Expert discovery using user query navigation paths

Patent metadata

Field	Value
Publication number	US-10831749-B2
Application number	US-201815970854-A
Country	US
Kind code	B2
Filing date	May 3, 2018
Priority date	May 3, 2018
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

A computing device determines that a user submits a query. The computing device tracks proximate web activities to the query by the user, determines a topic of the query, and determines a navigation path of the user from the proximate web activities. The computing device calculates a semantic score for the navigation path and associates the semantic score with the user, the topic, and the navigation path. The computing device calculates a threshold score for the topic using a sampling of semantic scores associated with matching topics in an expertise dataset and determines whether the semantic score meets the threshold score. When the semantic score does not meet the threshold score, the computing device performs one or more predetermined actions. An efficient manner of automatically discovering navigation paths used by experts in specific topics is provided, thus requiring less computing time and resources.

First claim

What is claimed is:

1. A method for expert discovery using user query navigation paths, comprising:
intercepting, by a computing device, a query submitted to a web server by a user;
in response to the interception of the query, triggering a tracking, by the computing device, of web activities by the user, the web activities comprising an order of webpages visited by the user after submission of the query;
determining, by the computing device, a topic of the query;
associating with the user, by the computing device, a navigation path comprising the web activities;
calculating, by the computing device, a semantic score for the navigation path associated with the user using a cognitive model, the semantic score for the navigation path associated with the user representing a level of expertise of the user in the topic, the cognitive model previously trained with a dataset from an expertise database comprising semantic scores for navigation paths associated with known experts in the topic;
calculating, by the computing device, a threshold score for the topic using a sampling of the semantic scores for the navigation paths associated with the known experts in the topic in the expertise database, the threshold score representing a level of expertise above which a particular user is considered to be an expert in the topic;
determining, by the computing device, whether the semantic score for the navigation path associated with the user meets the threshold score for the topic; and
when the semantic score for the navigation path associated with the user does not meet the threshold score for the topic, performing one or more predetermined actions.

2. The method of claim 1 , wherein the calculating of the semantic score for the navigation path associated with the user using the cognitive model comprises: processing, by the cognitive model, one or more of the following parameters:
an expertise of the user derived from a plurality of sources, wherein the semantic score for the navigation path associated with the user is adjusted when the user is determined to be an expert in the topic;
a number of steps in the navigation path associated with the user;
a relevancy of contents of one or more webpages in the navigation path associated with the user;
ranking of the webpages in the navigation path associated with the user according to levels of relevancy to the topic;
the user's interactions with the webpages in the navigation path associated with the user; and
an amount of time the user spends on the webpages in the navigation path associated with the user.

3. The method of claim 2 , wherein the one or more parameters further comprises at least one follow-up query, wherein the method further comprises:
after submission of the follow-up query, calculating a second semantic score for a second navigation path associated with the user using the cognitive model; and
calculating a composite semantic score for the navigation path and the second navigation path associated with the user.

4. The method of claim 1 , wherein the predetermined actions comprise one or more of the following:
sending a message to the user to connect to another user determined to be an expert in the topic;
sending one or more recommendations of webpages based on webpages in topic-relevant navigation paths in the expertise database; and
sending one or more recommendations for modifications to the navigation path associated with the user based on differences with the topic-relevant navigation paths in the expertise database.

5. A computer program product for expert discovery using user query navigation paths, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
intercept a query submitted to a web server by a user;
in response to the interception of the query, trigger a tracking of web activities by the user, the web activities comprising an order of webpages visited by the user after submission of the query;
determine a topic of the query;
associate with the user a navigation path comprising the web activities;
calculate a semantic score for the navigation path associated with the user using a cognitive model, the semantic score for the navigation path associated with the user representing a level of expertise of the user in the topic, the cognitive model previously trained with a dataset from an expertise database comprising semantic scores for navigation paths associated with known experts in the topic;
calculate a threshold score for the topic using a sampling of the semantic scores for the navigation paths associated with the known experts in the topic in the expertise database, the threshold score representing a level of expertise above which a particular user is considered to be an expert in the topic;
determine whether the semantic score for the navigation path associated with the user meets the threshold score for the topic; and
when the semantic score for the navigation path associated with the user does not meet the threshold score for the topic, perform one or more predetermined actions.

6. The computer program product of claim 5 , wherein the calculating of the semantic score for the navigation path associated with the user using the cognitive model comprises: processing, by the cognitive model, one or more of the following parameters:
an expertise of the user derived from a plurality of sources, wherein the semantic score for the navigation path associated with the user is adjusted when the user is determined to be an expert in the topic;
a number of steps in the navigation path associated with the user;
a relevancy of contents of one or more webpages in the navigation path associated with the user;
ranking of the webpages in the navigation path associated with the user according to levels of relevancy to the topic;
the user's interactions with the webpages in the navigation path associated with the user; and
an amount of time the user spends on the webpages in the navigation path associated with the user.

7. The computer program product of claim 6 , wherein the one or more parameters further comprises at least one follow-up query, wherein the processor is further caused to:
after submission of the follow-up query, calculate a second semantic score for a second navigation path associated with the user using the cognitive model; and
calculate a composite semantic score for the navigation path and the second navigation path associated with the user.

8. The computer program product of claim 5 , wherein the predetermined actions comprise one or more of the following:
sending a message to the user to connect to another user determined to be an expert in the topic;
sending one or more recommendations of webpages based on webpages in topic-relevant navigation paths in the expertise database; and
sending one or more recommendations for modifications to the navigation path associated with the user based on differences with the topic-relevant navigation paths in the expertise database.

9. A system comprising:
a processor; and
a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
intercept a query submitted to a web server by a user;
in response to the interception of the query, trigger a tracking of web activities by the user, the web activities comprising an order of webpages visited by the user after submission of the query;
determine a topic of the query;
associate with the user a navigation path comprising the web activities;
calculate a semantic score for t

Assignees

• IBM

Inventors

• Silva Asima
• Cunico Hernan A
• Joyce Declan
• Harpur Liam S

Classifications

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/2453 Primary

  Query optimisation · CPC title