[论文解读] Intelligent Document Processing -- Methods and Tools in the real world

Graham A. Cutting, Anne-Françoise Cutting-Decelle|arXiv (Cornell University)|Dec 28, 2021

Currency Recognition and Detection被引用 9

一句话总结

本文针对工业界需求，对智能文档处理（IDP）进行了实用性的分析，评估了商业工具在真实世界发票和表格上的光学字符识别（OCR）、文档分类和数据提取能力。研究展示了当前系统在处理表格方面的局限性，同时指出了工业界对100%准确率的严苛需求与前沿人工智能研究之间的差距，质疑了商业开发周期与学术研究进展之间的对齐程度。

ABSTRACT

The originality of this publication is to look at the subject of IDP (Intelligent Document Processing) from the perspective of an end-user and industrialist and not that of a Computer Science researcher. This domain is one part of the challenge of information digitalisation that constitutes the Industrial Revolution of the twenty first century (Industry 4.0) and this paper looks specifically at the difficult areas of classifying, extracting information and subsequent integration into business processes with respect to forms and invoices. Since the focus is on practical implementation a brief review is carried out of the market in commercial tools for OCR, document classification and data extraction in so far as this is publicly available together with pricing (if known). Brief definitions of the main terms encountered in Computer Science publications and commercial prospectuses are provided in order to de-mystify the language for the layman. A small number of practical tests are carried out on a few real documents in order to illustrate the capabilities of tools that are commonly available at a reasonable price. The unsolved (so far) issue of tables contained in invoices is raised. The case of a typical large industrial company is evoked where the requirement is to extract 100 per cent of the information with 100 per cent reliability in order to integrate into the back-end Enterprise Resource Planning system. Finally a brief description is given of the state-of-the-art research by the huge corporations who are pushing the boundaries of deep learning techniques further and further with massive computing and financial power - progress that will undoubtedly trickle down into the real world at some later date. The paper finishes by asking the question whether the objectives and timing of the commercial world and the progress of Computer Science are fully aligned.

研究动机与目标

• 评估商业可用的IDP工具在企业环境中实际部署的有效性。
• 解决从发票和表格中提取信息的实际挑战，特别是表格识别问题。
• 弥合深度学习学术研究与工业界对100%准确率和可靠性的实际需求之间的差距。
• 为业务和IT岗位的非研究人员阐明技术术语。
• 评估将IDP输出可靠地集成到ERP系统中的可行性。

提出的方法

• 使用价格合理、商业可用的IDP工具，对真实文档进行实际操作测试。
• 查阅公开的市场数据，涵盖OCR、分类和数据提取工具，包括已知的定价信息。
• 提供研究和商业文献中常见技术术语的清晰定义。
• 聚焦于将提取的数据端到端集成到企业后端系统（如ERP）中。
• 在复杂文档布局（特别是发票中的表格）上对工具性能进行基准测试。
• 对比工业界需求与当前深度学习研究的最先进水平。

实验结果

研究问题

• RQ1 商业可用的IDP工具在从真实世界发票和表格中提取数据方面的有效性如何？
• RQ2 当前IDP系统在表格识别方面存在哪些关键局限性？
• RQ3 大型工业企业的性能需求在多大程度上与当前人工智能研究的能力相匹配？
• RQ4 商业工具与深度学习学术研究在开发周期和目标上存在哪些差异？
• RQ5 价格合理、即插即用的IDP工具能否在端到端ERP集成中实现100%的准确率和可靠性？

主要发现

• 当前商业IDP工具在发票中的表格提取方面表现显著不足，构成一个重大未解决的挑战。
• 即使使用先进工具，实现在ERP系统中端到端数据集成的100%准确率和可靠性在实际部署中仍未能实现。
• 工业需求与深度学习学术研究进展之间的差距巨大，工业界需求已超越现有技术能力。
• 市场上的工具在价格和性能上存在差异，但没有一种能完全满足大规模、关键任务型文档处理的需求。
• 研究和商业文档中使用的技术语言和术语常常使非专业人士难以理解实际应用。
• 由大型企业主导的前沿研究正在迅速推进，但短期内不太可能惠及工业用户。