A purchase probability determination method and apparatus, electronic device, and storage medium

By constructing a directed graph of object touchpoint interactions and utilizing graph convolutional networks and long short-term memory networks, the problem of missing user behavior data across multiple channels and touchpoints was solved, enabling accurate prediction of purchase probability and precise recommendation push.

CN122415150APending Publication Date: 2026-07-17上海卫瓴信息科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
上海卫瓴信息科技有限公司
Filing Date
2026-05-25
Publication Date
2026-07-17

Smart Images

  • Figure CN122415150A_ABST
    Figure CN122415150A_ABST
Patent Text Reader

Abstract

本发明公开了一种购买概率确定方法、装置、电子设备以及存储介质。该方法包括：确定各个对象在各个时间窗口的行为数据，并基于所述行为数据生成行为时序数据；基于所述行为时序数据，构建对象触点交互有向图；基于各个时间窗口的对象触点交互有向图，确定下一时间窗口内各个对象的购买概率。采用本申请的技术方案，通过确定各个对象在各个时间窗口的行为数据，并基于所述行为数据生成行为时序数据；基于所述行为时序数据，构建对象触点交互有向图；基于各个时间窗口的对象触点交互有向图，确定下一时间窗口内各个对象的购买概率，从而实现对下一时间窗口内各个对象的购买概率进行准确预测，并为后续选择对各个用户的推荐推送方式提供基础。
Need to check novelty before this filing date? Find Prior Art