Method for in-loop human validation of disambiguated features

• US 9,223,833 B2
• Filed: 12/02/2014
• Issued: 12/29/2015
• Est. Priority Date: 12/02/2013
• Status: Active Grant

• Current Assignee: Finch Computing LLC (Qbase, LLC)
• Original Assignee: Qbase, LLC
• Inventors: Lightner, Scott, Dave, Rakesh, Boddhu, Sanjay
• Primary Examiner(s): MORRISON, JAY A
• Application Number:
  US14/558,237
• Publication Number:
  US 20150154198A1
• Time in Patent Office: 392 Days
• Field of Search: 707/706
• US Class Current: 1/1
• CPC Class Codes: G06F 16/21 Design, administration or maintenance of databases
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Methods for providing in-loop validation of disambiguated features are disclosed. The disclosed methods may include disambiguating features in unstructured text that may use co-occurring features derived from both the source document and a large document corpus. The disambiguating systems may include multiple modules, including a linking on-the-fly module for linking the derived features from the source document to the co-occurring features of an existing knowledge base. The system for disambiguating features may allow identifying unique entities from a knowledge base that includes entities with a unique set of co-occurring features, which in turn may allow for increased precision in knowledge discovery and search results, employing advanced analytical methods over a massive corpus, employing a combination of entities, co-occurring entities, topic IDs, and other derived features. The disclosed method may use validation to provide input to the system for disambiguating features.

Claims

1. A computer-implemented method comprising:

in response to receiving, by a search manager computer, a search query from a user device;

submitting, by the search manager computer, the search query to a search conductor computer module for processing;

receiving, by the search manager computer, search query results from the search conductor computer module, wherein the search query results having one or more records matching one or more fields of the search query, wherein the search query results are based at least in part on the search query;

sending, by the search manager computer, the search query results to a disambiguation analytic computer for disambiguating the search query results by determining relatedness among individual record features and topic identifications (topic IDs) associated with each record in the search query results, wherein the disambiguation analytic computer comprises a main memory storing an in-memory database, wherein the disambiguation analytic computer comprises a linking module which links disambiguation data, in real-time, as the disambiguation data is requested by the search manager computer from the disambiguation analytic computer, wherein the in-memory database is coupled to the linking module, wherein a scoring algorithm is used to determine a probability of at least two individual record features being the same;

receiving, by the search manager computer, disambiguated search query results from the disambiguation analytic computer;

forwarding, by the search manager computer, the disambiguated search query results to the user device for providing an input on the disambiguated search query results; and

in response to receiving, by the search manager computer, the input on the disambiguated search query results from the user device;

creating, by the search manager computer, a new feature occurrence record in a knowledge base database, wherein the new feature occurrence record including the input, wherein the in-memory database comprises the knowledge base database,

storing, by the search manager computer, the new feature occurrence record in the knowledge base database, and

adjusting, by the disambiguation analytic computer, one or more parameters of a disambiguation algorithm based on the input from the user device, wherein the disambiguation algorithm involves at least the linking module.

2. The method of claim 1 wherein the disambiguation analytic computer assigns a confidence score to the new feature occurrence record based on the input from the user device.

3. The method of claim 1 wherein the disambiguation analytic computer adjusts weights associated with the individual record features in the search query results based on the input from the user device.

4. The method of claim 1 wherein the user device includes a user interface that provides an option to select one or more of a set of disambiguation algorithms.

5. The method of claim 4 wherein the user interface provides an option to select a threshold of acceptance for at least one of the individual record features and the topic IDs in the search query results.

6. The method of claim 1 wherein the search query is constructed using a markup language.

7. The method of claim 6 wherein the markup language is one of XML and HTML.

8. The method of claim 1 wherein the search query is constructed in a binary format.

9. The method of claim 1 wherein the search manager computer module validates the input from the user device prior to storing the new feature occurrence record in the knowledge base database.

10. The method of claim 1 wherein the search manager computer processes the search query via one or more processes selected from the group consisting of:

address standardization, proximity boundaries, and nickname interpretation.

11. A system comprising:

one or more server computers comprising a main memory storing an in-memory database, wherein the one or more server computers having one or more processors coupled to the main memory and executing computer readable instructions for a plurality of computer modules including;

a search manager computer module configured to;

in response to a receipt of a search query from a user device;

submit the search query to a search conductor computer module for processing;

receive search query results from the search conductor computer module, wherein the search query results having one or more records matching one or more fields of the search query, wherein the search query results are based at least in part on the search query;

send the search query results to a disambiguation analytic computer module for disambiguating the search query results, wherein the disambiguation analytic computer module is configured to determine relatedness among individual record features and topic identifications (topic IDs) associated with each record in the search query results, wherein the disambiguation analytic computer module is coupled to a linking module which is configured to link disambiguation data, in real-time, as the disambiguation data is requested by the search manager computer module from the disambiguation analytic computer module, wherein the in-memory database is coupled to the linking module, wherein a scoring algorithm is used to determine a probability of at least two individual record features being the same;

receive disambiguated search query results from the disambiguation analytic computer module;

forward the disambiguated search query results to the user device for providing an input on the disambiguated search query results; and

in response to a receipt of the input on the disambiguated search query results from the user device;

create a new feature occurrence record in a knowledge base database, wherein the new feature occurrence record including the input, wherein the in-memory database comprises the knowledge base database,

store the new feature occurrence record in the knowledge base database, wherein the disambiguation analytic computer module is configured to adjust one or more parameters of a disambiguation algorithm based on the input from the user device, wherein the disambiguation algorithm involves at least the linking module.

12. The system of claim 11 wherein the disambiguation analytic computer module is configured to assign a confidence score to the new feature occurrence record based on the input from the user device.

13. The system of claim 11 wherein the disambiguation analytic computer module is configured to adjust weights associated with the individual record features in the search query results based on the input from the user device.

14. The system of claim 11 wherein the user device includes a user interface that provides an option to select one or more of a set of disambiguation algorithms.

15. The system of claim 14 wherein the user interface provides an option to select a threshold of acceptance for at least one of the individual record features and the topic IDs in the search query results.

16. The system of claim 11 wherein the search query is constructed using a markup language.

17. The system of claim 16 wherein the markup language is one of XML and HTML.

18. The system of claim 11 wherein the search query is constructed in a binary format.

19. The system of claim 11 wherein the search manager computer module is configured to validate the input from the user device prior to storing the new feature occurrence record in the knowledge base database.

20. The system of claim 11 wherein the search manager computer module is configured to process the search query via one or more processes selected from the group consisting of:

address standardization, proximity boundaries, and nickname interpretation.