Method and apparatus for providing a co-creation platform

• US 8,543,532 B2
• Filed: 10/05/2009
• Issued: 09/24/2013
• Est. Priority Date: 10/05/2009
• Status: Expired due to Fees

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Sathish, Sailesh Kumar, Lahti, Tommi Juhani
• Primary Examiner(s): Wong, Lut
• Application Number:
  US12/573,522
• Publication Number:
  US 20110082825A1
• Time in Patent Office: 1,450 Days
• Field of Search: 706/55
• US Class Current: 706/55
• CPC Class Codes: G06Q 10/1053 Employment or hiring
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

An approach is provided for providing a co-creation platform. A co-creation application extracts tags from a plurality of information sources reflecting the expertise of a user. The co-creation application creates a model of the user'"'"'s expertise by applying a probabilistic analysis on the extracted tags. The co-creation application collects assignment information including at least one or more specified areas of expertise, and matches the model of the user'"'"'s expertise against the specified areas of expertise.

Claims

1. A method comprising:

extracting tags from a plurality of information sources reflecting the expertise of a user;

creating a model of the user'"'"'s expertise by applying a probabilistic analysis on the extracted tags;

collecting assignment information including at least one or more specified areas of expertise associated with one or more assignment tasks; and

matching the model of the user'"'"'s expertise against the specified areas of expertise associated with the one or more assignment tasks.

2. A method of claim 1, further comprising:

clustering the tags into a plurality of tag sets based on a correlation among the tags within each of the tag sets;

performing probabilistic matching on the tags against an expertise category model to select one or more tags in each tag set with high probabilities of matching;

presenting the selected one or more tags to the user for confirmation; and

inserting the confirmed one or more tags into a user profile,

wherein the model of the user'"'"'s expertise is created using, at least in part, the user profile.

3. A method of claim 2, further comprising:

extracting one or more assignment tags from the assignment information;

compiling the model of the user'"'"'s expertise with a plurality of expertise models corresponding to other users;

mapping the one or more assignment tags to the compilation of user expertise models to determine one or more best matching user expertise models; and

selecting one or more users corresponding to the determined one or more user expertise models to take the assignment.

4. A method of claim 1, further comprising:

calculating a first appearance frequency value of each of the tags relative to an entirety of each of the plurality of information sources;

calculating a second appearance frequency value of each of the tags relative to one or more pages of each of the plurality of information sources in which the tag appears;

normalizing the first and second appearance frequency values of each tag to be in a predetermined range; and

forming a metric for each of the tags with the first and second appearance frequency values as corresponding fields in the metric,

wherein the probabilistic analysis includes, at least in part, analysis of the metric.

5. A method of claim 4, further comprising:

calculating a correlation value between each of the one or more categories selected for inclusion in the model of the user'"'"'s expertise and each of the tags extracted from the information sources;

obtaining an overall correlation for each of the one or more categories by adding together the correlation values corresponding to each of the respective one or more categories;

computing a weighting factor for the each of the one or more categories by averaging the metric of the each of the tags and the overall correlation value corresponding to each of the one or more categories;

causing, at least in part, actions that result in sending the weighting factors to the user for confirmation; and

adjusting the model of the user'"'"'s expertise based upon the weighting factors as confirmed by the user.

6. A method of claim 2, further comprising:

receiving an input, from the user, specifying a professional or social website;

soliciting a rating of the user based upon the one or more categories included in the model of the user'"'"'s expertise by peers associated with the professional or social website; and

adjusting the model of the user'"'"'s expertise based upon the rating.

7. A method of claim 1, wherein the model of the user'"'"'s expertise matches the specified areas of expertise, and the method further comprising:

causing, at least in part, transmission of the assignment information to a mobile terminal of the user;

extracting a content requirement from the assignment information;

performing a query in a database for the content requirement; and

receiving content from the database, in response to the query.

8. An apparatus comprising:

at least one processor; and

at least one memory including computer program code,

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,

extract tags from a plurality of information sources reflecting the expertise of a user;

create a model of the user'"'"'s expertise by applying a probabilistic analysis on the extracted tags;

collect assignment information including at least one or more specified areas of expertise associated with one or more assignment tasks; and

match the model of the user'"'"'s expertise against the specified areas of expertise associated with the one or more assignment tasks.

9. An apparatus of claim 8, wherein the apparatus is further caused to:

cluster the tags into a plurality of tag sets based on a correlation among the tags within each of the tag sets;

perform probabilistic matching on the tags against an expertise category model to select one or more tags in each tag set with high probabilities of matching;

present the selected one or more tags to the user for confirmation; and

insert the confirmed one or more tags into a user profile,

wherein the model of the user'"'"'s expertise is created using, at least in part, the user profile.

