Use of customer data with Document Understanding™

We process documents provided at design time to build or train extractors and classifiers and to run the automation. Some of them rely on machine learning, some of them are rule-based, but in most cases document samples are needed.

We also use the documents transmitted to our services at runtime to perform the Document Understanding™ functionality, primarily digitizing the documents, classifying them, extracting structured data from them, and allowing human in the loop validation in other components of the platform (like Forms, Apps, or Action Center). More information regarding the use and functionalities of Document Understanding can be found in the Introduction page of the Document Understanding user guide.

As part of ensuring the product performs as expected and errors are addressed timely, we may process the documents and configurations provided at design time and at run time for quality assurance of the Document Understanding product, which includes monitoring, testing, evaluating, and measuring the performance of all product functionalities and infrastructure.

We process telemetry data such as usage data, services latency, traffic peaks, documents sizes, as well as user and account identifiers like account ids, tenant ids, or user e-mail addresses to make sure that our platforms operate smoothly and to optimize the user experience based on the feedback and usage patterns we observe. We use data analytics to measure and evaluate the performance of our services.

We process account information such as username, password, etc. in order to provide you with access to the services and to secure your account.

We may process data that you send to us for support or as necessary for troubleshooting issues, in accordance with our Support terms.

We process documents used with the UiPath® platform to enhance and improve the model so that you receive more reliable, simpler, faster outputs, a more intuitive user experience, and a higher automation performance at runtime. We use anonymisation and filtering techniques when using the data for product enhancement.

We do not use data for product improvement if you have a BAA in place, if our contracts forbid it, or if you have submitted a Support ticket requesting an opt-out.

If our agreements allow it, we use anonymised documents sent to the UiPath platform to develop and test new products and features. This helps us provide you with new platform features and product functionalities, which increase the efficiency and self-healing capacity of your automations.