Binary interest vector for better audience targeting

• US 8,214,390 B2
• Filed: 06/03/2009
• Issued: 07/03/2012
• Est. Priority Date: 06/03/2009
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Watfa, Allie K., Nussel, Dale
• Primary Examiner(s): SYED, FARHAN M
• Application Number:
  US12/477,815
• Publication Number:
  US 20100313139A1
• Time in Patent Office: 1,126 Days
• Field of Search: None
• US Class Current: 707/771
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A binary interest vector is herein described, which represents information in a string of bits about user interest in a set of topics. The binary interest vector may represent the interests of a particular user, or the interests of users associated with a particular client machine. Such a binary interest vector can store a large amount of information in a very small space by assigning bit subsets of the string of bits to represent interest in respective topics of the set of topics based on the positions of the bits in the subsets. Additionally, the bits of a particular binary interest vector may include a version indicator identifying the pattern of topics assigned to the bits of the particular vector. The user interest information in a particular binary interest vector may be utilized in selecting content to display to the user that is associated with the particular vector.

Claims

1. A computer-executed method comprising:

detecting first activity, of a user associated with a particular entity, said first activity related to a first topic of a set of topics;

in response to detecting the first activity, modifying a first subset of bits, of a first set of bits associated with the particular entity, to reflect the first activity related to the first topic;

detecting second activity of the user, said second activity related to a second topic of the set of topics;

in response to detecting the second activity, modifying a second subset of bits, of the first set of bits, to reflect the second activity related to the second topic;

wherein the first subset of bits is distinct from the second subset of bits;

wherein the position of each bit of the first subset of bits indicates which topic of the set of topics that the first subset of bits reflects;

wherein the position of each bit of the second subset of bits indicates which topic of the set of topics that the second subset of bits reflects;

wherein a quantity of the first subset of bits is different than a quantity of the second subset of bits;

determining a value for the first topic based, at least in part, on the first subset of bits;

dividing the value for the first topic by a range of values that can be represented by the first subset of bits, to produce a normalized value for the first topic;

selecting a particular content item from a plurality of available content items based at least in part on the first set of bits; and

wherein the step of selecting the particular content item from the plurality of available content items further comprises selecting the particular content item based, at least in part, on the normalized value for the first topic;

displaying the particular content item; and

wherein the method is performed by one or more computing devices.

2. The computer-executed method of claim 1, wherein:

the first set of bits is associated with a version identifier that identifies a first format;

the first set of bits comprises a first plurality of distinct subsets of bits including the first and second subsets of bits; and

a topic represented in a particular subset of bits of the first plurality of distinct subsets of bits is determined according to the first format.

3. The computer-executed method of claim 1, further comprising:

determining a weight for the first topic;

prior to selecting the particular content item, modifying the value for the first topic based at least in part on the weight;

wherein the weight is based, at least in part, on a topic of a content item that is displayed to the user at the time that the particular content item is displayed to the user.

4. The computer-executed method of claim 1, wherein:

the first activity indicates interest of the user in the first topic;

the first activity is one of;

(a) viewing, by the user, a document related to the first topic,

(b) submitting, by the user, a query related to the first topic,

(c) receiving, by the user, a set of search results including a document related to the first topic, and

(d) submitting, by the user, information evidencing interest in the first topic; and

the particular entity is one of;

(a) a user profile,

(b) an Internet Protocol (IP) address, and

(c) a Media Access Control (MAC) address.

5. The computer-executed method of claim 2, further comprising:

generating a second set of bits based on the first set of bits wherein the second set of bits conveys at least the same information as the first set of bits;

associating the second set of bits with a second version identifier that identifies a second format that is different than the first format;

wherein the second set of bits comprises a second plurality of distinct subsets of bits;

wherein each subset of bits of the second plurality of distinct subsets of bits corresponds to a different topic of a second set of topics;

wherein a topic represented in each of the second plurality of distinct subsets of bits, respectively, is determined according to the second format.

6. The computer-executed method of claim 1, further comprising:

receiving an overwrite value for a third subset of bits of the first set of bits; and

modifying the bits of the third subset of bits to represent the overwrite value.

