Knowledge Center

Robodox is a PDF data extraction software that can be used for a variety of document processing use-cases. There are, however, a couple of use-cases that work better than others. As a rule of thumb, Robodox is a great fit if you want to process batches of documents that all have a similar layout/structure. Our most successful customer deals with anything between 1 – 100 different document layouts and processes between 50 – 10000 documents per month. Popular document types that can easily be processed with Robodox include:

• Accounts Payable & Invoice Processing and Automation
• Purchase & Sales Orders
• Shipping & Delivery Orders
• Form Based Contracts
• HR & Admin Documents
• Product Catalogues & Price Lists
• Bank Statements
• Fillable PDF Forms
• Various other transactional business documents

What exactly is a parsing rule? A parsing rule is a set of instructions that tells our algorithms what kind of data you are looking for. For example, you can tell our algorithms that you want to extract text from a specific position in your document. Furthermore, you could then add more instructions to the parsing rule, such as formatting a date, cropping and modifying words, etc. Parsing rules come in different forms and we offer many templates to get you started. Typically, some of your parsing rules will be position-based, which means that we will extract your data from a fixed position in your document. Other parsing rules will extract data from a variable position by looking for keyword markers inside the document text or applying pattern matching.

Robodox has been built to bring your data to life. With our intuitive platform, you’ll be able to explore the value hidden in your customer documents quickly and easily. Our combination of template-based spatial data recognition with state-of-the-art AI algorithms is one of the most accurate OCR tools you’ll find. Since we use machine learning to consistently improve our product, the more you use Robodox, the overall confidence level of extraction becomes even more accurate.

OCR, or Optical Character Recognition, is the technology that helps you edit, search and store the information in a scanned document or image. When you use OCR software on a pdf or scanned document, it converts your data into plain text that you can then manipulate and edit in any way you want. We’re all about helping you read and extract the information in your documents and images more efficiently so that you can spend your time solving important business problems, fast.

We built our service with privacy in mind. We believe that your data belongs to you and you decide how long we should store it for you. By default, we store the original files and the parsed data for one month. After that period, we destroy all data associated with the document (original file and the parsed data).

We are committed to cutting down the time it takes for your documents to get processed. Robodox only takes less than a minute to process a document from reception to finished processing in most cases.

The processing speed of your documents might vary when there are multiple pages and OCR or other preprocessing is needed. This includes normalizing scan, auto-rotate scan, etc. Slight variations in processing speed may also occur during unusually high volumes of incoming documents.

Robodox not only offers various options to import documents but also many different ways to export your parsed data. The following options are supported by Robodox:

• Download data of a single document in Excel / CSV / XML or JSON format
• Download data of multiple documents in Excel / CSV / XML or JSON format
• Automatically send extracted data to hundreds of apps through cloud integration (Google Sheets, Zapier, MS Flow, Workato, …)
• Use our HTTP API to poll for parsed data
• Use Webhooks to send parsed data to your own API in real-time

Robodox was primarily designed to process “transactional business documents”, such as invoices, purchase orders, work orders, etc. We try to support all common file formats used to exchange business documents between entities, as well as file formats used by scanning software.

At the time of writing, RObodox can read the following file formats:

• Native PDF documents with text
• Scanned PDF documents with images only
• Microsoft DOCX and DOC files
• JPG image files
• PNG image files
• TIFF image files

If you are having issues extracting the data from an uploaded file we are here to help. You can reach out to us at support@robodox.ai and include the email associated with your Robodox account, the name of the parser you are having problems with, screenshots, details on data you wished to extract, and any other useful information.

Once we have this information your request can be processed quickly and efficiently.

Robodox is designed to have an account with multiple users in it. Therefore, when you register at Robodox your user information is stored as account owner information, which can be updated anytime. The account owner information is used to identify your account when integrating your Robodox account with other integrations such as Zapier. You can update your account owner information by navigating to ‘My Account‘ ‘Account Info‘.

In order to reset your Robodox login password you can use either ‘Forgot Password?‘ link on the login page or simply change your password as shown below by navigating to ‘Change Password‘ by clicking on your username on the top right corner after logging in to your account.