Automatically assessing structured data for decision making

1. A computer-implemented method comprising, by a first computer system:

obtaining a first document, the first document comprising a combination of prose, semi-structured text, and standard clauses used in a plurality of similar other documents and defining at least one task to be performed by a user;

applying a plurality of extractors to extract document data having a plurality of data types from the first document, wherein each extractor of the plurality of extractors is configured to extract a corresponding type of the plurality of data types, and wherein each data type is associated with the corresponding extractor of the plurality of extractors and selected from a group consisting of: document structure information, a well known object comprising information previously extracted from one or more of the similar other documents, information about a person, a business object, a time period, an opportunity requirement defined in the first document, and a change to an opportunity document corpus; and

automatically presenting the document data to a user, the document data comprising: an indication of a structure of the document, a substantive effect of at least one well known object in the document, a substantive effect of a clause in the document, the contents of the document, or a combination thereof.

2. The computer-implemented method of claim 1 , wherein the step of applying the plurality of extractors comprises:

applying a first extractor to extract document structure information;

wherein the document data comprises the document structure information.

3. The computer-implemented method of claim 2 , wherein the step of applying the plurality of extractors comprises:

applying a second extractor to identify a well known document object in the first document;

wherein the document data comprises an indication of a substantive effect of the well known document object on the task.

4. The computer-implemented method of claim 3 , wherein the step of applying the plurality of extractors comprises:

applying a third extractor to identify a time period associated with the task;

wherein the document data comprises an indication of the time period.

5. The computer-implemented method of claim 4 , wherein at least two of the plurality of extractors are executed in parallel.

6. The computer-implemented method of claim 1 , wherein the plurality of extractors are executed in parallel.

7. The computer-implemented method of claim 1 , wherein the plurality of extractors are executed serially.

8. The computer-implemented method of claim 1 , further comprising:

receiving a query from a first user for information about the task;

automatically providing a response to the query, the response comprising information automatically extracted from the first document.

9. The computer-implemented method of claim 8 , wherein the response comprises the document data.

10. The system of claim 1 , wherein the processor is further configured to:

receive a query from a first user for information about the task;

automatically provide a response to the query, the response comprising information automatically extracted from the first document.

11. The system of claim 10 , wherein the response comprises the document data.

12. A system comprising:

a computer-readable medium storing a first plurality of documents and data extracted from a second plurality of documents, the second plurality including at least one document not included in the first plurality; and

a processor configured to:

obtain a first document of the plurality of documents, the first document comprising a combination of prose, semi-structured text, and standard clauses used in a plurality of similar other documents and defining at least one task to be performed by a user;

apply a plurality of extractors to extract document data having a plurality of data types from the first document, wherein each extractor of the plurality of extractors is configured to extract a corresponding type of the plurality of data types, and wherein each data type is associated with the corresponding extractor of the plurality of extractors and selected from a group consisting of: document structure information, a well known object comprising information previously extracted from one or more of the similar other documents, information about a person, a business object, a time period, an opportunity requirement defined in the first document, and a change to an opportunity document corpus; and

automatically present the document data to a user, the document data comprising:

an indication of a structure of the document, a substantive effect of at least one well known object in the document, a substantive effect of a clause in the document, the contents of the document, or a combination thereof.

13. The system of claim 12 , wherein the step of applying the plurality of extractors comprises:

applying a first extractor to extract document structure information;

wherein the document data comprises the document structure information.

14. The system of claim 13 , wherein the step of applying the plurality of extractors comprises:

applying a second extractor to identify a well known document object in the first document;

wherein the document data comprises an indication of a substantive effect of the well known document object on the task.

15. The system of claim 14 , wherein the step of applying the plurality of extractors comprises:

applying a third extractor to identify a time period associated with the task;

wherein the document data comprises an indication of the time period.

16. The system of claim 15 , wherein at least two of the plurality of extractors are executed in parallel.

17. The system of claim 12 , wherein the plurality of extractors are executed in parallel.

18. The system of claim 12 , wherein the plurality of extractors are executed serially.