7. The computer-executed method of claim 1, further comprising:

determining a privacy setting for the particular entity; and

based on the privacy setting, performing one of;

discarding the first set of bits, and

overwriting each bit of the first set of bits with zero.

8. The computer-executed method of claim 1, wherein the step of modifying the first subset of bits, of the first set of bits associated with the particular entity, to reflect the first activity related to the first topic further comprises:

determining whether the particular entity is associated with a particular set of bits;

in response to determining that the particular entity is associated with a particular set of bits, checking whether a version of the particular set of bits is current;

in response to determining that the version of the particular set of bits is not current;

generating a modified set of bits based at least in part on the particular set of bits, and

identifying the modified set of bits to be the first set of bits.

10. The computer-executed method of claim 1, wherein the step of determining a value for the first topic bits further comprises adding values of each bit of the first subset of bits together.

11. The computer-executed method of claim 5, further comprising:

identifying a third subset of bits of the second set of bits that represents the first topic; and

causing the third subset of bits to represent a value that is proportional to a value represented by the first subset of bits.

12. The computer-executed method of claim 1, further comprising:

generating a second set of bits based, at least in part, on the first set of bits;

wherein the second set of bits comprises a plurality of distinct subsets of bits;

causing a third subset of bits of the plurality of distinct subsets of bits to reflect a first interest value for a first subtopic of the first topic; and

causing a fourth subset of bits of the plurality of distinct subsets of bits to reflect a second interest value for a second subtopic of the first topic.

9. A computer-executed method comprising:

detecting activity, of a user associated with a particular entity, that indicates interest in a particular topic of a set of topics;

in response to detecting the activity, modifying a particular subset of bits of a set of bits that is associated with the particular entity, the step of modifying the particular subset of bits further comprising;

identifying a format for the set of bits based, at least in part, on a version identifier that is associated with the set of bits, and

determining that the particular topic is associated with the particular subset of bits based, at least in part, on the format for the set of bits;

wherein the set of bits includes a plurality of distinct subsets of bits;

wherein each distinct subset of bits of the plurality of distinct subsets of bits reflects activity related to a different topic of the set of topics;

determining a value for the particular topic based, at least in part, on the particular subset of bits;

dividing the value for the particular topic by a range of values that can be represented by the particular subset of bits, to produce a normalized value for the particular topic;

selecting a particular content item from a plurality of available content items based at least in part on the set of bits;

wherein the step of selecting the particular content item from the plurality of available content items further comprises selecting the particular content item based, at least in part, on the normalized value for the particular topic; and

displaying the particular content item to the user; and

wherein the method is performed by one or more computing devices.

13. A non-transitory computer-readable medium that stores instructions which, when executed by one or more processors, cause:

detecting first activity, of a user associated with a particular entity, said first activity related to a first topic of a set of topics;

in response to detecting the first activity, modifying a first subset of bits, of a first set of bits associated with the particular entity, to reflect the first activity related to the first topic;

detecting second activity of the user, said second activity related to a second topic of the set of topics;

in response to detecting the second activity, modifying a second subset of bits, of the first set of bits, to reflect the second activity related to the second topic;

wherein the first subset of bits is distinct from the second subset of bits;

wherein the position of each bit of the first subset of bits indicates which topic of the set of topics that the first subset of bits reflects;

wherein the position of each bit of the second subset of bits indicates which topic of the set of topics that the second subset of bits reflects;

wherein a quantity of the first subset of bits is different than a quantity of the second subset of bits;

determining a value for the first topic based, at least in part, on the first subset of bits;

dividing the value for the first topic by a range of values that can be represented by the first subset of bits, to produce a normalized value for the first topic;

selecting a particular content item from a plurality of available content items based at least in part on the first set of bits; and

wherein selecting the particular content item from the plurality of available content items further comprises selecting the particular content item based, at least in part, on the normalized value for the first topic; and

displaying the particular content item.

14. The non-transitory computer-readable medium of claim 13, wherein:

the first set of bits is associated with a version identifier that identifies a first format;

the first set of bits comprises a first plurality of distinct subsets of bits including the first and second subsets of bits; and

a topic represented in a particular subset of bits of the first plurality of distinct subsets of bits is determined according to the first format.

