๐ค AI Summary
This study addresses the complex challenge of volunteer task assignment in crowdsourcing scenarios, where fine-grained skill heterogeneity, unstructured profile data, dynamically evolving willingness, and็ชๅ task demands hinder effective allocation. To tackle these issues, this work proposes a novel framework that integrates large language modelโbased semantic preprocessing, an interpretable skill- and willingness-aware matching algorithm, and a blockchain-based execution mechanism. For the first time, the approach synergistically combines semantic intelligence, explainable matching, and decentralized execution to significantly enhance assignment quality and system trustworthiness without requiring on-chain optimization. Experimental results on multiple real-world resume datasets demonstrate a 42.3% improvement in task assignment utility and an increase in task coverage from 0.80 to 0.90.
๐ Abstract
Volunteer crowdsourcing or VCS platforms increasingly support education, healthcare, disaster response, and smart city applications, yet assigning volunteers to complex tasks remains challenging due to fine-grained skill heterogeneity, unstructured profiles, dynamic willingness, and bursty workloads. Existing methods often rely on coarse or keyword-based skill representations, resulting in poor matching quality. We propose a hybrid VCS framework that integrates LLM-assisted semantic preprocessing, an interpretable skill- and willingness-aware assignment engine, and blockchain-enforced execution. The LLM is used only to extract and canonicalize fine-grained skills and preference cues from unstructured resumes and task descriptions, while assignment is performed by a utility-driven matcher that models partial skill coverage and participation likelihood. Smart contracts provide transparent and tamper-resistant enforcement without on-chain optimization overhead. Experiments on diverse resume datasets show a 42.3% improvement in assignment utility over skill-only greedy matching and an increase in task coverage from 0.80 to 0.90. These results highlight the value of combining semantic intelligence, interpretable matching, and decentralized enforcement for effective volunteer-task allocation.