IP Library Granted Patent US 11,048,764
Granted Patent B2
US 11,048,764 · App. 15/394,995 · Granted Jun 29, 2021

Managing under—and over-represented content topics in content pools

Inventors: Michael Carey Wexler (Mountain View, CA); Don Matheson (Denver, CO)
Assignee: Verizon Media Inc.
G06F16/9535G06F16/954
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,048,764
App. No.
15/394,995
Granted
Jun 29, 2021
Kind
B2
Abstract

The present teaching, which includes methods, systems and computer-readable media, relates to techniques to manage representation of a content topic in a content pool. The disclosed techniques may include determining availability of content related to the content topic based on a set of content items in the content pool, and determining a level of interest of a set of users in the content topic based at least on information related to interaction of the set of users with the set of content items. A level of representation of the content topic in the content pool may be determined based at least on the determined availability of content and the determined level of interest. Based on the level of representation, at least some of the set of content items related to the content topic may be updated, e.g., content items may be added to or removed from the content pool.

Claims (88)

1. A method to manage representation of a content topic, implemented on a machine having a processor, a storage unit, and a communication platform capable of making a connection to a network, the method comprising:

determining, using the processor, for each of a plurality of content topics, a number of content items in a content pool classified as being related to the content topic;

determining, using the processor, a level of interest of a set of users in each of the plurality of content topics based on information related to interactions of the set of users with the content items in the content pool;

determining, using the processor, a level of representation of each of the plurality of content topics in the content pool based on a ratio of the number of content items in the content pool classified as being related to each of the plurality of content topics and the level of interest in each of the plurality of content topics; and

updating, using the processor, the number of content items in the content pool related to at least some of the plurality of content topics based on the level of representation of each of the plurality of content topics with respect to a threshold for a respective content topic of the plurality of content topics.

2. The method of claim 1 , wherein updating the number of content items comprises:

adding one or more content items related to the at least some of the plurality of content topics if the level of representation of each of the plurality of content topics is greater than the threshold for the respective content topic; and

deleting one or more content items related to the at least some of the plurality of content topics if the level of representation of each of the plurality of content topics is less than the threshold for the respective content topic.

3. The method of claim 1 , wherein determining, for each of the plurality of content topics, the number of content items in the content pool classified as being related to the content topic comprises:

accessing the content items from the content pool; and

classifying each of the content items from the content pool into one or more of the plurality of content topics based on content included in a corresponding content item.

4. The method of claim 3 , wherein classifying each of the content items from the content pool into the one or more of the plurality of content topics comprises:

characterizing each content item from the content pool into a multidimensional vector, wherein:

each attribute of the multidimensional vector corresponding to one of the plurality of content topics, and

a value of each attribute of the multidimensional vector indicates whether a corresponding content item relates to a corresponding content topic of the plurality of content topics.

5. The method of claim 1 , wherein determining the level of representation of each of the plurality of content topics in the content pool comprises:

normalizing the number of content items in the content pool for each of the plurality of content topics with respect to a total number of content items in the content pool;

normalizing the level of interest of the set of users in each of the plurality of content topics with respect to the number of content items in the content pool classified as being related to each of the plurality of content topics; and

calculating the ratio based on the normalized number of content items in the content pool related to each of the plurality of content topics and the normalized level of interest of the set of users in each of the plurality of content topics to determine the level of representation of each of the plurality of content topics.

6. The method of claim 1 , wherein updating the number of content items in the content pool related to the at least some of the plurality of content topics is further based on a financial budget related to the content pool.

7. The method of claim 1 , wherein determining the level of interest of the set of users in each of the plurality of content topics comprises:

receiving, for each user included in the set of users, a user interest vector, wherein:

each attribute of the user interest vector corresponds to one of the plurality of content topics, and

a value of each attribute of the user interest vector indicates whether a corresponding user is interested in a corresponding content topic determined based on user interaction information;

for each of the plurality of content topics:

extracting the value of the attribute associated with the content topic from the user interest vector of each user included in the set of users; and

combining the value of the attribute associated with the content topic to determine the level of interest of the set of users in the content topics.

