- 概述
- 入门指南
- 构建模型
- 使用模型
- ML 包
- 1040 - ML 包
- 1040 附表 C - ML 包
- 1040 附表 D - ML 包
- 1040 附表 E - ML 包
- 1040x - ML 包
- 3949a - ML 包
- 4506T - ML 包
- 941x - ML 包
- 9465 - ML 包
- ACORD125 - ML 包
- ACORD126 - ML 包
- ACORD131 - ML 包
- ACORD140 - ML 包
- ACORD25 - ML 包
- 银行对账单 - ML 包
- 提单 - ML 包
- 公司注册证书 - ML 包
- 原产地证书 - ML 包
- 检查 - ML 包
- 儿童产品证书 - ML 包
- CMS1500 - ML 包
- 欧盟符合性声明 - ML 包
- 财务报表 (Financial statements) - ML 包
- FM1003 - ML 包
- I9 - ML 包
- ID Cards - ML 包
- Invoices - ML 包
- InvoicesAustralia - ML 包
- 中国发票 - ML 包
- 希伯来语发票 - ML 包
- 印度发票 - ML 包
- 日本发票 - ML 包
- 装运发票 - ML 包
- 装箱单 - ML 包
- 工资单 - ML 包
- 护照 - ML 包
- 采购订单 - ML 包
- 收据 - ML 包
- 汇款通知书 - ML 包
- UB04 - ML 包
- 水电费账单 - ML 包
- 车辆所有权证明 - ML 包
- W2 - ML 包
- W9 - ML 包
- 公共端点
- 支持的语言
- Insights 仪表板
- 数据与安全性
- 许可
- 如何
UiPath® DocPath
The DocPath large language model (LLM) is our latest data extraction model technology, designed to replace current generation models used within UiPath® Document UnderstandingTM. While DocPath operates similarly to previous models, it was trained using a wide variety of documents. This enables it to process common document types with little to no training needed. What sets DocPath LLM apart is its generative architecture, which significantly improves accuracy and simplifies extraction. Additionally, you can also fine-tune the model with your unique datasets.
To gain further insights into the DocPath architecture and the techniques used for training, check the DocPath page from our AI blog.
Currently, UiPath DocPath is only available for US-based tenants. Support for other regions is planned to roll out in early 2025.
DocPath LLM offers numerous enhancements over previous models. It improves accuracy, especially with tables, adapts to various document layouts to reduce annotation efforts, and boosts automation rates.
- Improved accuracy: DocPath LLM delivers a higher accuracy rate and superior F1 score for semi-structured documents such as invoices, receipts, and purchase orders. This ensures precise and consistent data extraction.
- Effortless annotation: The model reduces manual work by only requiring one annotation per document, eliminating the need to annotate each field instance on every page.
- Enhanced automation: With a greater correlation between confidence level and accuracy, DocPath LLM enhances automation rates while reducing the number of documents sent to Action Center for the same accuracy level.
From our internal tests, DocPath outperformed its predecessor in performance. It reduced the false positive rate by around 15%, and the false negative rate dropped by nearly 17%.
The DocPath LLM is available exclusively for Document Understanding modern projects. Despite the introduction of DocPath, all existing project versions will still use current model versions. This ensures a seamless transition without any disruption to ongoing production workflows.
To start training an exisiting document type on DocPath, unconfirm and confirm all fields in a few documents.
The field names you choose can greatly impact the performance of the model. To ensure optimal results, use natural language and proper grammar for field names. You should only use widely recognized acronyms such as Number (No), Account (Acct), Address (Addr), and Apartment (Apt). Currently, only West European languages are supported, so make sure that the chosen field names align with these languages. Refrain from using non-descriptive names, such as "Column 3", unless the document specifically uses that terminology.
- The extracted fields must match exactly with the text in the documents. This process does not include summarization or other types of text analysis.
- Custom training is not applicable for the following document types. If you attempt to use DocPath for these, it will result in an error:
- 中国发票
- 希伯来语发票
- 日本发票