Task Allocation In Crowdsourcing Research Articles

Research on Express Crowdsourcing Task Allocation Considering Distribution Mode under Customer Classification

Research on Express Crowdsourcing Task Allocation Considering Distribution Mode under Customer Classification

Mobile Crowdsourcing Task Allocation Based on Dynamic Self-Attention GANs

Mobile Crowdsourcing Task Allocation Based on Dynamic Self-Attention GANs

Application of clustering cooperative differential privacy in spatial crowdsourcing task allocation

A framework for spatial crowdsourcing task allocation based on centralized differential privacy is proposed for addressing the problem of worker’s location privacy leakage. Firstly, by combining two stages of differential privacy noise addition and clustering matching, a spatial crowdsourcing worker dataset with high differential privacy protection can be obtained; Secondly, the dynamic problem of spatial crowdsourcing task allocation is transformed into a static combinatorial optimization problem by dividing the spatiotemporal units and the “delay matching” strategy; Finally, the improved discrete glowworm swarm optimization algorithm is used to calculate the results of spatial crowdsourcing task allocation. It has been demonstrated that, compared to the direct differential privacy noise-adding assignment method and the discrete glowworm swarm optimization assignment method, the proposed method achieves better task assignment results, with the total travel distance reduced by 12.42% and 3.56%, respectively, and the task assignment success rate increased by 11.75% and 3.34%, respectively.

An Improved Approximation Algorithm for Wage Determination and Online Task Allocation in Crowd-Sourcing

Crowd-sourcing has attracted much attention due to its growing importance to society, and numerous studies have been conducted on task allocation and wage determination. Recent works have focused on optimizing task allocation and workers' wages, simultaneously. However, existing methods do not provide good solutions for real-world crowd-sourcing platforms due to the low approximation ratio or myopic problem settings. We tackle an optimization problem for wage determination and online task allocation in crowd-sourcing and propose a fast 1-1/(k+3)^(1/2)-approximation algorithm, where k is the minimum of tasks' budgets (numbers of possible assignments). This approximation ratio is greater than or equal to the existing method. The proposed method reduces the tackled problem to a non-convex multi-period continuous optimization problem by approximating the objective function. Then, the method transforms the reduced problem into a minimum convex cost flow problem, which is a well-known combinatorial optimization problem, and solves it by the capacity scaling algorithm. Synthetic experiments and simulation experiments using real crowd-sourcing data show that the proposed method solves the problem faster and outputs higher objective values than existing methods.

Bidirectional k-nearest neighbor spatial crowdsourcing allocation protocol based on edge computing.

Spatial crowdsourcing refers to the allocation of crowdsourcing workers to each task based on location information. K-nearest neighbor technology has been widely applied in crowdsourcing applications for crowdsourcing allocation. However, there are still several issues need to be stressed. Most of the existing spatial crowdsourcing allocation schemes operate on a centralized framework, resulting in low efficiency of crowdsourcing allocation. In addition, these spatial crowdsourcing allocation schemes are one-way allocation, that is, the suitable matching objects for each task can be queried from the set of crowdsourcing workers, but cannot query in reverse. In this article, a bidirectional k-nearest neighbor spatial crowdsourcing allocation protocol based on edge computing (BKNN-CAP) is proposed. Firstly, a spatial crowdsourcing task allocation framework based on edge computing (SCTAFEC) is established, which can offload all tasks to edge nodes in edge computing layer to realize parallel processing of spatio-temporal queries. Secondly, the positive k-nearest neighbor spatio-temporal query algorithm (PKNN) and reverse k-nearest neighbor spatio-temporal query algorithm (RKNN) are proposed to make the task publishers and crowdsourcing workers conduct two-way query. In addition, a road network distance calculation method is proposed to improve the accuracy of Euclidean distance in spatial query scenarios. Experimental results show that the proposed protocol has less time cost and higher matching success rate compared with other ones.

Research on incentive strategy based on service quality in spatial crowdsourcing task allocation

In order to further improve the enthusiasm of spatial crowdsourcing workers, considering the service quality of workers, different incentive strategies are proposed and tasks are assigned. Firstly, the incentive model is constructed from the unit time revenue of task and online idle time, and the evaluation function of the evaluation model is constructed; Secondly, the task allocation is transformed into a combinatorial optimization problem by delay matching, and an improved glowworm swarm algorithm is proposed to solve the problem by discrete coding, introducing six kinds of mobile modes, adaptive probability matching and infeasible solution processing; Finally, the algorithm is used to solve the task allocation. The experimental results show that compared with the travel cost minimization strategy and random allocation strategy, the positive incentive index of the proposed strategy is improved by 11.79% and 14.60% respectively, and the fair incentive index is improved by 0.83% and 0.22% respectively, which can effectively improve the positive incentive range and incentive fairness of workers.

