Calculating expertise confidence based on content and social proximity

Patent metadata

Field	Value
Publication number	US-11151663-B2
Application number	US-201816185013-A
Country	US
Kind code	B2
Filing date	Nov 9, 2018
Priority date	Dec 17, 2014
Publication date	Oct 19, 2021
Grant date	Oct 19, 2021

Abstract

A document-oriented search can be executed to generate a set of document results, at least one of the documents associated with at least one potential expert. The document results can be analyzed to produce a list of potential experts. An expertise score for at least one of the potential experts can be calculated based on a content score and a metadata score for the at least one of the potential experts. A confidence score for the potential expert can be calculated based on a diversity-constrained content score and a diversity-constrained metadata score for the at least one of the potential experts, the diversity-constrained content score and the diversity-constrained metadata score calculated using an evidence diversity score for the at least one of the potential experts. A list of experts with associated confidence scores that are above a confidence score threshold can be sent to a client device.

First claim

What is claimed is:

1. A system, comprising:
a processor programmed to initiate executable operations comprising:
executing a document-oriented search based on a query in an index of documents of a search engine to generate a set of document results, the index of documents storing content documents and metadata associated with a plurality of potential experts;
analyzing the set of document results to produce a list of potential experts;
calculating, using the content documents and metadata, an expertise score for each potential expert in the list of potential experts based on a content score and a metadata score for the potential expert;
calculating a confidence score for each potential expert in the list of potential experts based on a diversity-constrained content score and a diversity-constrained metadata score for the potential expert, the diversity-constrained content score and the diversity-constrained metadata score calculated using an evidence diversity score for the potential expert, wherein:
the evidence diversity score used to calculate the diversity-constrained content score indicates a threshold number of different content document types and associations, the content document types associated with the potential expert within the document results, and associations of the potential expert with each of the document results, the content document types and associations gathered by parsing websites and stored in a data repository, and
the evidence diversity score used to calculate the diversity constrained metadata score indicates a threshold number of different metadata types associated with the at least one of the potential experts within the document results, the metadata types stored in the data repository; and

filtering the list of potential experts based on the confidence scores to generate a list of experts, each expert associated with a confidence score above a threshold;
sending the list of experts to a client device.

2. The system of claim 1 , the executable operations further comprising:
selecting a predetermined number of potential experts with expertise scores above a threshold from the list of potential experts and calculating an evidence diversity score for each selected potential expert; and
calculating the confidence score for at least one of the selected potential experts based on a diversity-constrained content score and a diversity-constrained metadata score for the at least one of the selected potential experts, the diversity-constrained content score and the diversity-constrained metadata score calculated using the evidence diversity score for the at least one of the selected potential experts.

3. The system of claim 2 , wherein the calculating the confidence score for the at least one of the selected potential experts further is based on a social score, the executable operations further comprising:
generating a graph of connections between the selected predetermined number of potential experts, the social score for the at least one of the selected potential experts calculated using the graph and based on a number of connections to other selected potential experts.

4. The system of claim 3 , wherein the graph of connections between the predetermined number of selected potential experts comprises at least one edge connecting at least two selected potential experts that share an association with a same content document that is relevant to the query.

5. The system of claim 4 , wherein the graph of connections between the predetermined number of selected potential experts further comprises context-free relations, wherein the context-free relations are social relations that are unrelated to a context of the query and unrelated to content documents.

6. The system of claim 1 , wherein the calculating the confidence score for each potential expert is further based on preconfigured thresholds.

7. The system of claim 1 , wherein the query comprises an expertise, and the confidence score is used to indicate a level of certainty in the expertise for the at least one of the potential experts.

8. The system of claim 1 , the executable operations further comprising sorting the list of experts by expertise scores.

9. A computer program product comprising a computer readable storage medium having program code stored thereon, the program code executable by a data processing system to initiate operations including:
executing a document-oriented search based on a query in an index of documents of a search engine to generate a set of document results, the index of documents storing content documents and metadata associated with a plurality of potential experts;
analyzing the set of document results to produce a list of potential experts;
calculating, using the content documents and metadata, an expertise score for each potential expert in the list of potential experts based on a content score and a metadata score for the potential expert;
calculating a confidence score for each potential expert in the list of potential experts based on a diversity-constrained content score and a diversity-constrained metadata score for the potential expert, the diversity-constrained content score and the diversity-constrained metadata score calculated using an evidence diversity score for the potential expert, wherein:
the evidence diversity score used to calculate the diversity-constrained content score indicates a threshold number of different content document types and associations, the content document types associated with the potential expert within the document results, and associations of the potential expert with each of the document results, the content document types and associations gathered by parsing websites and stored in a data repository, and
the evidence diversity score used to calculate the diversity constrained metadata score indicates a threshold number of different metadata types associated with the at least one of the potential experts within the document results, the metadata types stored in the data repository; and

filtering the list of potential experts based on the confidence scores to generate a list of experts, each expert associated with a confidence score above a threshold;
sending the list of experts to a client device.

10. The computer program product of claim 9 , the operations further comprising:
selecting a predetermined number of potential experts with expertise scores above a threshold from the list of potential experts and calculating an evidence diversity score for each selected potential expert; and
calculating the confidence score for at least one of the selected potential experts based on a diversity-constrained content score and a diversity-constrained metadata score for the at least one of the selected potential experts, the diversity-constrained content score and the diversity-constrained metadata score calculated using the evidence diversity score for the at least one of the selected potential experts.

11. The computer program product of claim 10 , wherein the calculating the confidence score for the at least one of the selected potential experts further is based on a social score, the executable operations further comprising:
generating a graph of connections between the selected predetermined number of potential experts, the social score for the at least one of the selected potential experts calculated using the graph and based on a number of connections to other selected potential experts.

12. The computer program product of claim 11 , wherein the graph of connections between the predetermined number of selected potential experts comprises at least one edge connecting at least two selected potential experts that sha

Assignees

• IBM

Inventors

• Bolshinsky Leonid
• Ronen Inbal
• Shapiro Eitan
• Yogev Arnon

Classifications

• G06Q10/40 Primary

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

• G06F16/248

  Presentation of query results · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/2455

  Query execution · CPC title