FREQUENTLY ASKED QUESTIONS

WHAT EVERYONE ASKS US

Does DocDigitizer provide results in real-time?

No. DocDigitizer is an asynchronous API. All documents have a processing lead time and, once done, results can either be pushed to a callback or queried via API. The maximum lead time will be determined alongside our customer when creating its license. Currently, we have lead times ranging from under 1 minute to under 16 business hours, depending on the use-case.

Can I get only the automatic results without human validation?

Yes. But only for particular use-cases where the information is very structured, and quality is stable. This scenario requires developing an assessment project so that an accuracy study may be undertaken and presented to the customer. There is also a hybrid model available, where the customer receives both the automatic and the curated data for the same documents.

How much time does it take to setup DocDigitizer?

A few hours. The setup of DocDigitizer is defining the expected data schemas (set of document types and their fields) and the generations of an API key. The setup process is done mainly by DocDigitizer’s team, following our customer’s requirements. After this setup process, an API key will be available and ready to process documents

If I have a new document, do I need to run any setup?

Yes. You need to contact your customer success manager and provide him with the new data schema. The new data schema will be added to your license in a few hours.

Let say that my document varies a lot in terms of layout. Do I need to train DocDigitizer with a dataset?

No. No training or specific configurations is needed. DocDigitizer is a managed software as a service. All the training, model improvement, and model setup, is done internally by our team with no customer intervention. For our customers, we provide (near) 100% accurate data from document 1 with No-Code.

Does DocDigitizer process Handwritten Documents?

Yes. We provide support to data capture over handwritten documents

Does the quality of the document impact DocDigitizer’s performance?

Yes. We strongly mitigate the impact of the document quality by having a human-in-the-loop that will act as a quality barrier, ensure that our customer always receives (near) 100% correct data. Nevertheless, if the human cannot read it, the document may be rejected due to low quality.

Are all documents reviewed by humans?

No. Our AI-assisted Human Revision Platform will decide upon each data point if it makes sense for our human data curators to review it. The decision is based on hundreds of features collected throughout the process, such as: Machine Learning Confidence, Similarity, and Performance within similar content, Response Time SLA, Document Quality… Based on those features, that document may require no revision or one or more revisions.

Do I know which documents are reviewed by humans?

No. As a managed service, DocDigitizer is responsible for managing its level of services and process optimization. This is done internally to our operation and not visible to our customers. Our customers will always receive (near) 100% accurate data independent of how the process was internally done.

Is it secure to have humans looking at my documents?

Yes. DocDigitizer’s data curation team follows strict privacy and security guidelines. DocDigitizer has in place GDPR and Data Handling contract that offers our customers a compliance framework completely aligned with the most demanding requirements.

Didn´t find the question you were looking? We have other frequently asked questions below:

Do I need a specific configuration for every supplier format?

No! Our service does not require layout configurations. We ensure the accuracy of the extracted data, regardless of the layout of the incoming documents.

I Don’t See My ERP On The List. Can I Still Use DocDigitizer?

Yes! DocDigitizer provides a set of standard outputs (such as XLS, XML, and CSV) that can be easily integrated within any ERP. Moreover, we can work directly with your IT team or ERP implementor to develop a connector for you.

Is It Possible To Have Access To An API?

Yes! DocDigitizer API is available for free with each license.

How Many Users Can Access The Portal?

Unlimited! We don’t charge per user.

Will DocDigitizer Store My Files After Extraction?

No! DocDigitizer is not a document repository. Files are stored within a specific timeframe to ensure proper data extraction and validation, then they are deleted.

Can I Have The Extracted Data In Real-Time?

No. To ensure that we provide (near) 100% accurate data extraction, each field is thoroughly validated by our review team within under 8 business hours. This is so that you don’t need to have people on your side validating data over and over again.

I Need Some Extra Fields From The Invoice. How Can I Get Them?

Simply contact your account manager and we will add them to your license. They will be available right away.

Is My Data Safe?

Yes! We ensure that all data handling is done under strict compliance with local regulation. We’ve made security and privacy our top priority by following industry best practices to protect all of your data.