Blockchain-based multi-skill mobile crowdsourcing services

With the boom in 5G technology, mobile spatial crowdsourcing has shown great dynamism in industrial mobile communications and edge computing node management. But the traditional crowdsourcing system is not advanced enough to adapt to the new environment. Typically, traditional crowdsourcing workflow is hosted by a centralized crowdsourcing platform. However, the centralized crowdsourcing platform faces the following problems: (1) single point of failure, (2) user privacy leakage, (3) subjective arbitration, (4) additional service fee, and (5) non-transparent task assignment process. To improve those problems, we replaced the centralized crowdsourcing platform with a decentralized blockchain infrastructure. And we analyzed the challenge problems of multi-skilled spatial crowdsourcing tasks in the blockchain crowdsourcing system. In addition, a crowdsourcing task allocation algorithm has been proposed, which implements a transparent task distribution process and can adapt to the computing-constrained environment on the blockchain. Compared with the TSWCrowd blockchain-based crowdsourcing model, our system has a higher task allocation rate under the same conditions. And the experimental result shows our work has good economic feasibility, which decentralizes the crowdsourcing process and significantly reduces the additional consumption of the crowdsourcing process.

Mobile Crowdsourcing Task Allocation with Differential-and-Distortion Geo-Obfuscation

In mobile crowdsourcing, organizers usually need participants’ precise locations for optimal task allocation, e.g., minimizing selected workers’ travel distance to task locations. However, the exposure of users’ locations raises privacy concerns. In this paper, we propose a location privacy-preserving task allocation framework with geo-obfuscation to protect users’ locations during task assignments. More specifically, we make participants obfuscate their reported locations under the guarantee of two rigorous privacy-preserving schemes, differential and distortion privacy, without the need to involve any third-party trusted entity. In order to achieve optimal task allocation with the differential-and-distortion geo-obfuscation, we formulate a mixed-integer non-linear programming problem to minimize the expected travel distance of the selected workers under the constraints of differential and distortion privacy. Moreover, a worker may be willing to accept multiple tasks, and a task organizer may be concerned with multiple utility objectives such as task acceptance ratio in addition to travel distance. Against this background, we also extend our solution to the multi-task allocation and multi-objective optimization cases. Evaluation results on both simulation and real-world user mobility traces verify the effectiveness of our framework. Particularly, our framework outperforms Laplace obfuscation, a state-of-the-art geo-obfuscation mechanism, by achieving up to 47 percent shorter average travel distance on real-world data under the same level of privacy protection.

A novel approach of two-stage three-way co-opetition decision for crowdsourcing task allocation scheme

In the crowdsourcing task allocation scheme, there is an emerging and realistic co-opetition phenomenon. To availably solve the crowdsourcing task allocation problem with co-opetition, this paper designs a two-stage co-opetition model by constructing novel three-way decision (TWD), including a competition-optimization model and a negotiation-cooperation model. Unlike the other studies, the two-stage co-opetition model with TWD can not only protect the profits of the task candidates, but also optimize the overall benefits. Specifically speaking, in the competition-optimization model, we construct an optimization model based on the data envelopment analysis (DEA) method in advance, which maximizes the personal benefit. By integrating information system and the loss function matrix, we consider the linkage of evaluation information and risk information and then improve the original TWD to make an initial allocation. In the negotiation-cooperation model, considering that the relationship among the candidates may influence the task performance, the fuzzy measure is introduced to describe a broader partnership. Meanwhile, we also design two different schemes to coordinate and optimize the best task allocations based on the initial allocation. In order to choose the best scheme, the selection strategy between schemes is further investigated under the guidance of the utility and the loss. Finally, we give an example of a medical supply chain crowdsourcing problem to illustrate and verify our proposed approach.

The user-knowledge crowdsourcing task allocation integrated decision model and genetic matrix factorization algorithm

Given the pattern matching problem between the knowledge in the Expert Knowledge Recommendation System (EKRS) established by the author of this article and user’s expertise knowledge, based on the full consideration of some constraint conditions such as user characteristics, task characteristics and matching eigenvalues, the user-knowledge integrated decision-making mathematical model (UKID) is established by using the crowdsourcing task allocation method and matrix decomposition algorithm. Aiming at the characteristics of slow convergence speed and inaccurate user-knowledge (task) matching of the UKID model in a high-dimensional space, the improved genetic matrix factorization algorithm (GMF) is designed. The genetic matrix algorithm is used to map the high-dimensional spatial data to the low-dimensional characteristic space which can improve the accuracy of task assignment. Through analysis to ‘hereditary property’ under high complexity condition, with the maximum preserved crossover operator and adaptive crossover mutation, GMF not only furthest retains the excellent characteristics of parents and improves the algorithm ‘premature properties’, but also builds up the quality of the simple genetic algorithm’s optimization capabilities and enhances the solution’s accuracy. Finally, the algorithm was experimentally verified with Amazon Public dataset and the real data extracted with EKRS. The experimental results showed that the UKID model and algorithm were applicable and could provide the decision-making guidance for the knowledge crowdsourcing task assignment.

