一种基于多维社交信任图谱的顺风车路径匹配方法
By constructing a trust relationship between passengers and drivers through a multi-dimensional social trust graph and combining it with route overlap for ride-sharing matching, the problem of insufficient social trust in existing algorithms is solved, thereby improving trip safety and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHENGDU LINGQI SPACE SOFTWARE
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing ride-sharing matching algorithms fail to adequately consider the social trust between passengers and drivers, resulting in users feeling insecure and having strong psychological defense mechanisms when traveling at night or on remote routes. This leads to higher rates of hesitation in placing orders, last-minute cancellations, and no-shows, while also causing difficulties in cold starts and wasting community and social attributes.
A multi-dimensional social trust graph is adopted to construct user trust relationships through geographical proximity, historical interaction and second-degree connection vectors. The comprehensive score between passengers and car owners is calculated and the matching decision is made in combination with the path overlap, and multi-dimensional social trust weights are introduced.
It improves the safety of ride-sharing trips, reduces order hesitation and no-show rates, solves the cold start problem, fully leverages the community and social attributes of real life, and enhances matching accuracy and user experience.
Smart Images
Figure CN122414522A_ABST