ALERTING SYSTEM BASED ON NEWLY DISAMBIGUATED FEATURES

• US 20150154196A1
• Filed: 12/02/2014
• Published: 06/04/2015
• Est. Priority Date: 12/02/2013
• Status: Active Grant

• Current Assignee: Finch Computing LLC (Qbase, LLC)
• Original Assignee: Qbase, LLC
• Inventors: LIGHTNER, Scott, WECKESSER, Franz
• Granted Patent: US 9,317,565 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence

Abstract

The present disclosure relates to a method of alerting users regarding newly disambiguated features. More specifically, a newly disambiguated feature may pass through different filters/restrictions, such as, the known knowledge base. The disclosed known knowledge base may filter the newly disambiguated feature, comparing the newly disambiguated features to the existing features to discover a new feature of interest. Particularly, the disclosed new feature of interest may include a new person, a new phone number, a new place, a new company, among others. Finally, if there is a new feature that did not match with the existing disambiguated features in the known knowledge base, then an alert may be emitted to a user.

Claims

1. A method comprising:

disambiguating, by a disambiguation computer, a document feature from an electronic document by way of;

extracting, via a feature extraction computer, the document feature from the electronic document, and

linking, by the linking computer, the extracted document feature, to a set of document features having a primary document feature and a secondary document feature stored in a knowledge database of document features of a plurality of electronic documents, the secondary document feature including a proximity cluster of co-occurring features in the plurality of electronic documents; and

adding, by an in-memory database computer, the disambiguated document feature to the knowledge database of co-occurring document features when the disambiguated document feature matches a document feature of interest in an alert database based at least in part on the linked set of document features including the proximity cluster; and

generating, by a computer, an electronic user alert regarding the matching.

2. The method of claim 1 further comprising assigning to the disambiguated document feature, by a scoring computer, a confidence score indicative of a level of confidence associated with a degree of disambiguation of the document feature, wherein the disambiguated document feature further matches the document feature of interest in the alert database based at least in part on the confidence score.

3. The method of claim 1 wherein the in-memory database computer matches the disambiguated document feature with the document feature of interest in the alert database based on a distance parameter associated with the proximity cluster.

4. The method of claim 1 wherein the in-memory database computer matches the disambiguated document feature with the document feature of interest in the alert database based on graph clustering of the secondary feature.

5. The method of claim 1 wherein the disambiguated document feature is selected from the group consisting of a person, a phone number, a location, and a company name.

6. The method of claim 1 wherein the extracted document feature and the set of document features are linked temporarily.

7. A system comprising:

a disambiguation computer configured to disambiguate a document feature from an electronic document by being further configured to extract the document feature from the electronic document, and link the extracted document feature to a set of document features having a primary document feature and a secondary document feature stored in a knowledge database of document features of a plurality of electronic documents, the secondary document feature including a proximity cluster of co-occurring features in the plurality of electronic documents; and

an in-memory database computer configured to add the disambiguated document feature to the knowledge database of co-occurring document features when the disambiguated document feature matches a document feature of interest in an alert database based at least in part on the linked set of document features including the proximity cluster, wherein the in-memory database computer is further configured to generate an electronic user alert regarding the matching.

8. The system of claim 7 further comprising a scoring computer configured to assign to the disambiguated document feature a confidence score indicative of a level of confidence associated with a degree of disambiguation of the document feature, wherein the disambiguated document feature further matches the document feature of interest in the alert database based at least in part on the confidence score.

9. The system of claim 7 wherein the in-memory database computer is configured to match the disambiguated document feature with the document feature of interest in the alert database based on a distance parameter associated with the proximity cluster.

10. The system of claim 7 wherein the in-memory database computer is configured to match the disambiguated document feature with the document feature of interest in the alert database based on graph clustering of the secondary feature.

11. The system of claim 7 wherein the disambiguated document feature is selected from the group consisting of a person, a phone number, a location, and a company name.

12. The system of claim 7 wherein the extracted document feature and the set of document features are linked temporarily.

13. A non-transitory computer readable medium having stored thereon computer executable instructions to be executed by a processor comprising:

disambiguating, by a processor executing a disambiguation computer module, a document feature from an electronic document by way of;

extracting, by the processor executing a feature extraction computer module, the document feature from the electronic document, and

linking, by the processor executing a linking computer module, the extracted document feature to a set of document features having a primary document feature and a secondary document feature stored in a knowledge database of document features of a plurality of electronic documents, the secondary document feature including a proximity cluster of co-occurring features in the plurality of electronic documents;

adding, by the processor executing an in-memory database computer module, the disambiguated document feature to the knowledge database of co-occurring document features when the disambiguated document feature matches a document feature of interest in an alert database based at least in part on the linked set of document features including the proximity cluster; and

generating, by the processor, an electronic user alert regarding the matching.

14. The computer readable medium of claim 13 wherein the instructions further comprise assigning to the disambiguated document feature, by the processor executing a scoring computer module, a confidence score indicative of a level of confidence associated with a degree of disambiguation of the document feature, wherein the disambiguated document feature further matches the document feature of interest in the alert database based at least in part on the confidence score.

15. The computer readable medium of claim 13 wherein the instructions further comprise matching, by the processor executing the in-memory database computer module, the disambiguated document feature with the document feature of interest in the alert database based on a distance parameter associated with the proximity cluster.

16. The computer readable medium of claim 13 wherein the instructions further comprise matching, by the processor executing the in-memory database computer module, the disambiguated document feature with the document feature of interest in the alert database based on graph clustering of the secondary feature.

17. The computer readable medium of claim 13 wherein the disambiguated document feature is selected from the group consisting of a person, a phone number, a location, and a company name.

18. The computer readable medium of claim 13 wherein the extracted document feature and the set of document features are linked temporarily.