FUTURE EVENT DETECTION

• US 20160239737A1
• Filed: 03/13/2015
• Published: 08/18/2016
• Est. Priority Date: 03/13/2015
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Jiang, Junwei, Cui, Wenliang, Wan, Qian
• Granted Patent: US 10,212,243 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/55 Push-based network services

Abstract

One or more methods and/or techniques for providing a personalized future event notification to a user are provided herein. A content item (e.g., a news article, a social network post, etc.) may be evaluated utilizing a future event detection model to identify a future event (e.g., a festival). The future event detection model may have been trained to identify future events based upon part of speech analysis and entity recognition analysis of text within content items. In an example, the future event detection model may be used to identify locational features, temporal features, and/or entities from the content item. A user having a user interest in the future event above an interest threshold may be identified based upon user identifying information (e.g., a social network profile) being indicative of user interest in the future event. A personalized future event notification of the future event may be provided to the user.

Claims

1. A method for providing a personalized future event notification, comprising:

evaluating a content item utilizing a future event detection model to identify a future event, the future event detection model trained to identify future events based upon part of speech analysis and entity recognition analysis of text within the content item;

identifying a user having a user interest in the future event above an interest threshold based upon user identifying information being indicative of the user interest in the future event; and

providing a personalized future event notification for the future event to the user.

2. The method of claim 1, the providing comprising:

constructing a push notification, identifying the future event, as the personalized future event notification; and

providing the push notification to a client device for display as a device alert notification.

3. The method of claim 1, the evaluating a content item comprising:

performing part of speech analysis on the content item to generate an event feature corresponding to least one of a subject, a predicate, an object, or an adverbial clause associated with at least one of a location or a future time;

performing entity recognition analysis to extract an entity from the content item;

generating a relevance score based upon an association between the entity and the event feature; and

responsive to the relevance score exceeding a relevancy threshold, identifying the future event based upon the entity and the event feature.

4. The method of claim 1, the identifying a user comprising:

identifying a set of future events from content items;

ranking the set of future events based upon a user profile of the user to create a ranked set of future events; and

providing a ranked future event from the ranked set of future events to the user based upon a rank of the ranked future event.

5. The method of claim 1, the content item, comprising at least one of:

a news article, a blog post, news feed content, a social network post, website content, application user interface data, an email message, an instant message, a forum message, a social media message, an in-app message, a video message, a text message, or an audio message.

6. The method of claim 1, the providing a personalized future event notification comprising:

providing a calendar creation option to the user; and

responsive to the user selecting the calendar creation option, creating a calendar entry, for the future event, within a calendar associated with the user.

7. The method of claim 1, comprising:

receiving feedback from the user regarding the personalized future event notification;

responsive to the feedback indicating that the future event is an invalid future event, training the future event detection model based upon the feedback.

8. The method of claim 1, comprising:

receiving feedback from the user regarding the personalized future event notification;

responsive to the feedback indicating that the future event is at least one of an interesting future event or a valid future event, training the future event detection model based upon the feedback.

9. The method of claim 1, comprising:

evaluating a second content item to identify a second future event;

evaluating a user profile of the user to determine that the user has a greater interest in the future event than the second future event; and

generating the personalized future event notification based upon the future event but not the second future event.

10. The method of claim 1, comprising:

displaying a copy user interface element used to copy the personalized future event notification for pasting.

11. The method of claim 1, comprising:

displaying a share interface element used to share the personalized future event notification with a second user.

12. The method of claim 1, comprising:

displaying a save interface element used to save the personalized future event notification as at least one of a file, a bookmark, a task item, an email, a calendar entry, or a reminder notification.

13. A method for training a future event detection model, comprising:

performing part of speech analysis on training content to generate a speech analysis result that identifies at least one of a subject, a predicate, an object, or an adverbial clause corresponding to at least one of a location or a future time;

performing entity recognition analysis to extract an entity relevant to a future event from the training content; and

assigning a relevance score between the entity and the speech analysis result to train a future event detection model for future event detection.

15. The method of claim 13, comprising:

evaluating a content item utilizing the future event detection model to identify a future event;

identifying a user having a user interest in the future event above an interest threshold based upon user identifying information being indicative of the user interest in the future event; and

providing a personalized future event notification for the future event to the user.

14. The method of 13, the future event detection model comprising:

a Gradient Boosting Decision Tree (GBDT) model or an XQuery Data Model (XDM).

16. A system for identifying future event content, comprising:

a model training component configured to;

perform part of speech analysis on training content to generate a speech analysis result that identifies at least one of a subject, a predicate, an object, or an adverbial clause corresponding to at least one of a location and a future time;

perform entity recognition analysis to extract an entity relevant to a future event from the training content; and

assign a relevance score between the entity and the speech analysis result to train a future event detection model for future event detection.

17. The system of claim 16, comprising:

a future event detection component configured to;

evaluate a content item utilizing the future event detection model to identify a future event;

identify a user having a user interest in the future event above an interest threshold based upon user identifying information being indicative of the user interest in the future event; and

provide a personalized future event notification for the future event to the user.

18. The system of claim 17, the future event detection component configured to at least one of:

display a feedback user interface element used to provide feedback based upon the personalized future event notification;

display a copy user interface element used to copy the personalized future event notification for pasting.

display a share interface element used to share the personalized future event notification with a second user;

or

display a save interface element used to save the personalized future event notification as at least one of a file, a bookmark, a task item, an email, a calendar item, or a reminder notification.

19. The system of claim 17, the future event detection component configured to receive feedback from the user regarding the personalized future event notification and the model training component configured to train the future event detection model based upon the feedback.

20. The system of claim 17, the future event detection component configured to:

provide a calendar creation option to the user;

responsive to the user selecting the calendar creation option, create a calendar entry, of the future event, within a calendar associated with the user.