城市兴趣点演化规律的可预测性分析

建立兴趣点生命周期可预测性模型来刻画城市兴趣点演化规律的可预测性. 该模型针对城市兴趣点在连续时间窗口的变化情况，给出其生命周期长度和生命周期状态的定义，分析兴趣点在演化过程中的可预测性. 为量化城市兴趣点演化规律的可预测性，将城市兴趣点的生命周期长度和生命周期状态的信息熵同Fano不等式相结合，基于信息论中信息的不确定性度量方法给出城市兴趣点生命周期长度和生命周期状态的可预测性计算方法，并结合7个城市的城市兴趣点数据，计算出不同粒度、不同类别的兴趣点的可预测性. 结果表明：城市兴趣点的生命周期是可预测的且不同类别兴趣点的可预测性差异较大；相对于稳定状态和爆发状态的兴趣点，处于消亡状态的兴趣点的可预测性更高.

Analysis on predictability of urban point-of-interest evolution

A PLCPA model was established to describe the predictability of urban point-of-interest evolution. Based on the change of urban interest points in continuous time window, a definition of the life cycle length and life cycle status was given and the predictability of point-of-interest evolution was analyzed. Fano’s inequality was combined with the life cycle length and status of urban point-of-interest to quantify the predictability of the evolution of urban point-of-interest. And the predictability calculation of life cycle length and status of urban point-of-interest was given based on the information uncertainty measure in the information theory. The predictability of different categories of point-of-interest with different levels of granularity was calculated according to the urban point-of-interest data of seven cities. Results show that the life cycle of urban interest points is predictable; the predictabilities of different categories of point-of-interest are quite different; the predictability of the points-of-interest in the decaying status is higher than that of the stable status and the booming status.