Telephone Caller Classification

• US 20120015639A1
• Filed: 09/26/2011
• Published: 01/19/2012
• Est. Priority Date: 05/26/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Trivi, Jean-Michel, Nelissen, Marco
• Granted Patent: US 8,325,900 B2
• Time in Patent Office: Days
• US Class Current: 455/415
• CPC Class Codes: H04M 2203/553 Data upload
• CPC Class Codes: H04M 2203/651 Text message transmission triggered by call automatic reactions in messaging within packet-switching networks H04L51/02
• CPC Class Codes: H04M 3/436 Arrangements for screening incoming calls , i.e. evaluating the characteristics of a call before deciding whether to answer it based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; diversion H04M3/54

Abstract

In general, the subject matter described in this specification can be embodied in methods, systems, and program products for identifying telephone spam. An indication of an incoming telephone call and a calling device telephone number for the incoming telephone call is received. An indication that the calling device telephone number has been determined to be a source of telephone spam based on identifications by one or more users, other than a user of a mobile telephone, that the calling device telephone number is a source of telephone spam is received. A secondary alert is output to the user of the mobile telephone that is different than a default alert. The default alert is output to the user of the mobile telephone if the calling device telephone number is not determined to be a source of telephone spam.

Claims

1. A computer-implemented method of identifying that an incoming telephone call originating from a first telephone number and directed to a second telephone number is or potentially is from a source of telephone spam, the method comprising:

identifying, by a computing system having a processor and memory, individuals that are within a predetermined distance in a social network graph of a person associated with the second telephone number;

accessing a plurality of classifications associated with previous calls from the first telephone number, wherein;

the classifications are submitted by the identified individuals, and

a classification indicates whether or not a previous call from the first telephone number was from a source of telephone spam;

identifying one or more of the plurality of classifications that indicates that a previous call from the first telephone number was from a source of telephone spam;

determining a weight for each of the identified one or more classifications, wherein a weight depends on a relative distance in the social network graph between an individual who submitted the classification and the person associated with the second telephone number;

combining the determined weights;

determining that the combined weights exceed a predetermined threshold;

determining that the incoming telephone call is or potentially is from a source of telephone spam based on the determination that the combined weights exceed a threshold; and

providing to a telephone associated with the second telephone number an indication that the incoming call is or potentially is from a source of telephone spam based on the determinination that the incoming telephone is or potentially is from a source of telephone spam.

2. The method of claim 1 wherein the social network graph represents relationships between subscribers to a telephone spam identification service.

3. The method of claim 2 wherein first and second subscribers to the spam identification service are considered by the computing system to be related and separated by a first predetermined distance in the social network graph if the second subscriber is listed in an electronic telephone contact book of the first subscriber.

4. The method of claim 3 wherein the first subscriber and a third subscriber to the spam identification service are considered by the computing system to be related and separated by a second predetermined distance greater than the first predetermined distance if the third subscriber is listed in an electronic telephone contact book of the second subscriber.

5. The method of claim 2 wherein first and second subscribers to the spam identification service are considered by the computing system to be related and separated by a first predetermined distance in the social network graph if the first subscriber has accepted a request by the second subscriber to view a profile of the first subscriber in a social network.

6. The method of claim 2 wherein first and second subscribers to the spam identification service are considered by the computing system to be related and separated by a first predetermined distance in the social network graph if the first subscriber has called the second subscriber or sent a text message to the second subscriber during a particular time frame.

7. The method of claim 2 wherein determining a weight for each of the classifications is based on a number of relationships in the social network graph between the person associated with the second telephone number and the individual who submitted the classification.

8. The method of claim 7 wherein determining a weight for each of the classifications is also based on a strength of relationship between the person associated with the second telephone number and the individual who submitted the classification.

9. The method of claim 8 wherein the strength of relationship is based on a frequency of communications between the person associated with the second telephone number and the individual who submitted the classification.

10. The method of claim 2 wherein first and second subscribers to the spam identification service are considered by the computing system to be related and separated by a first predetermined distance in the social network graph only if there has been a reciprocal communication between the first and second subscribers.

11. A computer system for identifying that an incoming telephone call originating from a first telephone number and directed to a second telephone number is or potentially is from a source of telephone spam, the computer system comprising:

a first data structure storing first information about a social network graph;

a second data structure storing second information relating to previous calls from the first telephone number, wherein the second information includes classifications by individuals that are within a predetermined distance in the social network graph of a person associated with the second telephone number;

a processor; and

memory storing instructions that, if executed by the processor, cause the computer system to;

access the plurality of classifications;

determine a weight for at least some of the classifications that indicate that a previous call from the first telephone number was from a source of telephone spam, wherein a weight depends on a relative distance in the social network graph between an individual who submitted the classification and the person associated with the second telephone number;

combine the weights for at least some of the classifications that indicate that a previous call from the first telephone number was telephone spam;

determine whether the combined weights exceed a threshold;

determine whether the incoming telephone call is or potentially is from a source of telephone spam based on a result of determining whether the combined weights exceed a threshold; and

cause an alert indicating that the incoming call is or potentially is from a source of telephone spam to be sent to a telephone associated with the second telephone number if it is determined that the incoming telephone call is or potentially is from a source of telephone spam.

