SYSTEMS AND METHODS OF DATA MINING TO CUSTOMIZE SOFTWARE TRIAL DEMONSTRATIONS

• US 20160224320A1
• Filed: 01/29/2015
• Published: 08/04/2016
• Est. Priority Date: 01/29/2015
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Jemiolo, Daniel Everett, Cronin, Beau David
• Granted Patent: US 9,805,427 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The technology disclosed describes systems and methods for delivering software trial demonstrations that are customized, with features identified as interesting to a software demonstration candidate, by mining biographical and behavioral data of the candidate. The technology further discloses systems and methods for the customization of trial demonstrations with software usage stories that reflect a software demonstration candidate'"'"'s interests, identified by analyzing mined biographical and behavioral data about the candidate.

Claims

1. A computer implemented system applied to customizing a demonstration of a software suite with numerous features and deployments, the computer implemented system including:

a processor, memory coupled to the processor, and program instructions stored in the memory that implement a method comprising;

obtaining user attributes of a demonstration candidate, including the demonstration candidate'"'"'s role within a company;

obtaining interest attributes extracted from the demonstration candidate'"'"'s browsing history or social media feed that indicate personal interest of the demonstration candidate in entities using the software suite;

using at least some of the user attributes of the demonstration candidate to select a subset of features of the software suite to guide the demonstration candidate through during a software demonstration;

using at least some of the interest attributes of the demonstration candidate to select one or more software usage stories of entities indicated to be of personal interest to the demonstration candidate to profile during the software demonstration; and

customizing the software demonstration for the demonstration candidate with the selected subset of software features and the software usage stories.

2. The computer implemented system of claim 1, further including obtaining at least some of the user attributes by presenting the demonstration candidate with a questionnaire and receiving responses.

3. The computer implemented system of claim 1, further including receiving permission from the demonstration candidate to access at least one social profile of the demonstration candidate and accessing the social profile.

4. The computer implemented system of claim 1, further including accessing and applying at least one rule set that maps the user attributes to subsets of features to select.

5. The computer implemented system of claim 1, further including accessing and applying at least one rule set that maps the interest attributes to software usage stories to select.

6. The computer implemented system of claim 1, further including applying a trained classifier to the user attributes and the interest attributes to select the subset of features and the software usage stories.

7. The computer implemented system of claim 6, further including training the classifier, the method including:

for a test set of data, accessing user attribute and interest attribute data for demonstration users of the software;

for the test set, accessing at least user dwell times during use of particular features and viewing of particular software usage stories by the demonstration users;

using at least the user attribute and interest attribute data as independent variables and at least the user dwell times as dependent variables, training the classifier to select for demonstration candidates a subset of features of the software and to select one or more software usage stories and producing classifier parameters that implement the trained classifier; and

using the classifier parameters for the customizing of the software demonstration.

8. The computer implemented system of claim 1, further including as user attributes of the demonstration candidate at least education, past employment, and assigned territory.

9. The computer implemented system of claim 1, further including as user attributes of the demonstration candidate at least affiliations, endorsements and skills.

10. The computer implemented system of claim 1, further including as user attributes of the demonstration candidate at least product line responsibility.

11. The computer implemented system of claim 1, further including as user attributes of company, other companies that compete with the company.

12. A method of customizing a demonstration of a software suite with numerous features and deployments, the method including:

obtaining user attributes of a demonstration candidate, including the demonstration candidate'"'"'s role within a company and the company'"'"'s business segment;

obtaining interest attributes extracted from the demonstration candidate'"'"'s browsing history or social media feed that indicate personal interest of the demonstration candidate in entities using the software suite;

using at least some of the user attributes of the demonstration candidate to select a subset of features of the software suite to guide the demonstration candidate through during a software demonstration;

using at least some of the interest attributes of the demonstration candidate to select one or more software usage stories of entities indicated to be of personal interest to the demonstration candidate to profile during the software demonstration; and

customizing the software demonstration for the demonstration candidate with the selected subset of software features and the software usage stories.

13. The method of claim 12, further including accessing and applying at least one rule set that maps the user attributes to subsets of features to select.

14. The method of claim 12, further including accessing and applying at least one rule set that maps the interest attributes to software usage stories to select.

15. The method of claim 12, further including applying a trained classifier to the user attributes and the interest attributes to select the subset of features and the software usage stories.

16. The method of claim 15, further including training the classifier, the method including:

for a test set of data, accessing user attribute and interest attribute data for demonstration users of the software;

for the test set, accessing at least user dwell times during use of particular features and viewing of particular software usage stories by the demonstration users;

using at least the user attribute and interest attribute data as independent variables and at least the user dwell times as dependent variables, training the classifier to select for demonstration candidates a subset of features of the software and to select one or more software usage stories and producing classifier parameters that implement the trained classifier; and

using the classifier parameters for the customizing of the software demonstration.

17. A method of training a classifier to customize a software demonstration for a demonstration candidate with a selected subset of software features and one or more software usage stories, the method including:

for a test set of data, accessing user attribute and interest attribute data for demonstration users of a software application;

for the test set, accessing at least user dwell times during use of particular features and viewing of particular software usage stories for the demonstration users;

using at least the user attribute and interest attribute data as independent variables and at least the user dwell times as dependent variables, training the classifier to select for demonstration candidates a subset of features of the software application and to select one or more software usage stories of and producing classifier parameters that implement the trained classifier; and

storing the classifier parameters for later use in customizing a software demonstration for demonstration candidates with the selected subset of software features and the software usage stories.

18. The method of claim 17, further including as user attributes of the demonstration candidate at least education, past employment, and assigned territory.

19. The method of claim 17, further including as user attributes of the demonstration candidate at least affiliations, endorsements and skills.

20. A non-transitory computer readable storage medium that stores program instructions that implement a method of customizing a demonstration of a software suite with numerous features and deployments, the implementation including:

obtaining user attributes of a demonstration candidate, including the demonstration candidate'"'"'s role within a company and the company'"'"'s business segment;

obtaining interest attributes extracted from the demonstration candidate'"'"'s browsing history or social media feed that indicate personal interest of the demonstration candidate in entities using the software suite;

using at least some of the user attributes of the demonstration candidate to select a subset of features of the software suite to guide the demonstration candidate through during a software demonstration;

using at least some of the interest attributes of the demonstration candidate to select one or more software usage stories of entities indicated to be of personal interest to the demonstration candidate to profile during the software demonstration; and

customizing the software demonstration for the demonstration candidate with the selected subset of software features and the software usage stories.

21. The non-transitory computer readable storage medium of claim 20, further including obtaining at least some of the user attributes by presenting the demonstration candidate with a questionnaire and receiving responses.

22. The non-transitory computer readable storage medium of claim 20, further including accessing and applying at least one rule set that maps the user attributes to subsets of features to select.

23. The non-transitory computer readable storage medium of claim 20, further including accessing and applying at least one rule set that maps the interest attributes to software usage stories to select.

24. The non-transitory computer readable storage medium of claim 20, further including applying a trained classifier to the user attributes and the interest attributes to select the subset of features and the software usage stories.

25. The non-transitory computer readable storage medium of claim 24, further including training the classifier, the method including:

for a test set of data, accessing user attribute and interest attribute data for demonstration users of the software;

for the test set, accessing at least user dwell times during use of particular features and viewing of particular software usage stories by the demonstration users;

using at least the user attribute and interest attribute data as independent variables and at least the user dwell times as dependent variables, training the classifier to select for demonstration candidates a subset of features of the software and to select one or more software usage stories and producing classifier parameters that implement the trained classifier; and

using the classifier parameters for the customizing of the software demonstration.