8. The method of claim 1 , further comprising:

obtaining candidate content via a web crawler;

extracting concepts covered by the candidate content;

computing a multidimensional vector of a content profile of the candidate content by mapping the concepts to the plurality of content topics;

determining whether to add the candidate content to the content pool based on the multidimensional vector of the content profile of the candidate content and a user interest vector for each user of the set of users indicating one or more of the plurality of content topics that the user is interested in.

9. A system having memory storing computer program instructions and at least one processor configured to execute the computer program instructions to manage representation of a content topic in a content pool, the system comprising:

a communication platform, implemented by the at least one processor, and configured to receive information related to content items in a content pool and information related to interactions of a set of users with the content items in the content pool;

an availability determiner, implemented by the at least one processor, and configured to determine for each of a plurality of content topics, a number of content items in the content pool classified as being related to the content topic;

an interest determiner, implemented by the at least one processor, and configured to determine a level of interest of the set of users in each of the plurality of content topics based on the information related to interactions of the set of users with the content items in the content pool;

a representation-level determiner, implemented by the at least one processor, and configured to determine a level of representation of each of the plurality of content topics in the content pool based on a ratio of the number of content items in the content pool classified as being related to each of the plurality of content topics and the level of interest in each of the plurality of content topics; and

a content pool manager, implemented by the at least one processor, and configured to update the number of content items in the content pool related to at least some of the plurality of content topics based on the level of representation of each of the plurality of content topics with respect to a threshold for a respective content topic of the plurality of content topics.

10. The system of claim 9 , further comprising:

a comparator configured to compare the level of representation of each of the plurality of content topics with the threshold for the respective content topic,

wherein the content pool manager is further configured to:

add one or more content items related to the at least some of the plurality of content topics based on a determination from the comparator that the level of representation of each of the plurality of content topics is greater than the threshold for the respective content topic; and

delete one or more content items related to the at least some of the plurality of content topics based on a determination from the comparator that the level of representation of each of the plurality of content topics is less than the threshold for the respective content topic.

11. The system of claim 9 , wherein the availability determiner is further configured to:

access the content items from the content pool; and

classify each of the content items from the content pool into one or more of the plurality of content topics based on content included in a corresponding content item.

12. The system of claim 11 , wherein the availability determiner is further configured to:

characterize each content item from the content pool into a multidimensional vector, wherein:

each attribute of the multidimensional vector corresponding to one of the plurality of content topics, and

a value of each attribute of the multidimensional vector indicates whether a corresponding content item relates to a corresponding content topic of the plurality of content topics.

13. The system of claim 9 , wherein the representation-level determiner is further configured to:

normalize the number of content items in the content pool for each of the plurality of content topics with respect to a total number of content items in the content pool;

normalize the level of interest of the set of users in each of the plurality of content topics with respect to the number of content items in the content pool classified as being related to each of the plurality of content topics; and

calculate the ratio based on the normalized number of content items in the content pool related to each of the plurality of content topics and the normalized level of interest of the set of users in each of the plurality of content topics to determine the level of representation of each of the plurality of content topics.

14. The system of claim 9 , wherein the content pool manager is configured to update the number of content items in the content pool related to the at least some of the plurality of content topics further based on a financial budget related to the content pool.

15. The system of claim 9 , wherein the interest determiner is further configured to:

receive, for each user included in the set of users, a user interest vector, wherein:

each attribute of the user interest vector corresponds to one of the plurality of content topics, and

a value of each attribute of the user interest vector indicates whether a corresponding user is interested in a corresponding content topic determined based on user interaction information;

for each of the plurality of content topics:

extract the value of the attribute associated with the content topic from the user interest vector of each user included in the set of users; and

combine the value of the attribute associated with the content topic to determine the level of interest of the set of users in the content topics.

