一种基于时空位置预测的空间众包任务分配方法

A Spatial Crowdsourcing Task Assignment Approach Based on Spatio-Temporal Location Prediction

空间众包技术在现实物理世界中有着丰富的应用场景,得到学术界和工业界的广泛关注.任务分配是空间众包的主要研究问题之一,即把工人分配给合适的任务.但是现有的任务分配方法大多假设众包工人和空间任务出现的位置和时间是已知的,忽略了真实的众包平台中众包工人和空间任务的动态变化,由于空间众包平台的强时效性,这种情况下设计的分配方式只能得到局部最优分配结果.提出最大价值最小成本任务分配的新问题,目标是对当前和未来的工人进行分配,使用最小的移动成本获得最大的分配价值.为解决这一问题,提出了基于轨迹的任务分布预测方法及基于核密度估计的工人分布预测方法,设计基于位置预测的任务分配算法来计算众包工人和空间任务的相对最优分配策略.所提位置预测方法利用图卷积神经网络和ConvLSTM模型进行预测,相较传统基于网格的位置分布预测更加精确和稳定.基于位置预测的启发式分配算法可以在线性时间内结合预测得到的位置信息完成任务分配,更加契合空间众包平台的强时效性.在真实数据集上进行大量实验来证明所提方法的有效性,相比于基于网格的预测方法,任务/工人位置预测准确率分别提高了15.7%和18.8%.

Space crowdsourcing technology has a varying type of application scenarios in the real physical world,which has been widely concerned by academia and industry.Task assignment is one of the important research issues in space crowdsourcing,that is,distributing workers to appropriate tasks.However,most existing task assignment methods assume that the location and time of crowdsourcing workers and space tasks are known,ignoring the dynamic change of crowdsourcing workers and space tasks in real crowdsourcing platforms.Due to the requirement of strong timeliness in space crowdsourcing platforms,in this situation,the designed assignment method can only get the local optimal results.A new problem of task assignment with maximum value and the minimum cost is proposed,which aims to distribute current and future workers and obtains the maximum assignment value by using the minimum traveling cost.To handle this problem,a trajectory based model is proposed to predict the distribution of tasks.In addition,a kernel density estimation based model is proposed to predict the distribution of workers.A task allocation algorithm based on location prediction is designed to calculate the relative optimal assignment strategy between crowdsourcing workers and spatial tasks.The proposed location prediction method uses graph convolution neural network and ConvLSTM model to predict,which is more accurate and stable than the traditional grid-based location distribution prediction approaches.The heuristic assignment algorithm based on location prediction can complete task allocation in a linear time by combining the predicted location information,which is consistent with the strong timeliness of the space crowdsourcing platform.Extensive experiments are conducted on real datasets to prove the effectiveness of the proposed methods.Compared with the grid-based prediction method,the accuracy of task/worker location prediction is increased by 15.7%and 18.8%,respectively.