arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.14282cs.LGcs.AIcs.IR
收藏

主动学习在海关人在环检查中的应用

Active Learning for Human-in-the-Loop Customs Inspection

Institute for Basic Science(基础科学研究院);KAIST(韩国科学技术院)

Sundong Kim, Tung-Duong Mai, Sungwon Han, Sungwon Park, Thi Nguyen Duc Khanh, Jaechan So, Karandeep Singh, Meeyoung Cha

摘要:

我们研究了人工智能海关检查场景,其中人工智能辅助算法通过推荐一组待检查的进口货物来支持海关官员。如果检查的物品有欺诈行为,官员可以征收额外的税款。然后将所形成的日志用作连续迭代的附加训练数据。选择首先检查可疑物品可以立即增加海关收入,但这种检查可能不会为了解动态交通模式带来新的见解。另一方面,检查不确定的项目,可以帮助获得新的知识,这将被用作一个补充的培训资源,以更新选择系统。基于从三个国家获得的多年海关数据集,我们证明了一定程度的探索是必要的,以应对贸易数据的领域转移。结果表明,选择可能的欺诈和不确定的项目的混合策略最终将优于剥削的唯一策略。

英文摘要:

We study the human-in-the-loop customs inspection scenario, where an AI-assisted algorithm supports customs officers by recommending a set of imported goods to be inspected. If the inspected items are fraudulent, the officers can levy extra duties. Th formed logs are then used as additional training data for successive iterations. Choosing to inspect suspicious items first leads to an immediate gain in customs revenue, yet such inspections may not bring new insights for learning dynamic traffic patterns. On the other hand, inspecting uncertain items can help acquire new knowledge, which will be used as a supplementary training resource to update the selection systems. Based on multiyear customs datasets obtained from three countries, we demonstrate that some degree of exploration is necessary to cope with domain shifts in trade data. The results show that a hybrid strategy of selecting likely fraudulent and uncertain items will eventually outperform the exploitation-only strategy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