Binary interest vector for better audience targeting
First Claim
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.
5 Assignments
0 Petitions
Accused Products
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.
-
Citations
24 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 10, 11, 12)
-
-
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. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 22, 23, 24)
-
-
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.
-
Specification