- Visão geral
- Processo do Document Understanding
- Tutoriais de início rápido
- Componentes do framework
- Pacotes de ML
- Pipelines
- Document Manager
- Serviços de OCR
- Document Understanding implantado no Automation Suite
- Document Understanding implantado no AI Center autônomo
- Aprendizagem profunda
- Treinamento de modelos de alto desempenho
- Licenciamento
- Referências
- UiPath.Abbyy.Activities
- UiPath.AbbyyEmbedded.Activities
- UiPath.DocumentUnderstanding.ML.Activities
- UiPath.DocumentUnderstanding.OCR.LocalServer.Activities
- UiPath.IntelligentOCR.Activities
- UiPath.OCR.Activities
- UiPath.OCR.Contracts
- UiPath.DocumentProcessing.Contracts
- UiPath.OmniPage.Activities
- UiPath.PDF.Activities
Machine Learning Classifier Trainer writes validated data from Classification Station to AI Center dataset storage for creation or update of the Machine Learning Classification model. Prior to using this trainer, create a dataset folder on AI Center. The project and dataset folder names will be used to configure the trainer.
Follow these steps to use the Machine Learning Classifier Trainer:
-
Use the Taxonomy Manager Wizard to define your document types and fields.
-
Drag and drop a Machine Learning Classifier Trainer activity in a Train Classifiers Scope activity.
-
No assistente do classificador com Machine Learning que é aberto automaticamente, forneça as informações da Habilidade de ML e a ApiKey.
- Se você não tiver um classificador de Habilidade de ML, pule para a etapa 5.
-
Click the Get Capabilities button. The wizard closes after this operation.
Observação:Se você estiver criando o modelo de classificador com Machine Learning pela primeira vez (em vez de tentar criar um conjunto de dados para revisar um modelo de ML existente), pule as etapas 3 e 4 e vá para a próxima tela e insira manualmente os nomes das classes de classificação e mapeie-as para os Tipos de documentos declarados no Gerenciador de taxonomia.
-
Enter a value for Project and Dataset.
Observação:The above information pertains to the AI Center project and the dataset within that project to which you wish to send the validated classifier data.
-
Select the Configure Extractors option of the Train Classifiers Scope. A wizard is displayed.
-
The Machine Learning Classifier Trainer is now ready for configuration. For each document type, fill in the textboxes either manually or by selecting, from the available drop-down list, the correct classification field you wish to map to each field. The drop-down list contains all fields that the Machine Learning Classifier Trainer, using the ML Skill entered in the Machine Learning Classifier wizard, declares as classification capability.
-
To check if you are using the latest capabilities of the extractor, you can click the Get or refresh classifier capabilities which opens the Machine Learning Classifier wizard.
-
A seleção de uma das opções em uma lista suspensa confirma automaticamente esse campo.
-
As you pass the document through the workflow containing the Machine Learning Classifier Trainer, the document will get labeled and stored in the appropriate folder on AI Center. You will see a structure like this: