- Introdução
- Componentes do framework
- Visão geral do treinamento em extração de dados
- Assistente para configurar extratores de Train Extractors Scope
- Machine Learning Extractor Trainer
- Atividades relacionadas ao treinamento em extração de dados
- Document Understanding no AI Center
- Pipelines
- Pacotes de ML
- Gerenciador de Dados
- Serviços de OCR
- Licenciamento
- Referências
Assistente para configurar extratores de Train Extractors Scope
O Assistente para Configurar Extratores acessado por meio do Train Extractors Scope permite que você escolha quais extratores são treinados para cada tipo de documento e campo.
As etapas abaixo descrevem o uso do assistente:
-
Add a Train Extractors Scope activity to your workflow.
-
In the Properties panel, add your custom configurations in the DocumentObjectModel, DocumentPath,DocumentText and HumanValidatedData fields.
-
Drag an Extractor Trainer activity (for instance, Machine Learning Extractor Trainer) or create a custom activity for extractor training by implementing the classes explained and place it inside the Train Extractors Scope activity.
-
Configure your extractors by clicking on the Configure Extractors button.
-
You can now see the Wizard.
-
-
Marque as caixas de seleção dos extratores que deseja ativar.
-
Click the Get of refresh extractor capabilities button, for the extractors that support this functionality, to easily map your taxonomy fields with the available extractor fields, or refresh them in case the extractor fields have changed.
-
To train the extractor based on its extraction result, you can enter any alphanumeric value in the Framework Alias field and then set the exact value in the corresponding Framework Alias field of one or more trainers to create a link between the extractor and the trainer(s).
-
Click on the Save button once all the extractors are selected.