Method and system for efficient matching of user profiles with audience segments
View Patent ↗Embodiments of the present teachings disclose method, system, and programs that monetize personalized user behavioral profiles by remapping the users to audience segments related to advertisement. In the method, the users can be targeted with advertisements that are personalized and hence are more likely to lead to conversions.
1. A method implemented on a machine having at least one processor, storage, and a communication interface connected to a network for providing content, the method comprising:
obtaining a user profile characterizing a user with respect to a first feature space;
obtaining information about one or more advertisement audience segments, each of which is associated with at least one advertisement and one or more keywords representing commercial interests associated with the advertisement audience segment;
retrieving one or more pieces of content with respect to each of the one or more advertisement audience segments based, at least in part, on the one or more keywords representing the commercial interests associated with the advertisement audience segment, wherein the one or more pieces of content have information consistent with the commercial interests associated with the advertisement audience segment;
generating, for each of the one or more advertisement audience segments, an advertisement audience segment profile in a second feature space, based on the corresponding retrieved one or more pieces of content, to characterize the advertisement audience segment;
correlating the user profile with each of the advertisement audience segment profiles;
selecting one of the one or more advertisement audience segments based on degree of the correlation; and
outputting the at least one advertisement associated with the selected advertisement audience segment to the user, wherein
the first and second feature spaces correspond to the same feature space.
2. The method of claim 1 , wherein the first feature space is a content taxonomy and the second feature space is an advertisement taxonomy.
3. The method of claim 1 , wherein the first feature space is a universal interest index.
4. The method of claim 1 , wherein the user profile is correlated with each of the advertisement audience segment profiles by mapping at least some of a first set of attributes associated with the user profile to a second set of attributes associated with the advertisement audience segment profile.
5. The method of claim 4 , wherein each of the first set of attributes is assigned with a weight factor with respect to the second feature space, where the weight factor represents importance of the attribute in distinguishing a corresponding advertisement audience segment in the second feature space.
6. The method of claim 1 , further comprising:
selecting one of the at least one advertisement for outputting based on at least one of:
click through rate of each of the at least one advertisement;
revenue associated with each of the at least one advertisement; and
quality of each of the at least one advertisement.
7. The method of claim 1 , wherein the at least one advertisement is presented to the user in a content stream, where the content stream includes one or more pieces of content associated with the user profile.
8. The method of claim 1 , wherein the retrieved one or more pieces of content include one or more search result pages obtained by searching based on the one or more keywords.
9. The method of claim 1 , wherein the retrieved one or more pieces of content further include one or more pages linked with the at least one advertisement associated with the advertisement audience segment.
10. The method of claim 1 , wherein generating an advertisement audience segment profile comprises:
extracting a set of features from the retrieved one or more pieces of content based on the second feature space; and
determining a weight for each of the set of features based on a machine learning model.
11. A system having at least one processor, a storage, and a communication platform for providing content, the system comprising:
a first profile obtainer configured for obtaining a user profile characterizing a user with respect to a first feature space;
a second profile obtainer configured for
obtaining information about one or more advertisement audience segments, each of which is associated with at least one advertisement and one or more keywords representing commercial interests associated with the advertisement audience segment,
retrieving one or more pieces of content with respect to each of the one or more advertisement audience segments based, at least in part, on the one or more keywords representing the commercial interests associated with the advertisement audience segment, wherein the one or more pieces of content have information consistent with the commercial interests associated with the advertisement audience segment, and
generating, for each of the one or more advertisement audience segments, an advertisement audience segment profile in a second feature space, based on the corresponding retrieved one or more pieces of content, to characterize the advertisement audience segment;
a correlator configured for correlating the user profile with each of the advertisement audience segment profiles and selecting one of the one or more advertisement audience segments based on degree of the correlation; and
an output configured for outputting the at least one advertisement associated with the selected advertisement audience segment to the user, wherein
the first and second feature spaces correspond to the same feature space.
12. The system of claim 11 , wherein the first feature space is a content taxonomy and the second feature space is an advertisement taxonomy.
13. The system of claim 11 , wherein a piece of content associated with the second feature space is an advertisement.
14. The system of claim 11 , further comprising:
selecting one of the at least one advertisement for outputting based on at least one of:
click through rate of each of the at least one advertisement;
revenue associated with each of the at least one advertisement; and
quality of each of the at least one advertisement.
15. The system of claim 11 , wherein the at least one advertisement is presented to the user in a content stream, where the content stream includes one or more pieces of content associated with the user profile.
16. A non-transitory machine readable medium having information recorded thereon for providing content, wherein the information, when read by a machine, causes the machine to perform the steps of:
obtaining a user profile characterizing a user, with respect to a first feature space;
obtaining information about one or more advertisement audience segments, each of which is associated with at least one advertisement and one or more keywords representing commercial interests associated with the advertisement audience segment;
retrieving one or more pieces of content with respect to each of the one or more advertisement audience segments based, at least in part, on the one or more keywords representing the commercial interests associated with the advertisement audience segment, wherein the one or more pieces of content have information consistent with the commercial interests associated with the advertisement audience segment;
generating, for each of the one or more advertisement audience segments, an advertisement audience segment profile in a second feature space, based on the corresponding retrieved one or more pieces of content, to characterize the advertisement audience segment;
correlating the user profile with each of the advertisement audience segment profiles;
selecting one of the one or more advertisement audience segments based on degree of the correlation; and
outputting the at least one advertisement associated with the selected advertisement audience segment to the user, wherein
the first and second feature spaces correspond to the same feature space.
17. The medium of claim 16 , wherein the first feature space is a content taxonomy and the second feature space is an advertisement taxonomy.
18. The medium of claim 16 , further comprising:
selecting one of the at least one advertisement for outputting based on at least one of:
click through rate of each of the at least one advertisement;
revenue associated with each of the at least one advertisement; and
quality of each of the at least one advertisement.
19. The medium of claim 16 , wherein the at least one advertisement is presented to the user in a content stream, where the content stream includes one or more pieces of content associated with the user profile.