TextXtractor is a pay-per-use service that allows RPA workflows and other apps to ingest and process a wide variety of documents that businesses may be processing manually. TextXtractor plays an important role in Automation and Digital Initiatives for processes that require the exchange of documents in multiple document formats. Incoming documents can be in a structured form, semi-structured form, like an invoice, or in an unstructured document, like an email, business letter or customer complaint.
TextXtractor is an independent SaaS Solution that is available as API and RPA activities for the developer community to use in solving typical document extraction problems. TextXtractor works on a per-page billing model based on utilization to ensure there is no large upfront cost.
TextXtractor includes most of the capabilities included in Amazon Textract, however the primary differences include:
  • TextXtractor’s ability to process structured, semi-structured and unstructured documents as opposed to only semi-structured
  • No vendor lock-in allows clients to switch between Amazon, Microsoft, and Google with ease.
  • Ready to use industry forms including Insurance and Mortgage documents.
  • JSON and XML Transformation to industry interchange formats.
Unstructured data is everywhere. Some examples include email, contracts, and forms. In many RPA Automations, there are opportunities to make them more autonomous by automatically classifying unstructured data and extracting the structured information from it. For example, a common use case is the extraction of information from Insurance Claims forms (which can be structured, semi-structured or completely paper-based). There are many solutions that exist for solving these problems, in most cases, the ideal solution is one that with a pre-trained model that has specific formats of Insurance Claims documents with higher levels of accuracy; TextXtractor is one of those solutions. TextXtractor can be combined with other OCR based tools to process this information, currently has a large number of Insurance forms already pre-trained, and a growing database of pre-trained documents. The use cases are infinite, however, one must understand that most of these tools use supervised machine learning which requires the extensive training of models for each use case.
TextXtractor comes with out-of-the-box support for UIPath, BluePrism and Microsoft Flow Automations. It also includes ready-to-use workflow activities to enable Intelligent Process Automation wherever documents are involved.
TextXtractor comes with a large database of pre-defined documents and formats including ones for industries such as Tax, Healthcare, P&C Insurance, and Mortgage Banking.