Model training method, and method for determining member conversion probability
By training a member user feature prediction model and a conversion probability model, and dynamically adjusting member user features, the problem of high computational resource consumption and low accuracy of decision tree strategies in large-scale data processing is solved, achieving higher member conversion prediction accuracy and user conversion rate.
WO2026144397A1PCT designated stage Publication Date: 2026-07-09CHINA MOBILE INTERNET CO LTD +1
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- CHINA MOBILE INTERNET CO LTD
- Filing Date
- 2025-10-15
- Publication Date
- 2026-07-09
Smart Images
Figure CN2025127888_09072026_PF_FP_ABST
Abstract
Provided in the present disclosure are a model training method, and a method for determining a member conversion probability. The model training method comprises: acquiring target data corresponding to a target product, wherein the target data comprises functional information of at least one historical version, user behavior data of member users corresponding to each historical version, and functional information of a version to be released; inputting the target data into a member user feature prediction model, so as to obtain at least one type of member user feature corresponding to the version to be released; and on the basis of the at least one type of member user feature, and user behavior data of non-member users corresponding to the at least one historical version corresponding to the target product, training a member user conversion probability prediction model.
Need to check novelty before this filing date? Find Prior Art