digital documents (ZinetroN/Shutterstock.com)

IRS floats plans to digitize more data

To support its ongoing digitalization efforts, the IRS plans to issue solicitations for three technology solutions, or verticals.

In an April 2 request for information, the agency outlined how it will reduce its reliance on paper by extracting machine-readable data from poor-quality paper and digital images, improving document scanning and using artificial intelligence to improve workflow processes.

Pulling machine-readable data from paper documents and low-quality images pose some basic challenges. First, machine-readable data must be extracted from low-resolution images that often reside in multiple legacy systems.  The agency IRS also has a large number of existing paper forms whose varying characteristics – size, paper weight and condition, formatting (some have handwritten responses) and stapled or binder-clipped attachments -- make them challenging to convert to machine-readable data. Plus, the sensitive nature of the data involved make cybersecurity critical. Any proposed solution must be interoperable with IRS’ existing systems and meet agency cybersecurity requirements.

The second vertical aims to improve digital intake and high-speed scanning of documents, ensuring that digital versions, which may not be regularly accessed, are available for enforcement purposes. It also calls for managing the distribution and disposal of physical documents. Currently, the IRS collects both hard-copy documents and digital files that include unstructured data and correspondence. Some of the intake is manual and some is partially digital, so identifying the best workflow process for routing images would likely involve some analysis of the information contained in the images and documents, the IRS said.

Finally, the IRS wants to use artificial intelligence, machine learning and robotic process automation to improve taxpayer experiences. Potential technologies would include chatbots to answer frequently asked questions or a mobile app that recognizes relevant correspondence or tax forms and provides submission or translation options.

The IRS also wants an automated process for analyzing and distributing open source data feeds about cryptocurrencies. The automated process would pull feeds from social media, public records filings and geolocation IP data, for example, via API calls from current IRS partners, for agencywide access.

The RFI has been issued solely for information and planning purposes, the IRS said.

About the Author

Connect with the GCN staff on Twitter @GCNtech.

Featured

  • Records management: Look beyond the NARA mandates

    Pandemic tests electronic records management

    Between the rush enable more virtual collaboration, stalled digitization of archived records and managing records that reside in datasets, records management executives are sorting through new challenges.

  • boy learning at home (Travelpixs/Shutterstock.com)

    Tucson’s community wireless bridges the digital divide

    The city built cell sites at government-owned facilities such as fire departments and libraries that were already connected to Tucson’s existing fiber backbone.

Stay Connected