System and method for constructing digital documents
In some aspects described herein, a computer-based system that is capable of constructing digital documents is provided. In some implementations, a machine learning system is provided that learns certain terms within a document. The terms may be, for example, part of a document that forms a legally-binding contract between two entities. In one implementation of the machine learning system, the machine learning system interoperates within a user interface to show predictions of certain terms within the document to the user. Further, the machine learning system may capture user answers relating to certain terms and provide feedback into the system that learns during operation of the system, improving user interactions, accuracy and reducing the number of user interactions.
1. A computer system comprising:
a processor;
a memory;
computer instructions, when executed, cause the computer system to provide a system for managing digital documents, the system for managing digital documents being programmed to:
define a data model defining a hierarchy of terms;
create at least one document, including the hierarchy of terms;
permit a user to selectively choose terms from the hierarchy of terms to form the at least one document;
create an anatomy of the at least one document;
generate a display for a graphical user interface comprising the anatomy and a range of acceptable values for at least one of the terms selectively chosen by the user;
output to the user the display comprising the anatomy and the range of acceptable values for the at least one of the terms selectively chosen by the user;
determine a value for the at least one term selectively chosen by the user within the range of acceptable values;
generate a display for the graphical user interface comprising a natural language version of the at least one document derived from the anatomy and the value for the at least one term selectively chosen by the user; and
output to the user the display comprising the natural language version of the at least one electronic document derived from the anatomy and the value for the at least one term selectively chosen by the user.
2. The system according to claim 1 , wherein the system is configured to compare at least two of the hierarchy of terms based on a relative strength between the at least two terms.
3. The system according to claim 1 , wherein the system is configured to auto-negotiate terms of the at least one document between at least two entities.
4. The system according to claim 3 , wherein the system is adapted to define, for each of the at least two entities, a playbook that identifies parameters by which the at least one document should be negotiated by the system.
5. The system according to claim 1 , wherein the system further comprises a machine learning element that is adapted to suggest at least one term among the hierarchy of terms for inclusion in the at least one document.
6. The system according to claim 5 , wherein the machine learning element is configured to train responsive to user input provided to the system.
7. The system according to claim 6 , wherein the machine learning element is configured to train and adapt responsively to user input provided to the system in a feedback loop.
8. A method comprising acts of:
defining a data model defining a hierarchy of terms associated with electronic documents;
creating at least one electronic document, including the hierarchy of terms; and
permitting, within a computer interface, a user to selectively choose terms from the hierarchy of terms to form the at least one electronic document;
create an anatomy of the at least one electronic document;
generate a display for a graphical user interface comprising the anatomy and a range of acceptable values for at least one of the terms selectively chosen by the user;
output to the user the display comprising the anatomy and the range of acceptable values for the at least one of the terms selectively chosen by the user;
determine a value for the at least one term selectively chosen by the user within the range of acceptable values;
generate a display for the graphical user interface comprising a natural language version of the at least one electronic document derived from the anatomy and the value for the at least one term selectively chosen by the user; and
output to the user the display comprising the natural language version of the at least one electronic document derived from the anatomy and the value for the at least one term selectively chosen by the user.
9. The method according to claim 8 , further comprising an act of comparing, by a computer system, at least two of the hierarchy of terms based on a relative strength between the at least two terms.
10. The method according to claim 8 , further comprising an act of auto-negotiating, by a computer system, terms of the at least one electronic document between at least two entities.
11. The method according to claim 10 , further comprising an act of defining, for each of the at least two entities, a playbook that identifies parameters by which the at least one electronic document should be negotiated by the computer system.
12. The method according to claim 8 , further comprising an act of suggesting, by a machine learning element, at least one term among the hierarchy of terms for inclusion in the at least one electronic document.
13. The method according to claim 12 , further comprising an act of training the machine learning element responsive to user input provided to the system.
14. The method according to claim 13 , further comprising an act of training the machine learning element responsively to user input provided to the system in a feedback loop.
15. A non-transitory computer-readable medium, that when executed by at least one processor, performs a method comprising acts of:
defining a data model defining a hierarchy of terms associated with electronic documents;
creating at least one electronic document, including the hierarchy of terms; and
permitting, within a computer interface, a user to selectively choose terms from the hierarchy of terms to form the at least one electronic document;
create an anatomy of the at least one electronic document;
generate a display for a graphical user interface comprising the anatomy and a range of acceptable values for at least one of the terms selectively chosen by the user;
output to the user the display comprising the anatomy and the range of acceptable values for the at least one of the terms selectively chosen by the user;
determine a value for the at least one term selectively chosen by the user within the range of acceptable values;
generate a display for the graphical user interface comprising a natural language version of the at least one electronic document derived from the anatomy and the value for the at least one term selectively chosen by the user; and
output to the user the display comprising a natural language version of the at least one electronic document derived from the anatomy and the value for the at least one term selectively chosen by the user.