System and method for automatically generating calculations for fields in compliance forms

A computing system implemented method for learning and incorporating new forms in an electronic document preparation system, the method comprising:

• generating structured form data by analyzing form data related to a new form having a plurality of data fields, the structured form data identifying the data fields of the new form and context data related to the data fields of the new form;
• gathering training set data related to previously filled forms, each previously filled form having completed data fields that each correspond to a respective data field of the new form;
• generating, for a first selected data field of the plurality of data fields of the new form, first candidate function data including a first set of candidate functions based on a first analysis process;
• generating, for the first selected data field of the plurality of data fields of the new form, second candidate function data including a second set of candidate functions based on a second analysis process;
• generating, for each candidate function of the first and second sets, test data by applying the candidate function to the training set data;
• comparing the test data to the training set data;
• selecting one or more of the candidate functions as acceptable candidate functions for the first selected data field based on how closely the test data for each candidate function matches data values in the completed data fields of the previously filled forms that correspond to the first selected data field;
• and
• outputting results data indicating the one or more acceptable functions.

A system for learning and incorporating new forms in an electronic document preparation system, the system comprising:

• at least one processor;
• and
• at least one memory coupled to the at least one processor, the at least one memory having stored therein instructions which, when executed by any set of the one or more processors, perform a process including:
• receiving, with an interface module of a computing system, form data related to a new form having a plurality of data fields;
• generating, a form analysis module of a computing system, structured form data by analyzing the new form, the structured form data identifying the data fields of the new form and context data related to context describing the data fields of the new form;
• gathering, with a data acquisition module of a computing system, training set data related to previously filled forms, each previously filled form having completed data fields that each correspond to a respective data field of the new form;
• generating, with a machine learning module of a computing system and for a first selected data field of the plurality of data fields of the new form, first candidate function data including a first set of candidate functions by performing a machine learning process;
• generating, with a natural language parsing module of a computing system and for the first selected data field of the plurality of data fields of the new form, second candidate function data including a second set of candidate functions by performing a natural language parsing process on the context data related to the first selected field;
• generating, with a historical instructions analysis module of a computing system, for the first selected data field of the plurality of data fields of the new form, third candidate function data including a third set of candidate functions by analyzing historical software instructions for providing a data value for a data field of a historical form related to the new form;
• generating, with an evaluator module of a computing system, for each candidate function of the first, second, and third sets, test data by applying the candidate function to the training set data;
• comparing, with the evaluator module, the test data to the training set data;
• and
• selecting, with the evaluator module, one or more of the candidate functions as acceptable candidate functions for the first selected data field based on how closely the test data for each candidate function matches data values in the completed data fields of the previously filled forms that correspond to the first selected data field;
• and
• outputting, with the evaluator module, results data indicating the one or more acceptable functions.

A non-transitory computer-readable medium having a plurality of computer-executable instructions which, when executed by a processor, perform a method for learning and incorporating new forms in an electronic document preparation system, the instructions comprising:

• an interface module configured to receive form data representing to a new form having a plurality of data fields;
• a form analysis module configured to generate structured form data by analyzing the new form, the structured form data identifying the data fields of the new form and context data related to context describing the data fields of the new form;
• a data acquisition module configured to gather training set data related to previously filled forms, each previously filled form having completed data fields that each correspond to a respective data field of the new form;
• a first data field analysis module configured to generate first candidate function data including one or more candidate functions for each selected data field from the plurality of data fields of the new form;
• a second data field analysis module configured to generate second candidate function data including one or more candidate functions for each selected data field from the plurality of data fields of the new form;
• and
• an evaluator module configured to identify, for each selected data field of the new form, one or more acceptable candidate functions from the first and second candidate function data by generating test data by applying the candidate functions to the training set data and ranking the candidate functions for each selected data field based on how closely the test data for each candidate function matches corresponding data values in the training set data.