Content subject suggestions

1. A method, comprising:

extracting text within an email body of an email, displayed through an email creation interface to a user for email composition, to generate a set of n-grams;

identifying features of n-grams within the set of n-grams;

utilizing classifiers, trained using a training set of email body text and email subjects, to assign probabilities to the n-grams within the set of n-grams based upon the features, a probability specifying a strength of an n-gram in relation to a user preference of the user for an email subject derived from the n-gram;

identifying a set of target n-grams from the set of n-grams based upon the set of target n-grams having assigned probabilities exceeding a threshold;

identifying a single common theme amongst a plurality of target n-grams within the set of target n-grams, wherein the plurality of target n-grams comprises a first target n-gram associated with the single common theme and a second target n-gram associated with the single common theme, wherein the first target n-gram is different than the second target n-gram;

responsive to identifying the single common theme, generating an email subject suggestion based upon the single common theme; and

providing the email subject suggestion through the email creation interface.

2. The method of claim 1 , wherein the generating an email subject suggestion comprises:

adding one or more words to at least some of the plurality of target n-grams to create a complete phrase as the email subject suggestion.

3. The method of claim 1 , wherein the email subject suggestion comprises a first portion of the first target n-gram and a second portion of the second target n-gram.

4. The method of claim 1 , comprising:

evaluating an attachment to the email to identify one or more n-grams to add into the set of n-grams.

5. The method of claim 4 , wherein the evaluating comprises:

extracting text from the attachment as the one or more n-grams.

6. The method of claim 4 , wherein the evaluating comprises:

extracting text from metadata of the attachment as the one or more n-grams.

7. The method of claim 4 , wherein the attachment comprises an image, and wherein the evaluating comprises:

utilizing an image recognition technique to evaluate the image to identify the one or more n-grams.

8. The method of claim 4 , wherein the attachment comprises audio, and wherein the evaluating comprises:

utilizing a voice recognition technique to evaluate the audio to identify the one or more n-grams.

9. The method of claim 1 , wherein the providing the email subject suggestion comprises:

displaying the email subject suggestion within an email subject input interface during email body composition of the email by the user through the email creation interface.

10. The method of claim 9 , wherein the displaying the email subject suggestion comprises:

displaying the email subject suggestion within the email subject input interface at a first point in time;

responsive to the user modifying the email with a text modification or an attachment modification at a second point in time later than the first point in time, updating the email subject suggestion based upon one or more new n-grams derived from a current state of the email at the second point in time to create a new email subject suggestion; and

displaying the new email subject suggestion within the email subject input interface.

11. The method of claim 1 , wherein the providing the email subject suggestion comprises:

responsive to determining that the user initiated an email send command for the email while the email did not comprise a user specified email subject, providing the email subject suggestion to the user for selective use as the email subject before executing the email send command.

12. The method of claim 1 , comprising:

disabling an email subject input interface for the email; and

providing an option to enable the email subject input interface.

13. The method of claim 1 , wherein the generating an email subject suggestion comprises:

generating an abstract phrase based upon the n-gram as the email subject suggestion.

14. The method of claim 1 , comprising:

identifying a second set of target n-grams having assigned probabilities exceeding the threshold;

generating a set of email subject suggestions based upon the second set of target n-grams; and

providing the set of email subject suggestions through the email creation interface.

15. The method of claim 14 , comprising:

responsive to the user selecting a first email subject suggestion and not a second email subject suggestion, adjusting a first feature used to assign a first probability to a first n-gram used to create the first email subject suggestion.

16. The method of claim 15 , comprising:

responsive to the user selecting the first email subject suggestion and not the second email subject suggestion, adjusting a second feature used to assign a second probability to a second n-gram used to create the second email subject suggestion.

17. The method of claim 1 , wherein a feature comprises at least one of a number of words feature, a proper noun feature, a date feature, a specific action feature, an event feature, a complete phrase feature, a location feature, or an identified person feature.

18. A computing device comprising:

a non-transitory memory containing machine readable medium comprising machine executable code having stored thereon instructions for performing a method; and

a processor coupled to the non-transitory memory, the processor configured to execute the machine executable code to cause the processor to:

train a set of classifiers using a training set of email body text and email subjects to create a set of trained classifiers;

extract text within an email body of an email being composed by a user to generate a set of n-grams;

responsive to the email comprising an attachment, evaluate the attachment to the email to identify one or more n-grams to add into the set of n-grams;

identify features of n-grams within the set of n-grams;

utilize the set of trained classifiers to assign probabilities to the n-grams within the set of n-grams based upon the features, a probability specifying a strength of an n-gram in relation to a user preference of the user for an email subject derived from the n-gram;

identify a set of target n-grams from the set of n-grams based upon the set of target n-grams having assigned probabilities exceeding a threshold;

identify a single common theme amongst a plurality of target n-grams within the set of target n-grams, wherein the plurality of target n-grams comprises a first target n-gram associated with the single common theme and a second target n-gram associated with the single common theme;

responsive to identifying the single common theme, generate an email subject suggestion based upon the single common theme; and

provide the email subject suggestion for the email.

19. The computing device of claim 18 , wherein the machine executable code causes the processor to:

train the set of classifiers using email body text and email subjects of historic emails associated with the user.

20. A non-transitory machine readable medium having stored thereon instructions for performing a method comprising machine executable code which when executed by at least one machine, causes the machine to:

extract content features from content to generate a set of n-grams;

identify features of n-grams within the set of n-grams;

utilize classifiers to assign probabilities to the n-grams within the set of n-grams based upon the features, a probability specifying a strength of an n-gram in relation to a user preference of a user for a content subject derived from the n-gram;

identify a set of target n-grams from the set of n-grams based upon the set of target n-grams having assigned probabilities exceeding a threshold;

identify a single common theme amongst a plurality of target n-grams within the set of target n-grams, wherein the plurality of target n-grams comprises a first target n-gram associated with the single common theme and a second target n-gram associated with the single common theme;

responsive to identifying the single common theme, generate a content subject suggestion based upon the single common theme; and

provide the content subject suggestion to the user.