| With the rapid development of 5G technology,spatial crowdsourcing platform has been widely used,but at the same time,traffic location privacy leakage has been caused.Therefore,in the spatial crowdsourcing platform,how to efficiently allocate tasks while ensuring users’ traffic location privacy security is an important social problem to be solved urgently.This paper conducts in-depth research from two aspects: spatial crowdsourcing task allocation and location privacy protection,and a spatial crowdsourcing task allocation research mechanism based on location privacy protection is proposed.The main work and results are as follows:(1)Aiming at the problem that most of the existing allocation protocols run on centralized architecture,which leads to low efficiency,a Bidirectional K-Nearest Neighbor Spatial Crowdsourcing Allocation Protocol Based on Edge Computing is proposed.Firstly,a spatial crowdsourcing task allocation system model based on edge computing is constructed,and tasks are sent to edge nodes for processing,so as to realize parallel processing of task allocation.Secondly,the K-nearest neighbor algorithm is improved,and the positive K-nearest neighbor spatial-time query algorithm and reverse K-nearest spatial-time query algorithm are proposed,so that task publishers and crowdsourcing workers can conduct two-way query.Finally,a calculation method of road network distance is proposed to improve the accuracy of Euclidean distance in spatial query scenario.Experimental results show that the proposed protocol has lower time cost and higher matching success rate.(2)In order to solve the problem that the location privacy of crowdsourcing participants is easy to be leaked in the road network environment,a Spatial Crowdsourcing Allocation Strategy Based on Migration Privacy Protection Technology is designed.Firstly,the road network area is divided,and the task assignment calculation is limited to a certain road network range to reduce the calculation cost.Secondly,the location coordinates of traffic network data and spatial crowdsourcing participants are offset to avoid revealing the real location.Finally,based on the pathfinding algorithm,a road network distance calculation method is proposed,which can accurately calculate the road network distance between the crowdsourced participants without disclosing the real locations.The experimental results show that the proposed strategy has lower time cost and higher success rate of location privacy anonymity.(3)Aiming at the problem that the existing task security allocation schemes fail to consider the sensitive location of users,which leads to the inability to resist inference attacks,a Spatial Crowdsourcing Security Allocation Scheme Based on Non-Sensitive Hidden Ring is proposed.Firstly,the position of task publisher is processed safely,and the non-sensitive hidden ring construction algorithm is proposed,so that the generalization region of task publisher position does not contain sensitive position.Secondly,the location of the crowdsourced workers is processed safely.The network embedding technology is used to crowdsource the location of the workers for high-dimensional transformation,and the Paillier homomorphic encryption is used for encryption.Finally,the nearest neighbor candidate set generation algorithm is proposed in the query processing stage,and the nearest neighbor worker set of the non-sensitive hidden ring is obtained.The crowdsourcing worker closest to the task publisher can be decrypted and screened to secure the crowdsourcing.Theoretical and experimental analysis show that the proposed scheme can not only resist inference attacks,but also has better generalization effect and nearest neighbor query efficiency.In summary,aiming at the problems of spatial crowdsourcing allocation efficiency to be improved and location privacy leakage,a crowdsourcing allocation protocol and two secure allocation methods based on location privacy protection are proposesd in this paper,which protect location privacy while implementing crowdsourcing intelligent services. |
