Machine learning of context of data fields for various document types

Abstract

A method and system learns new forms to be incorporated into an electronic document preparation system. The method and system receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system utilize machine learning in conjunction with the training set data to identify the correct function for each of the data fields of the new form.

Description

RELATED CASES[0001]This application is a Utility application depending from the U.S. provisional patent application filed Jul. 15, 2016 having attorney docket number INTU169813, Ser. No. 62 / 362,688, and entitled “SYSTEM AND METHOD FOR MACHINE LEARNING OF CONTEXT OF LINE INSTRUCTIONS FOR VARIOUS DOCUMENT TYPES,” which is hereby incorporated herein by reference in its entirety as if the contents were presented herein directly.BACKGROUND[0002]Many people use electronic document preparation systems to help prepare important documents electronically. For example, each year millions of people use electronic tax return preparation systems to help prepare and file their tax returns. Typically, electronic tax return preparation systems receive tax related information from a user and then automatically populate the various fields in electronic versions of government tax forms. Electronic tax return preparation systems represent a potentially flexible, highly accessible, and affordable source ...

AI Technical Summary

Benefits of technology

[0007]Embodiments of the present disclosure address some of the shortcomings associated with traditional electronic document preparation systems by providing methods and systems for incorporating new or updated forms by utilizing machine learning in conjunction with training set data. In particular, embodiments of the present disclosure receive form data related to a new form that includes data fields to be completed in accordance with specific functions designated by the new form. Embodiments of the present disclosure determine one or more possible dependencies for each data field. Embodiments of the present disclosure utilize machine learning to quickly and accurately determine the correct function needed to complete each data field of the form. Embodiments of the present disclosure gather training set data that includes previously filled forms related to the new form in order to assist in the machine learning process. The machine learning process for learning and incorporating the new form includes generating candidate functions for each data field of the new form based on the possible dependencies. The candidate functions can include one or more operators selected from a set or superset of operators. The machine learning process applies the candidate functions to the training set data in order to determine the accuracy of the candidate functions. For each data field, embodiments of the present disclosure generate and apply candidate functions in successive iterations until a candidate function is found that produces test data that matches the data values in the corresponding completed data fields of the previously filled forms of the training set data within a threshold level of error. Embodiments of the present disclosure then output results data that indicates that the correct function for a particular data field has possibly been found. This process is repeated for each selected data field of the new form until all selected data fields of the new form have been learned and incorporated. In this way, embodiments of the present disclosure provide a more reliable electronic document preparation system that quickly, efficiently, and reliably learns and incorporates new forms.

Problems solved by technology

However, the processes that enable the electronic tax return preparation systems to incorporate new tax forms into the tax return preparation systems often utilize large amounts of human and computing resources.

If a tax form changes, or a new tax form is introduced, it can be very difficult to efficiently update the electronic tax return preparation system to correctly populate the various fields of the tax forms with the requested values.

These functions range from very simple to very complex.

This can lead to delays in releasing an updated version of the electronic tax return preparation system as well as considerable expenses.

These expenses are then passed on to customers of the electronic tax return preparation system, as are the delays.

Furthermore, these processes for updating electronic tax returns can introduce inaccuracies into the tax return preparation system.

These expenses, delays, and possible inaccuracies can have an adverse impact on traditional electronic tax return preparation systems.

Customers may lose confidence in the electronic tax return preparation systems.

These issues and drawbacks are not limited to electronic tax return preparation systems.

Any electronic document preparation system that assists users to electronically fill out forms or prepare documents can suffer from these drawbacks when the forms are updated or new forms are released.

In some cases, it may not be feasible to obtain relevant historical tax related data related to previously filed tax returns to assist in the machine learning process of a new tax form.

Images