Email spam and junk mail as a vendor reliability signal

• US 9,299,076 B2
• Filed: 03/07/2012
• Issued: 03/29/2016
• Est. Priority Date: 03/07/2012
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Wiltzius, Thomas Christian
• Primary Examiner(s): Eskandarnia, Arvin
• Application Number:
  US13/414,639
• Publication Number:
  US 20150213456A1
• Time in Patent Office: 1,483 Days
• Field of Search: 709/206
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 30/018 Certifying business or products
• CPC Class Codes: H04L 65/1079 of unsolicited session attempts, e.g. SPIT
• CPC Class Codes: H04M 15/8088 involving increased rates, e.g. spam messaging billing differentiation

Abstract

A system and method is disclosed for determining a reliability of an online vendor. One or more groups of undesirable emails (for example, spam) are analyzed to determine a prevalence of a known vendor. A reliability indicator may be determined for the vendor based on the identified prevalence of the vendor in the emails. The reliability indicator may then be provided to a remote application for use in assessing the reliability of the vendor.

Claims

1. A computer-implemented method for determining a reliability of an online vendor, the method comprising:

analyzing one or more groups of received emails designated as undesirable to determine a prevalence of one or more known vendors in content portions of the received emails designated as undesirable;

identifying one or more links in the one or more groups of received emails;

analyzing at least a portion of one or more websites corresponding to the one or more links, wherein the prevalence of the one or more known vendors includes a prevalence of the one or more known vendors in the analyzed one or more websites;

determining one or more reliability indicators for the one or more known vendors based on the identified prevalence of the one or more known vendors in the content portions of the received emails designated as undesirable; and

providing the one or more reliability indicators to an application.

2. The computer-implemented method of claim 1, wherein analyzing the prevalence of the one or more known vendors comprises:

analyzing the one or more groups of emails to determine a prevalence of one or more characteristics associated with the one or more known vendors in the content portions of the received emails.

3. The computer-implemented method of claim 2, wherein the prevalence of the one or more characteristics includes a number of times the characteristic appears in the one or more groups of received emails.

4. The computer-implemented method of claim 2, wherein the prevalence of the one or more characteristics includes a number of emails which include the characteristic.

5. The computer-implemented method of claim 2, wherein the one or more characteristics include at least a portion of an electronic address associated with one or more respective known vendors.

6. The computer-implemented method of claim 2, wherein the one or more characteristics include one or more terms associated with one or more respective known vendors.

7. The computer-implemented method of claim 6, wherein the one or more terms include a name or partial name.

8. The computer-implemented method of claim 2, wherein the one or more characteristics include an image associated with one or more respective known vendors.

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

identifying one or more predetermined untrusted vendors,

wherein the one or more known vendors includes the one or more predetermined untrusted vendors.

10. A non-transitory machine-readable media including instructions thereon that, when executed, perform a method, the method comprising:

identifying one or more vendors that are present in content portions of a plurality of received email messages identified as undesirable;

determining a prevalence in the content portions of the plurality of received email messages of a characteristic associated with the identified one or more vendors;

determining one or more links in one or more of the email messages identified as undesirable;

analyzing one or more online resources corresponding to the one or more links;

for each identified vendor, determining a reliability indicator based on the prevalence of the characteristic in the content portions of the plurality of received email messages and based on a prevalence of the characteristic in the one or more online resources; and

providing one or more of the determined reliability indicators to an application.

11. The non-transitory machine-readable media of claim 10, wherein the step of identifying the one or more vendors in the content portions of the plurality of received email messages comprises:

for each identified vendor, analyzing the content portions of the plurality of received email messages to identify one or more email messages that include the characteristic; and

for each identified email message, associating the email message with a known vendor associated with the corresponding characteristic.

12. The non-transitory machine-readable media of claim 10, wherein the characteristic of the identified vendor includes at least a portion of a name.

13. The non-transitory machine-readable media of claim 10, wherein the characteristic of the identified vendor includes one or more terms associated with the identified vendor.

14. The non-transitory machine-readable media of claim 10, wherein the characteristic of the identified vendor includes one or more images associated with the identified vendor.

15. The non-transitory machine-readable media of claim 10, wherein the plurality of received email messages are identified as undesirable by instructions associated with one or more email accounts responsible for managing the plurality of email messages.

16. The non-transitory machine-readable media of claim 10, wherein determining the reliability indicator comprises:

determining a normalized value representative of a number of times the characteristic appeared in the content portions of the plurality of received email messages compared to other vendors.

17. The non-transitory machine-readable media of claim 10, wherein one or more online resources includes at least a portion of one or more websites.

18. A system, comprising:

a processor; and

a memory, including server instructions that, when executed, cause the processor to;

determine a presence of one or more vendors in content portions of a plurality of received email messages identified as spam;

identify one or more links in the one or more groups of received emails;

analyze at least a portion of one or more websites corresponding to the one or more links;

determine a prevalence of the one or more known vendors in the analyzed one or more websites; and

for each vendor determined to be in the plurality of received email messages,

determine a normalized value representative of a number of times the vendor appeared in the content portions of the plurality of received email messages compared to other vendors, and

provide a representation of the normalized value as a reliability indicator of the vendor to an application used to assess the quality of the identified retailer.