A Fog-Assisted Privacy-Preserving Task Allocation in Crowdsourcing

As a people-centric sensing paradigm, crowdsourcing has attracted considerable attention since it can solve a complicated task by gathering the wisdom of a crowd of workers. To increase the efficiency of task allocating and recruit suitable workers, the crowdsourcing server needs to obtain information related to task content and worker profiles, which poses a threat to privacy leaks of both tasks and workers. Although several privacy-preserving crowdsourcing mechanisms with simultaneously achieving task privacy and worker privacy have been proposed, there are two problems for these schemes, either the ability of workers is not taken into account or they are computationally intensive. To address the above problems simultaneously, fog-assisted privacy-preserving task allocation in crowdsourcing is proposed by means of the advantages of fog computing, which can not only achieve privacy protection of both the task and the worker but also alleviate the workers’ computational burden by offloading partial computation to the fog node. By applying threshold secret sharing technology, the proposed scheme enables that only workers satisfying task requirements can decrypt the task content, which achieves the verification of the workers’ ability and resists the attacks of the greedy workers. Then, rigorous security proofs about privacy properties are given in the proposed scheme. Finally, the proposed scheme is estimated through theoretical analysis and experiments. The experimental results show that compared with the current state-of-the-art scheme, the proposed scheme has more advantages in terms of computational cost and storage overhead. Especially for a worker, it only requires one pairing and two multiplication operations in the decrypting phase.

A trust-aware task allocation method using deep q-learning for uncertain mobile crowdsourcing

Mobile crowdsourcing has emerged as a promising collaboration paradigm in which each spatial task requires a set of mobile workers in near vicinity to the target location. Considering the desired privacy of the participating mobile devices, trust is considered to be an important factor to enable effective collaboration in mobile crowdsourcing. The main impediment to the success of mobile crowdsourcing is the allocation of trustworthy mobile workers to nearby spatial tasks for collaboration. This process becomes substantially more challenging for large-scale online spatial task allocations in uncertain mobile crowdsourcing systems. The uncertainty can mislead the task allocation, resulting in performance degradation. Moreover, the large-scale nature of real-world crowdsourcing poses a considerable challenge to spatial task allocation in uncertain environments. To address the aforementioned challenges, first, an optimization problem of mobile crowdsourcing task allocation is formulated to maximize the trustworthiness of workers and minimize movement distance costs. Second, for the uncertain crowdsourcing scenario, a Markov decision process-based mobile crowdsourcing model (MCMDP) is formulated to illustrate the dynamic trust-aware task allocation problem. Third, to solve large-scale MCMDP problems in a stable manner, this study proposes an improved deep Q-learning-based trust-aware task allocation (ImprovedDQL-TTA) algorithm that combines trust-aware task allocation and deep Q-learning as an improvement over the uncertain mobile crowdsourcing systems. Finally, experimental results illustrate that the ImprovedDQL-TTA algorithm can stably converge in a number of training iterations. Compared with the reference algorithm, our proposed algorithm achieves effective solutions on the experimental data sets.

Software Crowdsourcing Task Allocation Algorithm Based on Dynamic Utility

For crowdsourcing software development, poor matching between the workers' development skills and the requirements for the assigned tasks results in poor quality task completion. In this paper, we propose a dynamic utility task allocation algorithm (DUTA), a software crowdsourcing task allocation algorithm based on the dynamic utility. First, using the attributes provided by the worker registration information, we estimate the initial value of a worker's development abilities based on the attribute weights and levels. Second, the worker's development capabilities are calculated based on his or her history of the completed tasks, including task complexity, quality, and development efficiency. The worker's record of development capability is updated dynamically. Then, based on the skill weights, we calculate the degree to which the task requirements matche the worker's skills. Finally, we take the product of the worker's development ability and the degree of skill matching as the allocation utility, and the total utility is maximized as the optimization goal. To solve the optimal match between tasks and workers, we use the Kuhn-Munkres algorithm with a weighted bipartite graph. Our experimental results showed that DUTA provided good performance in total allocation utility, with a better task allocation success rate than the algorithm based on the user reliability. The DUTA achieved an average allocation accuracy of up to 85.63%, demonstrating that it can guide task assignments effectively.

