Methods and systems for retrieval of experts based on user customizable search and ranking parameters

• US 9,684,713 B2
• Filed: 12/23/2013
• Issued: 06/20/2017
• Est. Priority Date: 06/23/2011
• Status: Active Grant

• Current Assignee: Expect System France
• Original Assignee: Expect System France
• Inventors: Bhandari, Archna, Baker, Kirk
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US14/138,783
• Publication Number:
  US 20140181098A1
• Time in Patent Office: 1,275 Days
• Field of Search: 707728
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems

Abstract

Methods and systems for finding experts based upon user customizable search and ranking criteria, and providing the search results at a person or expert level are disclosed. The methods generally entail cataloging data within one or more document databases, and includes the steps of (a) inputting disparate data sources which may include publications, awarded grants, clinical trials, and/or patents; (b) processing the data within each document in the document database(s); (c) creating a document profile for each document using relevant keywords; (d) assigning weighting factors to the relevant keywords based upon selected attributes; (e) assigning an identifier to each document and document author; (f) removing duplicate document data using a disambiguation algorithm; (g) extracting author level attributes from the retrieved documents; and (h) creating or updating each document profile. The method steps may be implemented using a system of computer servers communicatively linked to a plurality of clients via a global network.

Claims

1. A method for cataloging a data set using a computer processor, the method comprising the steps of:

(a) accessing a plurality of documents stored in the data set;

(b) processing data, text and content of each of the plurality of documents;

(c) creating a document profile for each of the plurality of documents processed, using relevant document metrics;

(d) assigning a unique identifier to each of the plurality of documents processed;

(e) mapping the document profile data using standardization algorithms;

(f) removing duplicate documents based upon the mapped document profiles;

(g) integrating the document profile data for consistency using a plurality of data set attributes;

(h) creating a document profile database using the plurality of data set attributes;

(i) indexing said document profile database;

(j) updating said document profile database periodically to incorporate new data set data;

(k) selecting, by a user, ones of the relevant document metrics of the document profile;

(l) assigning, by the user, a weighting coefficient to each of the selected relevant document metrics;

(m) aggregating relevant document profiles based on the relevant document metrics for each of the experts, and creating an expert profile, and

(n) providing a ranking of experts using the assigned weighting coefficients.

2. The method for cataloging a data set using a computer processor, as described in claim 1, further comprising the step of:

(e1) assigning a unique identifier to an author attribute for each of the plurality of documents processed.

3. The method for cataloging a data set using a computer processor, as described in claim 2, further comprising the step of:

(e2) assigning a unique identifier to each of the plurality of created document profiles.

4. The method for cataloging a data set using a computer processor, as described in claim 1, wherein the metrics of step (c) includes one or more of keywords or concepts.

5. The method for cataloging a data set using a computer processor, as described in claim 4, wherein the one or more keywords or concepts, includes one or more of:

publications, grants, proceedings, standards, guidelines, clinical trials, patent applications, or patents.

6. The method for cataloging a data set using a computer processor, as described in claim 4, wherein the one or more keywords or concepts, includes one or more of:

bibliographic information about publications, date range, first author, last author, or h-index.

7. The method for cataloging a data set using a computer processor, as described in claim 4, wherein the one or more keywords or concepts, includes one or more of:

an individual'"'"'s attributes, name, clinical experience, language, country, affiliation, address, email address, or social media address.

8. The method for cataloging a data set using a computer processor, as described in claim 1, wherein the relevant document metrics of step (c) are user-selected metrics.

9. A method for identifying expertise data within one or more document databases using a computer processor, the method comprising the steps of:

(a) inputting into a computer processor a plurality of data sources, said data sources having respective expertise data and expertise content;

(b) processing the expertise data and expertise content of each data source within the one or more document databases;

(c) creating a document profile for each data source using document relevant metrics;

(d) assigning a unique identifier to each data source;

(e) implementing a disambiguation algorithm on each of the created document profiles;

(f) removing duplicate data sources based upon implementation of the disambiguation algorithm;

(g) extracting expert level attributes from the processed data sources;

(h) creating a document profile database;

(i) updating said document profile database;

(j) selecting, by a user, ones of the document relevant metrics of the document profile;

(k) assigning, by the user, a weighting coefficient to each of the selected document relevant metrics;

(l) aggregating relevant document profiles based on the document relevant metrics for each of the experts, and creating an expert profile; and

(m) providing a ranking of experts using the assigned weighting coefficients.

10. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, further comprising the step of:

(m) providing interactive analytic tools to locate particular experts based upon further expert level attributes.

11. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, wherein the respective expertise data and expertise content of step (a) includes one or more of:

publications, conference proceedings, awarded grants, clinical trials, standards, guidelines, patent applications and/or patents.

12. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, wherein the document relevant metrics of step (c) includes one or more of:

bibliographic information about publications, date range, first author, last author, h-index, or journal ranking.

13. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, wherein the document relevant metrics of step (c) includes one or more of:

an individual'"'"'s attributes, name, substantive expertise, language, country, affiliation, address, email address, or social media address.

14. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, further comprising the step of:

(e1) assigning a unique identifier to an author attribute for each of the data sources processed.

15. The method for identifying expertise data within one or more document databases using a computer processor, as described in claim 9, further comprising the step of:

(e2) assigning a unique identifier to each of the document profiles created.

16. A method for cataloging an expert data set using a computer processor, the method comprising the steps of:

(a) accessing a plurality of documents stored in the data set, said documents each having expert information and data;

(b) processing the expert information and data of each of the plurality of documents;

(c) creating a document profile for each of the plurality of documents processed, using document relevant metrics;

(d) assigning a unique identifier to each of the plurality of documents processed;

(e) mapping the document profile data using standardization algorithms;

(f) removing duplicate documents based upon the mapped document profiles;

(g) integrating the document profile data for consistency using the plurality of data set attributes;

(h) creating a document profile database using a plurality of data set attributes;

(i) indexing said document profile database;

(j) updating said document profile database periodically to incorporate new data set information;

(k) selecting, by a user, ones of the document relevant metrics of the document profile;

(l) assigning, by the user, a weighting coefficient to each of the selected document relevant metrics;

(m) aggregating relevant document profiles based on the document relevant metrics for each of the experts, and creating an expert profile; and

(n) providing a ranking of experts using the assigned weighting coefficients.

17. The method for cataloging an expert data set using a computer processor, as described in claim 16, further comprising the step of:

(e1) assigning a unique identifier to an author attribute for each of the plurality of documents processed.

18. The method for cataloging an expert data set using a computer processor, as described in claim 16, further comprising the step of:

(e2) assigning a unique identifier to each of the plurality of created document profiles.

19. The method for cataloging an expert data set using a computer processor, as described in claim 16, wherein the metrics of step (c) includes one or more of keywords or concepts.

20. The method for cataloging an expert data set using a computer processor, as described in claim 16, wherein the respective expert information and data of step (a) includes one or more of:

publications, conference proceedings, awarded grants, standards, guidelines, patent applications and/or patents.

21. The method for cataloging an expert data set using a computer processor, as described in claim 16, further comprising the step of:

(1) providing interactive analytic tools to locate particular experts based upon further expert level attributes.

22. A computerized system for electronically cataloging an expert data set, comprising:

a plurality of computer processors communicatively linked to a plurality of users, wherein the plurality of computer processors implement the method steps of;

(a) accessing a plurality of documents stored in the data set, said documents each having expert information and data;

(b) processing the expert information and data of each of the plurality of documents;

(c) creating a document profile for each of the plurality of documents processed, using document relevant metrics;

(d) assigning a unique identifier to each of the plurality of documents processed;

(e) mapping the document profile data using standardization algorithms;

(f) removing duplicate documents based upon the mapped document profiles;

(g) integrating the document profile data for consistency using the plurality of data set attributes;

(h) creating a document profile database using the plurality of data set attributes;

(i) indexing said document profile database;

(j) updating said document profile database periodically to incorporate new data set information;

(k) selecting, by a user, ones of the document relevant metrics of the document profile;

(l) assigning, by the user, a weighting coefficient to each of the selected document relevant metrics;

(m) aggregating relevant document profiles based on the document relevant metrics for each of the experts, and creating an expert profile; and

(n) providing a ranking of experts using the assigning weighting coefficients.

23. The computerized system for electronically cataloging an expert data set, as described in claim 22, wherein the plurality of computer processors are communicatively linked to a plurality of users, using the internet.