| Developers: | |
| Date of the premiere of the system: | November, 2020. |
| Technology: | EDMS - Systems of stream recognition, Development tools of applications |
2020: Start of Google Document AI - the platform for extraction of data from accounting and other documentation of the companies
At the beginning of November, 2020 Google provided the new Document AI tool, it allows the enterprises to take automatically information which is contained in digital and printing documents using machine learning. The platform is available in the fact-finding mode.
Google promises to automate process of extraction using the Document AI platform which integrates two the existing service of document handling, Lending DocAI and Procurement DocAI, in the uniform toolbar.
Document AI includes more than ten "processors", previously grouped engines of extraction of data, each of which is optimized for information output from a certain document type. Use of two processors of general purpose, the first - for normal documents, the second - for questionnaires is supposed. Developers also implemented support of auxiliary engines which specialize in extraction of data from financial documentation, for example, it is possible to process requests for issue of loans or the invoice. In the future developers intend to enter support of new processors which will allow to work with other document types.
Document AI also includes the application programming interface for integration into applications of the company.
According to Google, in addition to release of employees for accomplishment of more important tasks, the Document AI tool can also help the enterprises to increase the accuracy of the business information due to reduction of quantity of the errors connected with manual entry of data. So, one user from the Belgian financial technical-company Unifiedpost managed to increase the accuracy of data collection by 250%.
Main competitors of Google in this segment are Amazon Web Services company which offers Textract for information extraction from documents and also Microsoft with the Form Recogniser tool.[1]
Notes
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |