Multi-target feature prediction method based on small amount of questionnaire survey data
A prediction method and multi-objective technology, applied in the field of multi-objective feature prediction, can solve the problems of high labor cost and time cost, high cost of questionnaire distribution, high cost of questionnaire printing, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] A multi-target feature prediction method based on a small amount of questionnaire survey data, including the following steps:
[0049] S1: Sort out the questionnaire survey data;
[0050] S2: Use k-means method to impute the missing data in step S1;
[0051] S3: Convert the non-numeric features supplemented in step S2 into numeric features through One-hot Encoder and Label Encoder;
[0052] S4: Associate the numerical feature converted in step S3 with any target feature you want to predict, which is called a task; establish a multi-task supervised learning (MTSL-SCRBN) model based on a randomly configured radial basis network, and Predict multiple tasks;
[0053] S5: The output result of the model established in step S4 is the final prediction result.
[0054] The non-numerical features in step S3 include:
[0055] a: Aggregate the characteristics of physical condition according to basic information such as age and gender of the surveyed person;
[0056] b: Aggregate regional devel...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com