Ranking advertisements selected from one or more databases by georelevance

• US 10,565,610 B2
• Filed: 12/10/2010
• Issued: 02/18/2020
• Est. Priority Date: 12/10/2010
• Status: Active Grant

• Current Assignee: Thryv, Inc. (Mudrick Capital Management LP)
• Original Assignee: YellowPages.com LLC (Mudrick Capital Management LP)
• Inventors: Hicken, Wendell, Melick, Joshua
• Primary Examiner(s): Retta, Yehdega
• Application Number:
  US12/965,741
• Publication Number:
  US 20120150627A1
• Time in Patent Office: 3,357 Days
• Field of Search: 705 1449, 705 1454, 705 1457
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

A search request is received from a user and the user'"'"'s context is determined. A publisher is determined for the search request. Candidate advertisements are retrieved from at least one advertisement database to create an advertisement candidate pool, the retrieving based on the user context and the search request. A set of advertisements are selected from the advertisement candidate pool. A georelevance is determined for each of the set of advertisements. The set of advertisements is sorted, wherein the advertisements are sorted based on, at least in part, the georelevance of each of the set of advertisements. The sorted set of advertisements is then transmitted to the user.

Claims

1. A method comprising:

receiving over a network information from a publisher, by an advertising platform comprising a data processing system, said data processing system including a processor configured to process logic to determine user context, select and retrieve candidate advertisements and send advertisements, wherein;

the information corresponds to a search request initiated by a user at a user interface communicable with a media channel where the search request includes one or more of a search term, a location and a number of ads requested; and

the publisher is associated with provisioning of the media channel;

determining a context of the user by logging ad performance data based on user interaction data with a set of advertisements and adding ad performance data based on user interaction data to historical data records at a historical performance database, and establishing user preferences based on assessment of the historical data records;

detecting a geolocation, by a position detection device, of a user device of the user;

receiving a publisher geosensitivity level at a user interface processing at the advertiser platform and storing the publisher geosensitivity level to a publisher profile stored at an advertiser platform database;

accessing, by the data processing system, the publisher profile for the publisher and identifying the geosensitivity level, among a plurality of defined geosensitivity levels, of the publisher, wherein the geosensitivity level specifies a level of importance, among a plurality of defined levels of importance, that a location has on ranking advertisements;

selecting the candidate advertisements, by a weighted advertisement rotation algorithm processing at the data processing system where a weight is assigned the candidate advertisement based on relative spending of advertisers, and ad impressions are rotated based on the assigned weight, the selection being based at least in part on (a) the geosensitivity level of the publisher identified based on the publisher profile and based at least in part on (b) a first search category identified by the data processing system for the search request, the first search category corresponding to (i) a set of one or more topics to which the search relates and (ii) determined geolocations of businesses or services in a determined geographic area within a predetermined distance proximate to the detected geolocation of the user device of the user;

selecting the candidate advertisements based on the weighted advertisement rotation and electronically storing in a candidate advertisement database on the network, the candidate advertisements in two or more electronic storage bucket locations, where the candidate advertisement are sorted in the electronic storage bucket locations by higher and lower rankings;

selecting and retrieving from the candidate advertisement database, by a weighted advertisement rotation algorithm processing at the data processing system, candidate advertisements for one or more advertisers where the candidate advertisement database includes at least one or more of an advertisement database having subscription advertisements stored and an advertisement database having pay-per-call advertisements stored using a single API to create an advertisement candidate pool, the retrieving based on (a) the context of the user, (b) the detected geolocation of the user device and (c) the search request,

where selecting and retrieving includes one or more of,

processing one or more of filtering logic based on business rules of a publisher and scoring using a ranking function based on business value, and

where selecting and retrieving includes one or more of,

processing intermediate sorting logic using one or more of a weighted sort and a fixed sort and processing a final sorting based on geo-relevance and search request;

ranking, with a geo-relevant sorting technique of the weighted advertisement rotation algorithm, a set of the candidate advertisements according to the identified geosensitivity_level of the publisher based in part on respective distances between one or more locations, of the advertisers, corresponding to the candidate advertisements and the detected geolocation of the user device of the user; and

providing, by the advertising platform visible indicia of, one or more, top ranked advertisements from the ranked set of candidate advertisements to the user interface of a display device of the user device and displaying the visible indicia on the display with the user interface for user interaction.

2. The method of claim 1, additionally comprising:

wherein rankings for each of the set of advertisements is determined using a criterion selected based at least in part on a primary search category for the search request and an input geo accuracy of the search request.

3. The method of claim 2, wherein:

the ranking criteria comprises is a distance significance factor criterion.

4. The method of claim 3, wherein:

the distance significance factor criterion assigns each of the set of advertisements into one of a plurality of distance bands, each of the plurality of distance bands comprising a minimum distance from a geographic point and a maximum distance from a geographic point, and

the geographic point is a search center determined using the search request and the user context, and

each of the set of advertisements is assigned to a respective one of the plurality of distance bands where a distance from the geographic point associated with the respective one of the set of advertisements falls within the respective one of the plurality of distance bands, and

wherein each of the set of advertisements is sorted by the respective one of the plurality of distance bands in which the respective one of the set of advertisements falls.

