PRIORITIZATION OF RECIPIENT EMAIL MESSAGES

• US 20100211644A1
• Filed: 02/18/2009
• Published: 08/19/2010
• Est. Priority Date: 02/18/2009
• Status: Active Grant

• Current Assignee: Snap, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: RAHMAN, JAVED, LAVOIE, JASON D.
• Granted Patent: US 8,032,602 B2
• Time in Patent Office: Days
• US Class Current: 709/206
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/226 Delivery according to priorities

Abstract

A conveyed set of recipient email messages can be identified. An event triggering the conveyed set of email message to be prioritized relative to each other can be detected. Responsive to the detected event, a priority score for each of the emails in the conveyed set can be determined based upon recipient specific criteria. The recipient specific criteria can be based upon recipient behavior regarding a set of previous email messages. The priority score can be calculated base upon prioritizing factors determined from patterns discovered in the recipient behavior regarding the set of previous email messages. At least one programmatic action can be performed based upon the determined priority scores of the email messages.

Claims

1. A method for prioritizing a set of email messages comprising:

identifying a conveyed set of recipient email messages;

detecting an event triggering the conveyed set of email messages to be prioritized relative to each other;

responsive to the detected event, determining a priority score for each of the emails in the conveyed set based upon recipient specific criteria; and

performing at least one programmatic action based upon the determined priority scores of the email messages.

2. The method of claim 1, wherein the recipient specific criteria is based upon recipient behavior regarding a set of previous email messages, and wherein the priority score is calculated base upon prioritizing factors determined from patterns discovered in the recipient behavior regarding the set of previous email messages.

3. The method of claim 1, further comprising:

for each of the email messages, parsing a plurality of previously defined tokens from the email messages;

calculating a token score for each of the tokens, wherein the token score is based upon a token probability table computed from recipient behavior regarding a set of previously analyzed email messages; and

determining the priority score based upon a summation of the calculated token scores.

4. The method of claim 3, further comprising:

ascertaining a set of previous email messages and recipient behavior regarding each of the previous email messages, where the set of previous email messages and the recipient behavior are utilized as training data;

quantifying prioritizing factors by analyzing the training data; and

determining the priority score for each of the email messages using the quantified prioritizing factors.

5. The method of claim 4, further comprising:

classifying each email message of the set of previous email messages into a discrete set of defined categories;

parsing tokens present in the email messages of each defined category;

computing a category specific value for each parsed token; and

utilizing the category specific value of each parsed token when quantifying the prioritizing factors.

6. The method of claim 1, wherein the determining of the priority score is based upon at least one of:

values of a recipient specific white/black list;

a rate for responding to a type of content contained in email messages;

a rate of responding to specific senders of email messages; and

a relative position of senders of email messages within a reporting structure.

7. The method of claim 1, wherein the performing of the at least one programmatic action comprises:

presenting at least a portion of the conveyed set of email messages within a user interface of an email application used by a recipient of the email messages, wherein the presentation is ordered by the priority score.

8. The method of claim 1, further comprising:

receiving at least one email message after the performing of the at least one programmatic action, which results in a changed set of recipient email messages;

detecting a second event triggering the changed set of conveyed email messages to be prioritized relative to each other;

responsive to the second event, determining a priority score for each of the emails in the changed set based upon recipient specific criteria; and

performing at least one programmatic action based upon the determined priority scores of the email messages of the changed set.

9. The method of claim 1, wherein the detected event comprises at least one of a user command to prioritize received emails, a quantity of unread email messages in the conveyed set exceeding a previously defined threshold, and an instantiation of an email application configured associated with the set of recipient email messages.

10. The method of claim 1, wherein the recipient specific criteria comprises a rate and frequency of which email messages are received from a sender associated with the each of the recipient email messages.

11. The method of claim 1, wherein the recipient specific criteria comprises a rate and frequency of which email messages are sent by a recipient of the email messages to a sender associated with each of the recipient email messages.

12. The method of claim 1, wherein the recipient specific criteria comprises retention and deletion rates for email historically sent by a sender associated with each of the email messages of the conveyed set.

13. The method of claim 1, wherein the recipient specific criteria comprises a quantity of different messages associated with each of the email messages of the conveyed set, whereby hot threaded discussions are able to have a relatively greater priority score than email messages lacking a discussion thread.

14. The method of claim 1, wherein the recipient specific criteria comprises a semantic content criterion based upon semantic content of at least one of the subject heading and email body of an associated one of the email messages, where the semantic content is compared against previous established content criteria to determine a semantic content criteria score.

15. A computer program product for prioritizing a set of email messages comprising a computer usable medium having computer usable program code embodied therewith, the computer program product comprising:

computer usable program code configured to identify a conveyed set of recipient email messages;

computer usable program code configured to detect an event triggering the conveyed set of email message to be prioritized relative to each other;

computer usable program code configured to, responsive to the detected event, determine a priority score for each of the emails in the conveyed set based upon recipient specific criteria; and

computer usable program code configured to perform at least one programmatic action based upon the determined priority scores of the email messages.

16. The computer program product of claim 15, wherein the recipient specific criteria is based upon recipient behavior regarding a set of previous email messages, and wherein the priority score is calculated base upon prioritizing factors determined from patterns discovered in the recipient behavior regarding the set of previous email messages.

17. The computer program product of claim 15, further comprising:

computer usable program code configured to, for each of the email messages, parse a plurality of previously defined tokens from the email messages;

computer usable program code configured to calculate a token score for each of the tokens, wherein the token score is based upon a token probability table computed from recipient behavior regarding a set of previously analyzed email messages; and

computer usable program code configured to determine the priority score based upon a summation of the calculated token scores.

18. The computer program product of claim 17, further comprising:

computer usable program code configured to ascertain a set of previous email messages and recipient behavior regarding each of the previous email messages, where the set of previous email messages and the recipient behavior are utilized as training data;

computer usable program code configured to quantify prioritizing factors by analyzing the training data; and

computer usable program code configured to determine the priority score for each of the email messages using the quantified prioritizing factors.

19. The computer program product of claim 18, further comprising:

computer usable program code configured to classify each email messages of the set of previous email messages into a discrete set of defined categories;

computer usable program code configured to parse tokens present in the email messages of each defined category;

computer usable program code configured to compute a category specific value for each parsed token; and

computer usable program code configured to utilize the category specific value of each parsed token when quantifying the prioritizing factors.

20. The computer program product of claim 15, wherein the computer usable program code that when executed on a machine is configured to determine the priority score does so based upon at least one of:

values of a recipient specific white/black list;

a rate for responding to a type of content contained in email messages;

a rate of responding to specific senders of email messages; and

a relative position of senders of email messages within a reporting structure.