Event detection using roles and relationships of entities

• US 9,886,665 B2
• Filed: 12/08/2014
• Issued: 02/06/2018
• Est. Priority Date: 12/08/2014
• Status: Active Grant

• Current Assignee: Baylor College of Medicine (Baylor College), International Business Machines Corporation, Board of Regents of the University of Texas System (University of Texas System)
• Original Assignee: International Business Machines Corporation
• Inventors: Chen, Ying, Kato, Linda H., Labrie, Jacques J., Nagarajan, Meenakshi, Spangler, William Scott, Stanoi, Ioana R., Adikesavan, Anbu Karani, Bachman, Benjamin J., Donehower, Lawrence A., Lichtarge, Olivier, Regenbogen, Sam J., Terron-Diaz, Maria E., Wilkins, Angela D., Pickering, Curtis R.
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US14/564,040
• Publication Number:
  US 20160162788A1
• Time in Patent Office: 1,156 Days
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

A method, system, and computer program product for event detection using roles and relationships of entities are provided in the illustrative embodiments. A training event and a set of entities participating in the training event are identified in a training data. For a first entity in the set of entities, a first role occupied by the entity in the event is determined. A behavior attribute is assigned to the first role. A relationship of the first role with a second role corresponding to a second entity in the set of entities is determined. An event rule is constructed to detect an event corresponding to the training event in new data and comprising a plurality of roles, behavior attributes, and the relationship. The plurality of roles includes the first role and the second role, and the plurality of behavior attributes includes the behavior attribute assigned to the first role.

Claims

1. A method for event detection in data, the method comprising:

identifying, in a training data, a training event and a set of entities participating in the training event;

determining, for a first entity in the set of entities, a first role occupied by the entity in the event;

assigning a behavior attribute to the first role;

determining a relationship of the first role with a second role corresponding to a second entity in the set of entities; and

constructing an event rule, wherein the event rule is usable to detect an event in new data, the event corresponding to the training event, and wherein the event rule comprises a plurality of roles, a plurality of behavior attributes, and the relationship, wherein the plurality of roles includes the first role and the second role, and the plurality of behavior attributes includes the behavior attribute assigned to the first role.

2. The method of claim 1, further comprising:

assigning the event rule a confidence score, the confidence score corresponding to a number of training events in the training data used in constructing the event rule.

3. The method of claim 1, further comprising:

receiving the new data;

selecting the event rule;

determining whether a new first entity in the new data occupies the first role, whether the new first entity participates in the new data according to the behavior attribute of the first role, whether the new first entity has the relationship with a new second entity in the second role, and whether a third new entity is present in the new data according to a condition in the event rule; and

detecting, responsive to the determining being affirmative, the event in the new data.

4. The method of claim 3, further comprising:

assigning a second confidence score to the event rule according to the event actually being represented in the new data.

5. The method of claim 3, wherein the event rule is selected as a member of a set of event rules, the selecting being responsive to the confidence score of the event rule exceeding a threshold.

6. The method of claim 1, further comprising:

determining whether a third role corresponding to a third entity is present in the training data according to a condition; and

adding the condition and the third role to the event rule.

7. The method of claim 6, wherein the condition comprises an optional use of the third role.

8. The method of claim 6, wherein the condition comprises a mandatory presence of the third role.

9. The method of claim 6, wherein the condition comprises an implied participation of the third role.

10. The method of claim 6, wherein the event rule further comprises the condition and the third role.

11. The method of claim 1, further comprising:

determining, to configure the behavior attribute, a manner in which the first role operates in the event according to one or a linguistic resource and a lexical resource.

12. The method of claim 1, wherein the set of entities comprises more than two entities, and the event rule comprises more than two roles.

13. A computer usable program product comprising a computer readable storage device including computer usable code for event detection in data, the computer usable code comprising:

computer usable code for identifying, in a training data, a training event and a set of entities participating in the training event;

computer usable code for determining, for a first entity in the set of entities, a first role occupied by the entity in the event;

computer usable code for assigning a behavior attribute to the first role;

computer usable code for determining a relationship of the first role with a second role corresponding to a second entity in the set of entities; and

computer usable code for constructing an event rule, wherein the event rule is usable to detect an event in new data, the event corresponding to the training event, and wherein the event rule comprises a plurality of roles, a plurality of behavior attributes, and the relationship, wherein the plurality of roles includes the first role and the second role, and the plurality of behavior attributes includes the behavior attribute assigned to the first role.

14. The computer usable program product of claim 13, further comprising:

computer usable code for assigning the event rule a confidence score, the confidence score corresponding to a number of training events in the training data used in constructing the event rule.

15. The computer usable program product of claim 13, further comprising:

computer usable code for receiving the new data;

computer usable code for selecting the event rule;

computer usable code for determining whether a new first entity in the new data occupies the first role, whether the new first entity participates in the new data according to the behavior attribute of the first role, whether the new first entity has the relationship with a new second entity in the second role, and whether a third new entity is present in the new data according to a condition in the event rule; and

computer usable code for detecting, responsive to the determining being affirmative, the event in the new data.

16. The computer usable program product of claim 15, further comprising:

computer usable code for assigning a second confidence score to the event rule according to the event actually being represented in the new data.

17. The computer usable program product of claim 15, wherein the event rule is selected as a member of a set of event rules, the selecting being responsive to the confidence score of the event rule exceeding a threshold.

18. The computer usable program product of claim 13, wherein the computer usable code is stored in a computer readable storage device in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system.

19. The computer usable program product of claim 13, wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

20. A data processing system for event detection in data, the data processing system comprising:

a storage device, wherein the storage device stores computer usable program code; and

a processor, wherein the processor executes the computer usable program code, and wherein the computer usable program code comprises;

computer usable code for identifying, in a training data, a training event and a set of entities participating in the training event;

computer usable code for determining, for a first entity in the set of entities, a first role occupied by the entity in the event;

computer usable code for assigning a behavior attribute to the first role;

computer usable code for determining a relationship of the first role with a second role corresponding to a second entity in the set of entities; and

computer usable code for constructing an event rule, wherein the event rule is usable to detect an event in new data, the event corresponding to the training event, and wherein the event rule comprises a plurality of roles, a plurality of behavior attributes, and the relationship, wherein the plurality of roles includes the first role and the second role, and the plurality of behavior attributes includes the behavior attribute assigned to the first role.