15. The non-transitory computer-readable medium of claim 13, further comprising instructions for:

determining a weight for the first topic;

prior to selecting the particular content item, modifying the value for the first topic based at least in part on the weight;

wherein the weight is based, at least in part, on a topic of a content item that is displayed to the user at the time that the particular content item is displayed to the user.

16. The non-transitory computer-readable medium of claim 13, wherein:

the first activity indicates interest of the user in the first topic;

the first activity is one of;

(a) viewing, by the user, a document related to the first topic,

(b) submitting, by the user, a query related to the first topic,

(c) receiving, by the user, a set of search results including a document related to the first topic, and

(d) submitting, by the user, information evidencing interest in the first topic; and

the particular entity is one of;

(a) a user profile,

(b) an Internet Protocol (IP) address, and

(c) a Media Access Control (MAC) address.

17. The non-transitory computer-readable medium of claim 14, further comprising instructions for:

generating a second set of bits based on the first set of bits wherein the second set of bits conveys at least the same information as the first set of bits;

associating the second set of bits with a second version identifier that identifies a second format that is different than the first format;

wherein the second set of bits comprises a second plurality of distinct subsets of bits;

wherein each subset of bits of the second plurality of distinct subsets of bits corresponds to a different topic of a second set of topics; and

wherein a topic represented in each of the second plurality of distinct subsets of bits, respectively, is determined according to the second format.

18. The non-transitory computer-readable medium of claim 13, further comprising instructions for:

receiving an overwrite value for a third subset of bits of the first set of bits; and

modifying the bits of the third subset of bits to represent the overwrite value.

19. The non-transitory computer-readable medium of claim 13, further comprising instructions for:

determining a privacy setting for the particular entity; and

based on the privacy setting, performing one of;

discarding the first set of bits, and

overwriting each bit of the first set of bits with zero.

20. The non-transitory computer-readable medium of claim 13, wherein modifying the first subset of bits, of the first set of bits associated with the particular entity, to reflect the first activity related to the first topic further comprises:

determining whether the particular entity is associated with a particular set of bits;

in response to determining that the particular entity is associated with a particular set of bits, checking whether a version of the particular set of bits is current;

in response to determining that the version of the particular set of bits is not current;

generating a modified set of bits based at least in part on the particular set of bits, and

identifying the modified set of bits to be the first set of bits.

22. The non-transitory computer-readable medium of claim 13, wherein determining a value for the first topic further comprises adding values of each bit of the first subset of bits together.

23. The non-transitory computer-readable medium of claim 17, further comprising instructions for:

identifying a third subset of bits of the second set of bits that represents the first topic; and

causing the third subset of bits to represent a value that is proportional to a value represented by the first subset of bits.

24. The non-transitory computer-readable medium of claim 13, further comprising instructions for:

generating a second set of bits based, at least in part, on the first set of bits;

wherein the second set of bits comprises a plurality of distinct subsets of bits;

causing a third subset of bits of the plurality of distinct subsets of bits to reflect a first interest value for a first subtopic of the first topic; and

causing a fourth subset of bits of the plurality of distinct subsets of bits to reflect a second interest value for a second subtopic of the first topic.

21. A non-transitory computer-readable medium that stores instructions which, when executed by one or more processors, cause:

detecting activity, of a user associated with a particular entity, that indicates interest in a particular topic of a set of topics;

in response to detecting the activity, modifying a particular subset of bits of a set of bits that is associated with the particular entity;

wherein modifying the particular subset of bits further comprises;

identifying a format for the set of bits based, at least in part, on a version identifier that is associated with the set of bits, and

determining that the particular topic is associated with the particular subset of bits based, at least in part, on the format for the set of bits;

wherein the set of bits includes a plurality of distinct subsets of bits;

wherein each distinct subset of bits of the plurality of distinct subsets of bits reflects activity related to a different topic of the set of topics;

determining a value for the particular topic based, at least in part, on the particular subset of bits;

dividing the value for the particular topic by a range of values that can be represented by the particular subset of bits, to produce a normalized value for the particular topic;

selecting a particular content item from a plurality of available content items based at least in part on the set of bits;

wherein selecting the particular content item from the plurality of available content items further comprises selecting the particular content item based, at least in part, on the normalized value for the particular topic; and

displaying the particular content item to the user.