Event-driven share autonomous vehicle dispatching based on knowledge graph

Predicting taxi demand in autonomous vehicle ages 从自动驾驶切入去讲

关键在于特殊日期的预测（节日，演唱会）,基于其他网站的补充信息。是不是曾经有人通过他来预测堵车呢？

Claim the field

Why is this problem important?

dynamic relocation problem to balance the demand and supply

recommendation tour / restaurant

However, different people tend to go to very different destinations. Even for the same person, the destinations may be different at different departure times and locations. However, it brings extra work for the users to enter the full name of the destination. Therefore, the user experience can be greatly enhanced if the intended destination can be accurately predicted when a user opens the APP.

mobile advertisement

relocation problem， many new users

predicting demand

现在还依赖司机自身的判断，而未来是没有司机的， 就全局优化

event-driving: movie … yanchanghui, xiabanshijian

出租车司机比你更清楚你几点下班。 -> 小黄车 OFO relocation problem

Identify the problem

previous studies

many new users

POI

geo-based social network

event-driving

传统机器学习模型，重新训练不容易，对异常值（如节日）不敏感。造成调度问题。

知识图谱

Propose method

advantages

Contribution

propose a even-representation framework

Review

tegrated moving average (ARIMA)

图像方法

Reference

AdNext: A visit-pattern-aware mobile advertising system for urban commercial complexes

Artificial neural networks applied to taxi destination prediction.

Next place prediction using mobility Markov chains

SHARED-VEHICLE MOBILITY-ON-DEMAND SYSTEMS: A FLEET OPERATOR’S GUIDE TO REBALANCING EMPTY VEHICLES