10. An apparatus of claim 9, wherein the apparatus is further caused to:

extract one or more assignment tags from the assignment information;

compile the model of the user'"'"'s expertise with a plurality of expertise models corresponding to other users;

map the one or more assignment tags to the compilation of user expertise models to determine one or more best matching user expertise models; and

select one or more users corresponding to the determined one or more user expertise models to take the assignment.

11. An apparatus of claim 8, wherein the apparatus is further caused to:

calculate a first appearance frequency value of each of the tags relative to an entirety of each of the plurality of information sources;

calculate a second appearance frequency value of each of the tags relative to one or more pages of each of the plurality of information sources in which the tag appears;

normalize the first and second appearance frequency values of each tag to be in a predetermined range; and

form a metric for each of the tags with the first and second appearance frequency values as corresponding fields in the metric,

wherein the probabilistic analysis includes, at least in part, analysis of the metric.

12. An apparatus of claim 11, wherein the apparatus is further caused to:

calculate a correlation value between each of the one or more categories selected for inclusion in the model of the user'"'"'s expertise and each of the tags extracted from the information sources;

obtain an overall correlation for each of the one or more categories by adding together the correlation values corresponding to each of the respective one or more categories;

compute a weighting factor for the each of the one or more categories by averaging the metric of the each of the tags and the overall correlation value corresponding to each of the one or more categories;

cause, at least in part, actions that result in sending the weighting factors to the user for confirmation; and

adjust the model of the user'"'"'s expertise based upon the weighting factors as confirmed by the user.

13. An apparatus of claim 9, wherein the apparatus is further caused to:

receive an input, from the user, specifying a professional or social website;

solicit a rating of the user based upon the one or more categories included in the model of the user'"'"'s expertise by peers associated with the professional or social website; and

adjust the model of the user'"'"'s expertise based upon the rating.

14. An apparatus of claim 11, wherein the model of the user'"'"'s expertise matches the specified areas of expertise, and wherein the apparatus is further caused to:

cause, at least in part, transmission of the assignment information to a mobile terminal of the user;

extract a content requirement from the assignment information;

perform a query in a database for the content requirement; and

receive content from the database, in response to the query.

15. A computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:

extracting tags from a plurality of information sources reflecting the expertise of a user;

creating a model of the user'"'"'s expertise by applying a probabilistic analysis on the extracted tags;

collecting assignment information including at least one or more specified areas of expertise associated with one or more assignment tasks; and

matching the model of the user'"'"'s expertise against the specified areas of expertise associated with the one or more assignment tasks.

16. A computer-readable storage medium of claim 15, wherein the apparatus is caused to further perform:

clustering the tags into a plurality of tag sets based on a correlation among the tags within each of the tag sets;

performing probabilistic matching on the tags against an expertise category model to select one or more tags in each tag set with high probabilities of matching;

presenting the selected one or more tags to the user for confirmation; and

inserting the confirmed one or more tags into a user profile,

wherein the model of the user'"'"'s expertise is created using, at least in part, the user profile.

17. A computer-readable storage medium of claim 16, wherein the apparatus is caused to further perform:

extracting one or more assignment tags from the assignment information;

compiling the model of the user'"'"'s expertise with a plurality of expertise models corresponding to other users;

mapping the one or more assignment tags to the compilation of user expertise models to determine one or more best matching user expertise models; and

selecting one or more users corresponding to the determined one or more user expertise models to take the assignment.

18. A computer-readable storage medium of claim 15, wherein the apparatus is caused to further perform:

calculating a first appearance frequency value of each of the tags relative to an entirety of each of the plurality of information sources;

calculating a second appearance frequency value of each of the tags relative to one or more pages of each of the plurality of information sources in which the tag appears;

normalizing the first and second appearance frequency values of each tag to be in a predetermined range; and

forming a metric for each of the tags with the first and second appearance frequency values as corresponding fields in the metric,

wherein the probabilistic analysis includes, at least in part, analysis of the metric.

19. A computer-readable storage medium of claim 18, wherein the apparatus is caused to further perform:

calculating a correlation value between each of the one or more categories selected for inclusion in the model of the user'"'"'s expertise and each of the tags extracted from the information sources;

obtaining an overall correlation for each of the one or more categories by adding together the correlation values corresponding to each of the respective one or more categories;

computing a weighting factor for the each of the one or more categories by averaging the metric of the each of the tags and the overall correlation value corresponding to each of the one or more categories;

causing, at least in part, actions that result in sending the weighting factors to the user for confirmation; and

adjusting the model of the user'"'"'s expertise based upon the weighting factors as confirmed by the user.

20. A computer-readable storage medium of claim 16, wherein the apparatus is caused to further perform:

receiving an input, from the user, specifying a professional or social website;

soliciting a rating of the user based upon the one or more categories included in the model of the user'"'"'s expertise by peers associated with the professional or social website; and

adjusting the model of the user'"'"'s expertise based upon the rating.