
成都健康医联信息产业有限公司
Publication Date
2021-10-29
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a medical data classification and grading method, computer equipment and a storage medium. The method comprises the steps of medical data preprocessing: performing word segmentation, filtering and word bag processing on medical data; word vector extraction: performing word vectorization on the preprocessed medical data, namely mapping the preprocessed medical data into word vectors, and constructing a word vector corpus according to the generated word vectors; constructing a classification model: inputting the word vectors in the word vector corpus to a TextCNN model for training; and classification and classification prediction: calling the trained TextCNN model to calculate the classification and classification probability of the to-be-classified medical data, and outputting a classification and classification result. According to the method, the problem of low accuracy of a medical data classification result caused by data sparsity and huge dimension can be well solved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of electric digital data, in particular to a medical data classification and grading method, computer equipment and a storage medium. Background technique

[0002] Traditional medical data classification methods are mainly divided into two categories. One is the data classification based on the dictionary, which compares the data with the established dictionary database to classify. The second is data classification based on machine learning. This method uses feature engineering such as text preprocessing, feature extraction, and text representation, such as calculating the frequency of words through the bag of words model, and calculating the weight of words in the text through the TF-IDF model. On the basis of feature engineering, classification models such as SVM, Naive Bayesian, and K nearest neighbor classification are used for classification.

[0003] But there is following defective in above-mention...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More