Automatic update detection for regulation compliance

Patent metadata

Field	Value
Publication number	US-10467717-B2
Application number	US-201615081194-A
Country	US
Kind code	B2
Filing date	Mar 25, 2016
Priority date	Oct 7, 2015
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

An embodiment of the invention provides a method comprising monitoring publications for regulatory changes with a monitoring device, and identifying at least one regulatory change based on the monitoring of the publications. The monitoring device monitors published comments to the identified regulatory change. A processor connected to the monitoring device identifies one or more topics and/or objects in the regulatory change and/or the published comments. An alert generating device connected to the processor generates an alert including one or more policies above a threshold level of likelihood that the policy will be affected by the regulatory change.

First claim

What is claimed is:

1. A method comprising:
automatically monitoring, via processing circuitry and without user input, publications for regulatory changes;
identifying, via web crawling by the processing circuitry, at least one regulatory change based on said monitoring of the publications;
monitoring, in response to identifying the regulatory change, published comments to the identified regulatory change;
identifying, via the processing circuitry, at least one topic and a plurality of objects in the regulatory change and the published comments, a plurality of objects influenced by the regulatory change, and how an impact of the regulatory change changes with time, each object describing what will be affected by the regulatory change;
generating in memory a dynamically linked object mapping of the identified objects;
identifying a sentiment towards the identified regulatory change based on said monitoring of the published comments and the dynamically linked object mapping;
generating, based on the at least one topic and objects, an alert with an alert generating device connected to the processing circuitry, the alert including at least one policy above a threshold level of likelihood that it will be affected by the regulatory change;
identifying a hidden social association with respect to the regulatory change based on the sentiment;
generating, by the alert generating device and in response to identifying the hidden social association, an alert indicating the hidden social association with respect to the regulatory change.

2. The method according to claim 1 , wherein the topic includes at least one word describing a regulation subject to the regulatory change.

3. The method according to claim 1 , wherein the objects include at least one entity above a threshold level of likelihood that it will be affected by the regulatory change.

4. The method according to claim 1 , further comprising:
identifying comments in the published comments having a threshold degree of similarity based on said identifying of the topic and objects in at least one of the regulatory change and the published comments;
grouping comments in the published comments based on similarity.

5. The method according to claim 1 , further comprising:
creating a domain regulation ontology; and
identifying associations between identified topics and concepts in the domain regulation ontology.

6. The method according to claim 5 , further comprising:
selecting a key topic from the identified topics according to the ontology.

7. The method according to claim 4 , further comprising:
creating a domain regulation ontology; and
identifying associations between identified objects and concepts in the domain regulation ontology.

8. The method according to claim 7 , further comprising:
selecting a key object from the identified topics according to the ontology.

9. A system providing automatic update detection for regulation compliance, said system comprising:
processing circuitry configured to
automatically monitor, without user input, publications for regulatory changes,
identify, via web crawling, at least one regulatory change based on said monitoring of the publications,
monitor, in response to identifying the regulatory change, published comments to the identified regulatory change,
identify at least one topic and a plurality of objects in the regulatory change and the published comments, a plurality of objects influenced by the regulatory change, and how an impact of the regulatory change changes with time, each object describing what will be affected by the regulatory change,
generate in memory a dynamically linked object mapping of the identified objects;
identify a sentiment towards the identified regulatory change based on said monitoring of the published comments and the dynamically linked object mapping,
generate, based on the at least one topic and objects, an alert including at least one policy above a threshold level of likelihood that it will be affected by the regulatory change,
identify a hidden social association with respect to the regulatory change based on the sentiment;
generate, in response to identifying the hidden social association, an alert indicating the hidden social association with respect to the regulatory change.

10. The system according to claim 9 , wherein the topic includes at least one word describing a regulation subject to the regulatory change.

11. The system according to claim 9 , wherein the objects include at least one entity above a threshold level of likelihood that it will be affected by the regulatory change.

12. The system according to claim 9 , wherein the processing circuitry is further configured to
identify comments in the published comments having a threshold degree of similarity based on said identifying of the topic and the objects in the regulatory change and the topic and the object in the published comments, and
group comments in the published comments based on similarity.

13. The system according to claim 9 , wherein the processing circuitry is further configured to
create a domain regulation ontology, and
identify associations between identified topics and concepts in the domain regulation ontology.

14. The method according to claim 13 , wherein the processing circuitry is further configured to select a key topic from the identified topics according to the ontology.

15. The method according to claim 12 , wherein the processing circuitry is further configured to
create a domain regulation ontology, and
identify associations between identified objects and concepts in the domain regulation ontology.

16. The method according to claim 15 , wherein the processing circuitry is further configured to select a key object from the identified topics according to the ontology.

17. A non-transitory computer-readable medium having computer-readable instructions stored thereon which when executed by a computer cause the computer to perform a method comprising:
automatically monitoring, without use input, publications for regulatory changes;
identifying, via web crawling at least one regulatory change based on the monitoring of the publications;
monitoring, in response to identifying the regulatory change, published comments to the identified regulatory change;
identifying a topic and a plurality of objects in the regulatory change and in the published comments, a plurality of objects influenced by the regulatory change, and how an impact of the regulatory change changes with time, each object describing what will be affected by the regulatory change,
generating in memory a dynamically linked object mapping of the identified objects;
identifying a sentiment towards the identified regulatory change based on said monitoring of the published comments and the dynamically linked object mapping;
generating, based on the identifying of the sentiment, an alert including at least one policy above a threshold level of likelihood that it will be affected by the regulatory change;
identifying a hidden social association with respect to the regulatory change based on the sentiment;
generating, in response to identifying the hidden social association, an alert indicating the hidden social association with respect to the regulatory change.

18. The non-transitory computer-readable medium according to claim 17 , further comprising:
identifying a sentiment towards the identified regulatory change based on said monitoring of the published comments.

Assignees

• IBM
• IBM

Inventors

• Cai Keke
• Guo Honglei
• Guo Zhili
• Jiang Jianmin
• Jin Feng
• Su Zhong
• Sun Changhua
• Tang Guoyu

Classifications

• G06Q10/40 Primary

  Business processes related to social networking or social networking services · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06Q30/018 Primary

  Certifying business or products · CPC title

• G06Q50/205 Primary

  Education administration or guidance · CPC title

• G06F17/2785

  Physics · mapped topic