- Primeros pasos
- Componentes de marco
- Resumen de la clasificación de documentos
- Asistente para Configurar clasificadores de Clasificar ámbito de documento
- Clasificador basado en palabras clave
- Clasificador inteligente de palabra clave
- Clasificador de CapturaFlexible
- Clasificador de aprendizaje automático
- Actividades relacionadas con la clasificación de documentos
- Visión general de clasificación de documentos
- Asistente para Configurar clasificadores de Entrenar el alcance de los clasificadores
- Entrenador del clasificador de aprendizaje automático
- Actividades relacionadas con la validación de clasificación de documentos
- Paquetes ML
- Procesos
- Gestor de datos
- Servicios de OCR
- Document Understanding implementado en Automation Suite
- Document Understanding implementado en AI Center independiente
- Aprendizaje profundo
- Licencia
- Referencias
- Actividades.DeUipath
- 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.
-
En el asistente Clasificador con aprendizaje automático que se abre automáticamente, proporciona la información de la habilidad ML y la Clave API.
Si no tienes una Habilidad ML del clasificador, ve al paso 5.
-
Click the Get Capabilities button. The wizard closes after this operation.
Nota:If you are creating the Machine Learning Classifier model for the first time (as opposed to trying to create a dataset to revise an existing ML model), skip steps 3 and 4 and just proceed to the next screen and manually enter the names of classification classes and map them to the Document Types declared in the Taxonomy Manager.
-
Enter a value for Project and Dataset.
Nota: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.
-
Al seleccionar una de las opciones de una lista desplegable se confirma automáticamente ese 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: