Method and apparatus for processing a query based on associating intent and audience

Patent metadata

Field	Value
Publication number	US-9886509-B2
Application number	US-201114343030-A
Country	US
Kind code	B2
Filing date	Sep 8, 2011
Priority date	Sep 8, 2011
Publication date	Feb 6, 2018
Grant date	Feb 6, 2018

Abstract

An approach is provided for determining the intent of a question and determining an appropriate audience to answer the question based on the intent of the question. The approach comprises processing and/or facilitating a processing of a query to cause, at least in part, a determination of one or more topics of the query based, at least in part, on one or more user preferences. The approach also comprises processing and/or facilitating a processing of the query to cause, at least in part, a determination of a classification of the query, The approach further comprises determining an audience comprising one or more candidate audience members for the query based, at least in part, on the classification of the query and the one or more topics of the query.

First claim

What is claimed is:

1. A method for processing a query based on associating intent and audience, the method comprising:
receiving, utilizing at least one interface, the query including text from a user;
parsing, utilizing at least one processor, the text of the received query to identify one or more words and/or terms associated with the query;
calculating a probability that the identified one or more words and/or terms are associated with one or more topics;
identifying the associated one or more topics with the received query based on the calculated probability meeting or exceeding a predetermined threshold;
mapping the identified one or more topics of the query to predetermined topics associated with the user based on one or more calculations determining a probability that the query belongs to the one or more topics that is a subset of the predetermined topics associated with the user;
classifying the query as belonging to a public question class, a personal request class or a combination thereof based, at least in part, on the identified one or more topics;
determining one or more candidate audience members for forwarding the query based, at least in part, on the classification of the query and the one or more mapped predetermined topics of the query associated with the user that are shared by the one or more candidate audience members; and
forwarding, utilizing the at least one interface, the query via a network to one or more devices of the one or more candidate audience members.

2. A method of claim 1 , wherein the one or more candidate audience members are further determined based on a proficiency score that is based, at least in part, on a similarity between the one or more topics of the query and topics associated with a profile of the one or more candidate audience members, wherein the profile includes one or more preferences of the one or more candidate audience members.

3. A method of claim 2 , further comprising:
determining a social score that is a social distance between the user and the one or more candidate audience members in one or more social networks,
wherein the one or more candidate audience members are further determined based on the social score.

4. A method of claim 3 , further comprising:
determining an inactivity factor of the one or more candidate audience members that affects the determination of the audience; and
initiating a depreciation of a likelihood that one or more of the candidate audience members will answer the query based, at least in part, on the inactivity factor,
wherein the one or more candidate audience members are further determined based on the likelihood.

5. A method of claim 3 , further comprising:
determining an importance factor of the one or more candidate audience members in the one or more social networks,
wherein the one or more candidate audience members are further determined based on the importance factor.

6. A method of claim 1 , further comprising:
determining a ranking of the one or more candidate audience members in the order of a likelihood that the one or more candidate audience members will answer the query; and
initiating a presentation of the audience in the ranked order of candidate audience members.

7. A method of claim 1 , further comprising:
initiating a database search for the one or more candidate audience members ui based on following:
rank( ui,uj,q )= e −αt(ui) × [ P rc ×TRR ( ui,q )+(1 −P rc )× R ( ui,uj )]× Inf ( ui )

wherein TRR(ui,q) is a proficiency score that measures a similarity between a profile of ui and the query q based on topics associated with the profile Tu and the one or more topics of the query Tq,
R(ui,uj) is a social score that measures a social distance between ui and the user uj in one or more online social networks,
e−at(ui) is an inactivity factor goes against the social score of ui,
Prc is a probability that q belongs to a public query class, and
Inf(ui) is an importance factor that measures importance of ui on the one or more online social networks.

8. A method of claim 1 , wherein the classification is based, at least in part, on a rule-based calculation, a fuzzy logic-based calculation, or a combination thereof.

9. An apparatus for processing a query based on associating intent and audience, the apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs,
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,
receive, utilizing at least one interface, the query including text from a user;
parse, utilizing at least one processor, the text of the received query to identify one or more words and/or terms associated with the query;
calculate a probability that the identified one or more words and/or terms are associated with one or more topics;
identify the associated one or more topics with the received query based on the calculated probability meeting or exceeding a predetermined threshold;
map the identified one or more topics of the query to predetermined topics associated with the user based on one or more calculations determining a probability that the query belongs to the one or more topics that is a subset of the predetermined topics associated with the user;
classify the query as belonging to a public question class, a personal request class or a combination thereof based, at least in part, on the identified one or more topics;
determine one or more candidate audience members for forwarding the query based, at least in part, on the classification of the query and the one or more mapped predetermined topics of the query associated with the user that are shared by the one or more candidate audience members; and
forward, utilizing the at least one interface, the query via a network to one or more devices of the one or more candidate audience members.

10. An apparatus of claim 9 , wherein the apparatus is further caused to:
determine a social score that is a social distance between the user and the one or more candidate audience members in one or more social networks,
wherein the one or more candidate audience members are further determined based on the social score.

11. An apparatus of claim 10 , wherein the apparatus is further caused to:
determine an importance factor of the one or more candidate audience members in the one or more social networks,
wherein the one or more candidate audience members are further determined based on the importance factor.

12. An apparatus of claim 9 , wherein the apparatus is further caused to:
determine an inactivity factor of the one or more candidate audience members that affects the determination of the audience; and
initiate a depreciation of a likelihood that one or more of the candidate audience members will answer the query based, at least in part, on the inactivity factor,
wherein the one or more candidate audience members are further determined based on the likelihood.

13. An apparatus of claim 9 , wherein the apparatus is further caused to:
determine a ranking of the one or more candidate audience members in the order of a likelihood that the one or more candidate audience members will answer the query; and
initiate a presentation of the audience in the ranked order of candidate audience members.

14. An apparatus of claim 9 , wherein the apparatus is further caused to:
initiate a database search for the one or more candidate audience members ui based on following:
rank( ui,uj,q )= e −αt(ui) × [ P rc ×TRR ( ui,q )+(1 −P rc )× R (

Assignees

• Du Nan
• Wang Hao
• Guo Liang
• Cui Yidong
• Wang Wendong
• Nokia Technologies Oy

Inventors

• Du Nan
• Wang Hao
• Guo Liang
• Cui Yidong
• Wang Wendong

Classifications

• G06Q10/40

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

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title

• G06F17/30702

  Physics · mapped topic

• G06Q10/101

  Collaborative creation, e.g. joint development of products or services · CPC title

• G06Q50/01

  Physics · mapped topic