System for reclassification of electronic messages in a spam filtering system

• US 8,782,781 B2
• Filed: 04/05/2010
• Issued: 07/15/2014
• Est. Priority Date: 06/30/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Dulitz, Daniel Wesley, Golub, Seth
• Primary Examiner(s): Kyle, Tamara T
• Assistant Examiner(s): FABBRI, ANTHONY E
• Application Number:
  US12/754,523
• Publication Number:
  US 20100263045A1
• Time in Patent Office: 1,562 Days
• Field of Search: 726/22, 726/21, 726/25, 726/1, 709/206, 709/207, 709/202, 709/224
• US Class Current: 726/22
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/212 using filtering or selective blocking

Abstract

A method for indicating probability of spam for email comprises tracking network traffic characteristics for the email, and comparing the tracked characteristics for the email to characteristics for email from trusted or known spam sources.

Claims

1. A computer implemented method for filtering emails on a server system having one or more processors and memory storing one or more programs for execution by the one or more processors, comprising:

receiving an email to a recipient from a sender;

in response to receiving the email;

determining whether there is a direct relationship between the sender and the recipient; and

(i) when no direct relationship between the sender and the recipient is found, searching for an indirect relationship between the sender and the recipient, and utilizing the existence of the indirect relationship, when found, for determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions associated with the sender; and

(ii) when a direct relationship between the sender and the recipient is found, determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions between the recipient and the sender using one or more non-email applications; and

classifying the email according the identified spam probability.

2. The computer implemented method of claim 1, wherein determining the spam probability further comprises:

combining historical electronic interactions from an email application and historical electronic interactions from the one or more non-email applications to produce a combined condition; and

identifying the spam probability of the email based at least in part on the combined condition.

3. The computer implemented method of claim 1, wherein identifying the spam probability further comprises:

identifying the spam probability of an email based on historical electronic interactions between one or more additional recipients and the sender.

4. The computer implemented method of claim 1, wherein the one or more non-email applications includes a plurality of:

an instant messaging application, an on-line chat application, a file-sharing application, and a collaboration application.

5. The computer implemented method of claim 1, wherein:

the statistical information relating to previous interactions between the recipient and the sender includes one or more of the following;

types of interaction and frequency of interaction.

6. A system, for filtering emails, comprising:

at least one processor; and

memory storing one or more programs to be executed by the at least one processor;

the one or more programs comprising instructions for;

receiving an email to a recipient from a sender;

in response to receiving the email;

determining whether there is a direct relationship between the sender and the recipient; and

(i) when no direct relationship between the sender and the recipient is found, searching for an indirect relationship between the sender and the recipient, and utilizing the existence of the indirect relationship, when found, for determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions associated with the sender; and

(ii) when a direct relationship between the sender and the recipient is found, determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions the recipient and the sender using one or more non-email applications; and

classifying the email according the identified spam probability.

7. The system of claim 6, wherein instructions for determining the spam probability further comprises instructions for:

combining historical electronic interactions from an email application and historical electronic interactions from the one or more non-email applications to produce a combined condition; and

identifying the spam probability of the email based at least in part on the combined condition.

8. The system of claim 6, wherein instructions for identifying the spam probability further comprises instructions for:

identifying the spam probability of an email based on historical electronic interactions between one or more additional recipients and the sender.

9. The system of claim 6, wherein the one or more non-email applications also includes a plurality of:

an instant messaging application, an on-line chat application, a file-sharing application, and a collaboration application.

10. The system of claim 6, wherein:

the statistical information relating to previous interactions between the recipient and the sender includes one or more of the following;

types of interaction, media of interaction, and frequency of interaction.

11. A non-transitory computer readable storage medium storing one or more programs configured for execution by a computer, the one or more programs comprising instructions for:

receiving an email to a recipient from a sender;

in response to receiving the email;

determining whether there is a direct relationship between the sender and the recipient; and

(i) when no direct relationship between the sender and the recipient is found, searching for an indirect relationship between the sender and the recipient, and utilizing the existence of the indirect relationship, when found, for determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions associated with the sender; and

(ii) when a direct relationship between the sender and the recipient is found, determining a spam probability of the email by evaluating statistical information regarding the historical electronic interactions between the recipient and the sender using one or more non-email applications; and

classifying the email according the identified spam probability.

12. The non-transitory computer readable storage medium of claim 11, wherein instructions for determining the spam probability further comprises instructions for:

combining historical electronic interactions from an email application and historical electronic interactions from the one or more non-email applications to produce a combined condition; and

identifying the spam probability of the email based at least in part on the combined condition.

13. The non-transitory computer readable storage medium of claim 11, wherein instructions for identifying the spam probability further comprises instructions for:

identifying the spam probability of an email based on historical electronic interactions between one or more additional recipients and the sender.

14. The non-transitory computer readable storage medium of claim 11, wherein the one or more non-email applications also includes a plurality of:

an instant messaging application, an on-line chat application, a file-sharing application, and a collaboration application.

15. The non-transitory computer readable storage medium of claim 11, wherein:

the statistical information relating to previous interactions between the recipient and the sender includes one or more of the following;

types of interaction and frequency of interaction.