2024.10.0

Data de lançamento: 11 de novembro de 2024

Document Understanding™ 2024.10 LTS Release

Novidades

UiPath Extended Languages OCR

We are excited to announce that our latest OCR engine, UiPath Extended Languages OCR, is now in general availability. The new OCR is capable of digitizing documents in over 200 languages, bringing a significant improvement over its predecessor, especially in regards to Chinese, Japanese, and Korean. Additionally, it can process documents in Thai, Vietnamese, all major languages from India, and languages using the Cyrilic alphabet, and Greek.

Pacotes de ML de extração de dados

The following new ML packages are available:

• 709
• 941x
• 9465
• 1040x
• 3949a
• Faturas em hebraico

Melhorias

Pacotes de ML de extração de dados

We've made significant improvements to our document digitization process. Now, when using the UiPath Extended Languages OCR, the output will be regular word boxes instead of individual characters.

UiPath Document Understanding OCR

• Esta versão traz melhorias de precisão e desempenho para reconhecimento de escrita à mão.
• O reconhecimento e a detecção para o Magnetic Ink Character Recognition (MIRC) foram melhorados, trazendo precisão aprimorada, especialmente para verificações.
• Previously, numbers were not recognized in some instances when a space was used as separator. Numbers are now recognized when space is used as separator.
• The confidence score for the UiPath Document Understanding OCR is improved, particularly when used on lower quality images. In workflows where confidence score is used to decide if documents need human validation in Action Center, this may result in an increased number of documents undergoing validation.

Correções de bugs

UiPath Document Understanding OCR

Corrigimos um problema no qual as caixas de anotação eram retornadas horizontalmente, mesmo que alguns documentos estivessem ligeiramente inclinados, causando o desalinhamento na anotação.

Pacotes de ML de extração de dados

We've fixed an issue related to Japanese text while using the Extended Languages OCR. This issue was resulting in several extra spaces appearing in certain situations due to individual character boxes.