IP Library Granted Patent US 9,684,908
Granted Patent B2
US 9,684,908 · App. 14/449,390 · Granted Jun 20, 2017

Automatically generated comparison polls

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 9,684,908
App. No.
14/449,390
Granted
Jun 20, 2017
Kind
B2
Abstract

A content item presented to a user may involve two or more topics, such as news articles mentioning athletes or actors. Users may enjoy expressing opinions about a comparison of the topics, such as personal preferences or an evaluation of talent. Presented herein are techniques for automatically generating, for the content item, a poll among the topics of the content item. The respective comparisons of a comparison set are evaluated for the topics of the content item, and a comparison relevance score is computed identifying the relevance of the comparison of the topics. The comparison having the highest relevance for the topics is selected, and a comparison question is formulated and presented to the user with the content item. Results may be tabulated and presented for the topics of the content item. These techniques facilitate user expression about the content item without depending upon user-authored polls for each content item.

Claims (87)

1. A method of supplementing a presentation of a content item to a user, comprising:

identifying at least two topics in the content item;

for a first comparison in a comparison set, calculating a first comparison relevance score of the first comparison to the at least two topics;

for a second comparison in the comparison set, calculating a second comparison relevance score of the second comparison to the at least two topics;

based upon the first comparison relevance score and the second comparison relevance score, identifying the first comparison as a selected comparison;

using the selected comparison, generating, using a processor, a comparison question that compares the at least two topics by inserting a first topic of the at least two topics into a first slot of a comparison question template of the selected comparison and inserting a second topic of the at least two topics into a second slot of the comparison question template; and

presenting the comparison question with the content item to the user.

2. The method of claim 1 , wherein:

the content item describes the at least two topics in a language; and

identifying the at least two topics in the content item further comprises:

evaluating the content item according to a language cue set of the language; and

identifying the respective topics in the content item according to the language cue set.

3. The method of claim 1 , wherein:

the content item comprises a media item;

the respective topics are associated with a topic identifier; and

identifying the respective topics in the content item further comprises: identifying, within the media item, the topic identifier of the topic.

4. The method of claim 1 , wherein identifying the first comparison as the selected comparison further comprises:

for respective comparisons of the comparison set:

for the respective topics, determine a topic relevance of the topic to the comparison; and

upon determining that the topic relevance of at least one topic is below a topic relevance threshold, refrain from identifying the comparison as the selected comparison.

5. The method of claim 1 , wherein identifying the first comparison as the selected comparison further comprises:

for the respective topics, determine a topic type of the topic; and

identifying a selected comparison according to comparison relevance scores among at least two topics with a matching topic type.

6. The method of claim 5 , wherein:

the respective topics have a comparison magnitude for the topic type; and

identifying the first comparison as the selected comparison further comprises:

identifying the first comparison as the selected comparison according to the comparison relevance scores among at least two topics having a comparison magnitude above a comparison magnitude threshold.

7. The method of claim 1 , wherein:

the content item is associated with a context; and

identifying the first comparison as the selected comparison further comprises: identifying the first comparison as the selected comparison according to comparison relevance scores and matching the context of the content item.

8. A server that presents a content item to a user, the server comprising:

a processor; and

a memory storing instructions that, when executed by the processor, provide:

a comparison generator that:

identifies at least two topics in the content item;

for a first comparison in a comparison set, calculates a first comparison relevance score of the first comparison to the at least two topics;

for a second comparison in the comparison set, calculates a second comparison relevance score of the second comparison to the at least two topics;

based upon the first comparison relevance score and the second comparison relevance score, identifies the first comparison as a selected comparison; and

using the selected comparison, generates a comparison question that compares the at least two topics by inserting a first topic of the at least two topics into a first slot of a comparison template of the selected comparison and inserting a second topic of the at least two topics into a second slot of the comparison template; and

a comparison presenter that presents the comparison question with the content item to the user.

9. The server of claim 8 , wherein:

the server further comprises a comparison template set comprising at least one comparison template; and

the comparison generator further identifies the first comparison as the selected comparison by, among the comparison templates of the comparison template set, identifying a selected comparison template according to comparison relevance scores of comparisons of the comparison set.

10. The server of claim 9 , wherein:

the server further comprises a training content item set comprising at least one training content item; and

the memory further stores instructions that, when executed by the processor, provide a comparison trainer that, for the respective training content items:

examines the training content item to identify a training comparison question;

using the training comparison question, generates a first comparison template; and

adds the first comparison template to the comparison template set.

11. The server of claim 10 , wherein:

the comparison trainer, for the respective training content items:

identifies a selected topic in the training content item that is comparable with a third topic, and

adds the selected topic to a topic database; and

the comparison generator further identifies the at least two topics in the content item by identifying in the content item at least two topics of the topics database.

12. The server of claim 10 , wherein:

the comparison trainer further evaluates the respective training content items to identify a topic set comprising at least two topics having a relation in the training content item; and

the comparison generator further identifies the at least two topics in the content item by identifying in the content item the topics of a topic set.

13. The server of claim 10 , wherein:

the comparison trainer further calculates, for the respective training comparisons, a comparison relevance score;

the comparison trainer further trains a classifier to generate the comparison relevance score of the respective training comparisons; and

the comparison generator further invokes the classifier to calculate the first comparison relevance score of the first comparison to the at least two topics.

14. The server of claim 9 , wherein:

the respective comparison templates comprise a comparison question template.

15. The server of claim 8 , wherein:

the comparison template comprises a comparison question template.

16. A nontransitory memory device storing instructions that, when executed by a processor of a server, cause the server to supplement a presentation of a content item to a user, by:

identifying at least two topics in the content item;

for a first comparison in a comparison set, calculating a first comparison relevance score of the first comparison to the at least two topics;

for a second comparison in the comparison set, calculating a second comparison relevance score of the second comparison to the at least two topics;

based upon the first comparison relevance score and the second comparison relevance score, identifying the first comparison as a selected comparison;

using the selected comparison, generating a comparison question that compares the at least two topics by inserting a first topic of the at least two topics into a first slot of a comparison template of the selected comparison and inserting a second topic of the at least two topics into a second slot of the comparison template; and

presenting the comparison question with the content item to the user.

17. The nontransitory memory device of claim 16 , wherein presenting the comparison question further comprises:

upon receiving a comparison response from the user, store the comparison response in a comparison response set for the comparison question; and

upon presenting the comparison question to a second user, present the comparison response set for the comparison question to the second user.

18. The nontransitory memory device of claim 16 , wherein presenting the comparison question further comprises:

upon receiving a comparison response from the user, store the comparison response in a comparison response set for the first comparison;

rank the topics for the first comparison according to one or more comparison responses; and

present a rank list of the topics for the first comparison.

19. The nontransitory memory device of claim 16 , wherein presenting the comparison question further comprises:

upon receiving a comparison response from the user, present to the user an offer to present a second comparison question for the first comparison; and

upon receiving from the user an acceptance of the offer:

generate a second comparison question presenting the first comparison between at least two other topics; and

present the second comparison question to the user.

20. The nontransitory memory device of claim 16 , wherein:

the user is associated with a user profile indicating a user interest of the user in respective topics; and

presenting the comparison question further comprises: upon receiving a comparison response from the user, adjust the user interest in the user profile of the user for the at least two 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 Aug 27, 2014
From: ROKHLENKO, OLEG; SZPEKTOR, IDAN
To: YAHOO!, INC.
Reel/Frame 033627/0115 →