Crowdsourcing Software Task Assignment Method for Collaborative Development

Software crowdsourcing is an emerging and promising software development model. It is based on the characteristics of Internet community intelligence, which makes it have certain advantages in development cost and product quality. Companies are increasingly using crowdsourcing to accomplish specific software development tasks. However, this development model still faces many challenges. One of the key issues is the collaboration between crowdsourced workers. Developer collaboration is important to software development, but workers in crowdsourcing come from an undefined network community, so it's hard to guarantee that they can work together. This paper focuses on task assignment and uses the active time of workers as the basis of grouping to provide a solution for multi-task to multi-worker allocation. Based on the on-demand distribution model, this paper considers three factors: worker's ability, task module complexity, and worker's active time. First, the workers are divided into multiple collaborative candidate groups based on active time. Then, the Hungarian algorithm is used to select the optimal workers for each module from the collaborative candidate groups of each task, and the coordination candidate group replacement strategy is used to solve the assignment failure problem. Finally completing the assignment of all tasks within an assignment cycle. The experiments have shown that the proposed method increases the total utility by 25% and the success rate of distribution by 30% than the sequential assignment method. The proposed method can give a reasonable solution for software crowdsourcing task allocation based on collaborative development.

Multi-Objective Optimization Based Allocation of Heterogeneous Spatial Crowdsourcing Tasks

With the rapid development of mobile networks and the proliferation of mobile devices, spatial crowdsourcing, which refers to recruiting mobile workers to perform location-based tasks, has gained emerging interest from both research communities and industries. In this paper, we consider a spatial crowdsourcing scenario: in addition to specific spatial constraints, each task has a valid duration, operation complexity, budget limitation, and the number of required workers. Each volunteer worker completes assigned tasks while conducting his/her routine tasks. The system has a desired task probability coverage and budget constraint. Under this scenario, we investigate an important problem, namely heterogeneous spatial crowdsourcing task allocation (HSC-TA), which strives to search a set of representative Pareto-optimal allocation solutions for the multi-objective optimization problem, such that the assigned task coverage is maximized and incentive cost is minimized simultaneously. To accommodate the multi-constraints in heterogeneous spatial crowdsourcing, we build a worker mobility behavior prediction model to align with allocation process. We prove that the HSC-TA problem is NP-hard. We propose effective heuristic methods, including multi-round linear weight optimization and enhanced multi-objective particle swarm optimization algorithms to achieve adequate Pareto-optimal allocation. Comprehensive experiments on both real-world and synthetic data sets clearly validate the effectiveness and efficiency of our proposed approaches.

Complex crowdsourcing task allocation strategies employing supervised and reinforcement learning

Purpose Allocation of complex crowdsourcing tasks, which typically include heterogeneous attributes such as value, difficulty, skill required, effort required and deadline, is still a challenging open problem. In recent years, agent-based crowdsourcing approaches focusing on recommendations or incentives have emerged to dynamically match workers with diverse characteristics to tasks to achieve high collective productivity. However, existing approaches are mostly designed based on expert knowledge grounded in well-established theoretical frameworks. They often fail to leverage on user-generated data to capture the complex interaction of crowdsourcing participants’ behaviours. This paper aims to address this challenge. Design/methodology/approach The paper proposes a policy network plus reputation network (PNRN) approach which combines supervised learning and reinforcement learning to imitate human task allocation strategies which beat artificial intelligence strategies in this large-scale empirical study. The proposed approach incorporates a policy network for the selection of task allocation strategies and a reputation network for calculating the trends of worker reputation fluctuations. Then, by iteratively applying the policy network and reputation network, a multi-round allocation strategy is proposed. Findings PNRN has been trained and evaluated using a large-scale real human task allocation strategy data set derived from the Agile Manager game with close to 500,000 decision records from 1,144 players in over 9,000 game sessions. Extensive experiments demonstrate the validity and efficiency of computational complex crowdsourcing task allocation strategy learned from human participants. Originality/value The paper can give a better task allocation strategy in the crowdsourcing systems.

Infusing Human Factors into Algorithmic Crowdsourcing


 
 
 Algorithmic Crowdsourcing (AC) is an emerging field in which computational methods are proposed to automate cer- tain aspects of crowdsourcing. A number of AC methods have proposed recently in an attempt to address this problem. However, existing AC approaches are based on highly simplified models of worker behaviour which limit their practical applicability. To make efficient utilization of human resources for crowdsourcing tasks, the following tech- nical challenges remain open: Fairness of the solution, temporal changes in behaviour, optimizing wellbeing, and non-compliance by users. For AI researchers to propose effective solutions to these challenges, labelled datasets reflecting various aspects of human decision-making related to task allocation in crowd-sourcing are needed. We construct an anonymized dataset based on player behavior trajectories captured by a multiagent game platform - Agile Manage. It allows players to demonstrate their task delegation strategies under different scenarios based on key characteristics involved in crowdsourcing task allocation. The game adopts implicit human computation in which players contribute data which are valuable for research through informal games.