A shopping intention evaluation method and device and related equipment
By constructing a dynamic spatiotemporal graph and extracting behavioral temporal feature embedding vectors, combined with user attributes and spatiotemporal information, the problem of low accuracy in existing shopping intention assessment methods is solved, and a more accurate shopping intention assessment is achieved.
CN122434568APending Publication Date: 2026-07-21CHINA MOBILE SHANGHAI ICT CO LTD +2
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA MOBILE SHANGHAI ICT CO LTD
- Filing Date
- 2026-04-10
- Publication Date
- 2026-07-21
Smart Images
Figure CN122434568A_ABST
Abstract
The application provides a shopping intention evaluation method and device and related equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: obtaining user behavior data, user attributes and user space-time information, wherein the user behavior data and the user space-time information are associated with the shopping intention of a user; constructing a dynamic space-time graph according to the user behavior data, the user attributes and the user space-time information; extracting a behavior time sequence feature embedding vector according to the dynamic space-time graph, wherein the behavior time sequence feature embedding vector is used for representing cross-scene time sequence causal information corresponding to the multiple user behaviors; and determining an evaluation result of the shopping intention according to the behavior time sequence feature embedding vector. The method can improve the accuracy of intention evaluation.
Need to check novelty before this filing date? Find Prior Art