Method, device and equipment for realizing feature sorting

A technology of eigenvalues ​​and feature sets, applied in the field of data processing, can solve problems such as poor user experience, low correlation, and complexity, and achieve the effects of improving efficiency, improving semantic relevance, and reducing the amount of calculation

CN112951405APending Publication Date: 2021-06-11BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-06-11

Smart Images

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

Abstract

The embodiment of the invention discloses a method, device and equipment for realizing feature selection. The method comprises the steps: acquiring a current symptom feature set of a user, and determining a first symptom feature and a feature value of the first symptom feature; acquiring the conditional probability of the first symptom feature under each disease condition and the conditional probability of a second symptom feature under each disease condition from the medical knowledge graph, calculating the global importance of the second symptom feature, and / or calculating the identification importance of the second symptom feature; and finally, according to the global importance and / or identification importance of the second symptom features, determining the importance of the second symptom features, sorting the second symptom features, and selecting the second symptom features meeting a preset condition from a sorting result as candidate symptom features. Therefore, the correlation degree between the symptom features of the inquiry can be enhanced, the calculation complexity of determining the second symptom feature is reduced, the inquiry times required for determining the predicted disease are reduced, and the inquiry efficiency of the symptom features is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the technical field of data processing, and in particular to a method, device and equipment for implementing feature sorting. Background technique

[0002] The automatic consultation system can obtain the user's symptom characteristics through multiple rounds of inquiries, so as to predict the diseases that the user may suffer from according to the symptom characteristics entered by the user, so that the user can follow up with the doctor or treatment based on the predicted disease.

[0003] When making an inquiry, the automatic consultation system uses the historical symptom characteristics input by the user to select the symptom characteristics that need to be determined for inquiry. At present, the method for selecting the symptom characteristics to be determined in the automatic medical consultation system is relatively complicated, the correlation between the symptom characteristics of two consecutive inquiries i...

Examples

specific Embodiment approach

[0200] The embodiment of the present application provides a specific implementation method of determining the importance of the second symptom feature according to the global importance and / or identification importance of the second symptom feature in step S204, including:

[0201] The global importance and discrimination importance of the second symptom feature are weighted and summed to determine the importance of the second symptom feature.

[0202] The weight of the global importance of the second symptom feature and the weight of the discriminative importance of the second symptom feature are respectively set, and the global importance and the discriminative importance of the second symptom feature are weighted and summed to obtain the importance of the second symptom feature .

[0203] The global importance S(f i ) and discriminative importance Gini(f i ) weighted calculation formula can be shown in formula (12):

[0204] V f =αS(f i )+βGini(f i ) (12)