Personnel stability evaluation and model training method and device
By using the random forest algorithm model and the backpropagation algorithm trained personnel stability evaluation model, the problem of high cost and low efficiency of manual evaluation of candidates in the prior art is solved, and more efficient and accurate stability evaluation is achieved.
CN119721845APending Publication Date: 2025-03-28INDUSTRIAL AND COMMERCIAL BANK OF CHINA
0 Cites 2 Cited by
Patent Information
- Application Number
- CN202411861135.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-03-28
AI Technical Summary
Technical Problem
The existing interview process relies on manual assessment of candidate stability, and there are problems such as high operational cost, low efficiency and strong subjectivity, so it is impossible to effectively and objectively evaluate the stability of candidates.
Method used
By obtaining the feature data of interview candidates, inputting the trained personnel stability evaluation model, the random forest algorithm model is trained through N-fold cross-validation and backpropagation algorithm, and the model parameters are updated in real time to evaluate the stability of the candidates.
Benefits of technology
Reduce the dependence of manual evaluation, improve the evaluation efficiency and accuracy, and enable more objective evaluation of candidate stability.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention provides a personnel stability evaluation method which can be applied to the technical field of big data and artificial intelligence. The personnel stability evaluation method comprises the steps of obtaining feature data of interview candidate personnel; the feature data are input into a trained personnel stability evaluation model, a stability evaluation result is obtained, and the trained personnel stability evaluation model is obtained by training a random forest algorithm model through an N-fold cross validation method and a back propagation algorithm; and the trained personnel stability evaluation model updates model parameters in real time according to a stability evaluation result. The invention further provides a model training method, a personnel stability evaluation device, a model training device, equipment, a storage medium and a program product.
Need to check novelty before this filing date? Find Prior Art