16. A machine readable, tangible, and non-transitory medium storing computer program instructions that, when executed by the machine, effectuate operations comprising:

determining, for each of a plurality of content topics, a number of content items in a content pool classified as being related to the content topic;

determining a level of interest of a set of users in each of the plurality of content topics based on information related to interactions of the set of users with the content items in the content pool;

determining a level of representation of each of the plurality of content topics in the content pool based on a ratio of the number of content items in the content pool classified as being related to each of the plurality of content topics and the level of interest in each of the plurality of content topics; and

updating the number of content items in the content pool related to at least some of the plurality of content topics based on the level of representation of each of the plurality of content topics with respect to a threshold for a respective content topic of the plurality of content topics.

17. The medium of claim 16 , wherein updating the number of content items comprises:

adding one or more content items related to the at least some of the plurality of content topics if the level of representation of each of the plurality of content topics is greater than the threshold for the respective content topic; and

deleting one or more content items related to the at least some of the plurality of content topics if the level of representation of each of the plurality of content topics is less than the threshold for the respective content topic.

18. The medium of claim 16 , wherein determining, for each of the plurality of content topics, the number of content items in the content pool classified as being related to the content topic comprises:

accessing the content items from the content pool; and

classifying each of the content items from the content pool into one or more of the plurality of content topics based on content included in a corresponding content item.

19. The medium of claim 18 , wherein classifying each of the content items from the content pool into the one or more of the plurality of content topics comprises:

characterizing each content item from the content pool into a multidimensional vector, wherein:

each attribute of the multidimensional vector corresponding to one of the plurality of content topics, and

a value of each attribute of the multidimensional vector indicates whether a corresponding content item relates to a corresponding content topic of the plurality of content topics.

20. The medium of claim 16 , wherein determining the level of representation of each of the plurality of content topics in the content pool comprises:

normalizing the number of content items in the content pool for each of the plurality of content topics with respect to a total number of content items in the content pool;

normalizing the level of interest of the set of users in each of the plurality of content topics with respect to the number of content items in the content pool classified as being related to each of the plurality of content topics; and

calculating the ratio based on the normalized number of content items in the content pool related to each of the plurality of content topics and the normalized level of interest of the set of users in the each of the plurality of content topics to determine the level of representation of each of the plurality of content topics.

21. The medium of claim 16 , wherein determining the level of interest of the set of users in each of the plurality of content topics comprises:

receiving, for each user included in the set of users, a user interest vector, wherein:

each attribute of the user interest vector corresponds to one of the plurality of content topics, and

a value of each attribute of the user interest vector indicates whether a corresponding user is interested in a corresponding content topic determined based on user interaction information;

for each of the plurality of content topics:

extracting the value of the attribute associated with the content topic from the user interest vector of each user included in the set of users; and

combining the value of the attribute associated with the content topic to determine the level of interest of the set of users in the content topics.

Assignments (6)
PATENT SECURITY AGREEMENT (FIRST LIEN) Recorded Sep 29, 2022
From: YAHOO ASSETS LLC
To: ROYAL BANK OF CANADA, AS COLLATERAL AGENT
Reel/Frame 061571/0773 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 16, 2021
From: YAHOO AD TECH LLC (FORMERLY VERIZON MEDIA INC.)
To: YAHOO ASSETS LLC
Reel/Frame 058982/0282 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 26, 2020
From: OATH INC.
To: VERIZON MEDIA INC.
Reel/Frame 054258/0635 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 2, 2018
From: YAHOO HOLDINGS, INC.
To: OATH INC.
Reel/Frame 045240/0310 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 23, 2017
From: YAHOO! INC.
To: YAHOO HOLDINGS, INC.
Reel/Frame 042963/0211 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 4, 2017
From: WEXLER, MICHAEL CAREY; MATHESON, DON
To: YAHOO! INC.
Reel/Frame 040841/0770 →
Continuity (1)
Related Publication 20180189289A1 · Jul 5, 2018
Cited By (2)
US 12,389,080 US 12,598,241