Train with PwC Document Insights our machine learning model and get the data you need. After a short training, our system will automatically extract data from your documents. See here how to get your data step by step.
Create a new project and upload machine-readable PDF files. We support all documents, regardless of the domain.
Start by selecting the data you want to extract. Create as many data points as you need.
Train our machine learning model by confirming or correcting some data point suggestions.
Train until you reach the desired quality for your data analysis. We process the rest of the documents automatically.
Export the data from all documents and download an XLS file. You can add more documents at any time without further training.