12. The system of claim 11 wherein the social network graph represents relationships between subscribers to a spam identification service.

13. The system of claim 12 wherein at least some of the relationships represented in the social network graph are based on prior occurrence of e-mail communications between subscribers, telephone calls between subscribers, or text messages between subscribers.

14. The system of claim 12 wherein the weight for at least some of the classifications is based on a type of relationship between the individual who submitted the classification and the person associated with the second telephone number.

15. The system of claim 12 wherein the weight for at least some of the classifications is based on a frequency of interaction between the individual who submitted the classification and the person associated with the second telephone number.

16. The system of claim 15 wherein the frequency of interaction is based on a frequency of any combination of telephone calls, electronic text messages, voicemail messages and e-mail messages between the individual who submitted the classification and the person associated with the second telephone number.

17. A non-transitory computer-readable medium encoded with a computer program comprising instructions that, if executed, operate to cause the computer system to perform operations for indicating that an incoming telephone call originating from a first telephone number and directed to a second telephone number is or potentially is from a source of telephone spam, the operations comprising:

accessing a plurality of classifications by individuals that are within a predetermined distance in a social network graph of a person associated with the second telephone number;

determining a weight for at least some of the classifications that indicate that a previous call from the first telephone number was from a source of telephone spam, wherein a weight depends on a relative distance in the social network graph between an individual who submitted the classification and the person associated with the second telephone number;

combining the weights for at least some of the classifications that indicate that a previous call from the first telephone number was telephone spam;

determining whether the combined weights exceed a threshold;

determining whether the incoming telephone call is or potentially is from a source of telephone spam based on a result of determining whether the combined weights exceed a threshold; and

causing an alert indicating that the incoming call is or potentially is from a source of telephone spam to be sent to a telephone associated with the second telephone number if it is determined that the incoming telephone call is or potentially is from a source of telephone spam.

18. The medium of claim 17 wherein the weight for at least some of the classifications is based on a type of relationship between the individual who submitted the classification and the person associated with the second telephone number.

19. The medium of claim 17 wherein the weight for at least some of the classifications is based on a frequency of interaction between the individual who submitted the classification and the person associated with the second telephone number.

20. The medium of claim 19 wherein the frequency of interaction is based on a frequency of any combination of telephone calls, electronic text messages, voicemail messages and e-mail messages between the individual who submitted the classification and the person associated with the second telephone number.

21. The medium of claim 17 wherein the weight for at least some of the classifications is based on frequency of communications between the person associated with the second telephone number and the individual who made the classification.

22. A computer system for identifying that an incoming telephone call originating from a first telephone number and directed to a second telephone number is or potentially is from a source of telephone spam, the computer system comprising:

a processor;

memory;

one or more data structures storing first information about a social network graph and storing second information relating to previous calls from the first telephone number, wherein the second information includes classifications by individuals that are within a predetermined distance in the social network graph of a person associated with the second telephone number;

a telephone spam determination unit operable to receive a request from a mobile telephone to determine if a calling number is or potentially is a source of telephone spam, wherein the telephone spam determination unit is operable in response to receiving the request to;

access the plurality of classifications;

determine a weight for at least some of the classifications that indicate that a previous call from the first telephone number was from a source of telephone spam, wherein the weight depends on a relative distance in the social network graph between an individual who submitted the classification and the person associated with the second telephone number;

combine the weights for at least some of the classifications that indicate that a previous call from the first telephone number was from a source of telephone spam and determine whether the combined weights exceed a threshold;

determine whether the incoming telephone call is or potentially is a source of telephone spam based on a result of determining whether the combined weights exceed a threshold; and

cause an alert indicating that the incoming call is or potentially is a source of telephone spam to be sent to a telephone associated with the second telephone number if it is determined that the incoming telephone is or potentially is from a source of telephone spam.

23. The system of claim 22 wherein the telephone spam determination unit is operable to determine a weight for one of the classifications based on a number of relationships in the social network graph between the person associated with the second telephone number and the individual who submitted the classification.

24. The system of claim 22 wherein the telephone spam determination unit is operable to determine a weight for one of the classifications based on a strength of relationship between the person associated with the second telephone number and the individual who submitted the classification.

25. The system of claim 24 wherein the strength of relationship is based on a frequency of communications between the person associated with the second telephone number and the individual who submitted the classification.

26. The system of claim 22 wherein first and second subscribers to the spam identification service are considered by the telephone spam determination unit to be related and separated by a first predetermined distance in the social network graph only if there has been a reciprocal communication between the first and second subscribers.