5. The method of claim 4, wherein:

the set of advertisements are secondarily sorted by performance, such that advertisements falling within a respective one of the plurality of distance bands are sorted by performance with respect to one another.

6. The method of claim 4, wherein:

each of the set of advertisements is assigned into one of the plurality of distance bands using one of a set of distance factors calculated using an equation of the form;

y=mx+b

wherein

y is the distance significance factor

x is a distance from the geographic point

b is a minimum distance significance factor

m is a distance sensitivity factor

wherein each of a set of progressively increasing values of x are used to calculate a respective one of the set of distance significance factors,

wherein for each of the set of advertisements, a respective one of the plurality of distance significance factors is selected where the distance from the geographic point associated with the respective one of the set of advertisements is at least equal to the value of x associated with the respective one of the plurality of distance significance factors and less than the next greatest value of x.

7. The method of claim 2, wherein:

the ranking criteria comprises a direct match criterion.

8. The method of claim 7, wherein:

the direct match criterion assigns a georelevance to each of the set of advertisements based on how closely the respective advertisement matches the input search request.

9. The method of claim 2, wherein:

the ranking criteria comprise a distance boosting criterion.

10. The method of claim 9, wherein:

the distance boosting technique assigns each of the set of advertisements into one of a plurality of distance bands, each of the plurality of distance bands comprising a minimum distance from a geographic point and a maximum distance from a geographic point, and

the geographic point is a search center determined using the search request and the user context, and

each of the set of advertisements is assigned to a respective one of the plurality of distance bands where a distance from the geographic point associated with the respective one of the set of advertisements falls within the respective one of the plurality of distance bands, and

a distance boosting factor is assigned to each of the set of advertisements based on the respective one of the plurality of distance bands into which the respective advertisements falls,

wherein the set of advertisements is sorted using the distance boosting factors assigned to each of the set of advertisements as boosting factors.

11. The method of claim 10, wherein:

the performance of each of the set of advertisements is additionally used as boosting factors in sorting the set of advertisements.

12. The method of claim 11, wherein:

the distance boosting factor assigned to each of the set of advertisements is a distance band boosting factor relating to the respective one of the plurality of distance bands, and

the distance band boosting factor for each of the plurality of distance bands is determined using an equation of the form

y=b−

mx

wherein

y is the distance boosting factor

x is a distance from the geographic point

b is a maximum distance boosting factor

m is a distance sensitivity factor

wherein, for each of the plurality of distance bands, x is the respective minimum distance from the geographic point associated with the respective distance band.

13. The method of claim 2, further comprising selecting the set of advertisements comprises selecting the set of advertisements using weighted advertisement rotation.

14. The method of claim 13, wherein advertisements in the advertisement candidate pool are sorted into at least a first bucket and a second bucket, the first bucket having a higher advertisement selection priority than the second bucket, and the selecting further comprises selecting the set of advertisements using weighted advertisement rotation.

19. The method of claim 1, wherein the geosensitivity level further specifies a pre-selected level of importance accorded to distance for qualifying advertisements, the pre-selected level being a most important factor, a least important factor, or a factor that is neither a most important factor nor a least important factor.

21. The method of claim 1, wherein:

the closer a location associated with an advertisement of the set of candidate advertisements is to the detected geolocation of the user device of the user, the higher the advertisement is ranked in the set of candidate advertisements.

15. A non-transitory computer-readable storage medium for tangibly storing thereon computer readable instructions, the instructions causing a data processing system to perform a method, the method comprising:

receiving over a network information from a publisher, by an advertising platform comprising a data processing system, said data processing system including a processor configured to process logic to determine user context, select and retrieve candidate advertisements and send advertisements wherein;

the information corresponds to a search request initiated by a user at a user interface communicable with a media channel where the search request includes one or more of a search term, a location and a number of ads requested; and

the publisher is associated with provisioning of the media channel;

detect a geolocation, by a position detection device, of a user device of the user;

determining a context of the user by logging ad performance data based on user interaction data with a set of advertisements and adding ad performance data based on user interaction data to historical data records at a historical performance database, and establishing user preferences based on assessment of the historical data records;

receiving a publisher geosensitivity level at a user interface processing at the advertiser platform and storing the publisher geosensitivity level to a publisher profile stored at an advertiser platform database;

accessing, by the data processing system, the publisher profile for the publisher and identifying the geosensitivity level, among a plurality of defined geosensitivity levels, of the publisher, wherein the geosensitivity level specifies a level of importance, among a plurality of defined levels of importance, that a location has on ranking advertisements;

selecting the candidate advertisements, by a weighted advertisement rotation algorithm processing at the data processing system where a weight is assigned based on relative spending of advertisers and click volume and ad impressions are rotated based on assigned weight, the selection being based at least in part on (a) the geosensitivity level of the publisher identified based on the publisher profile and based at least in part on (b) a first search category identified by the data processing system for the search request, the first search category corresponding to (i) a set of one or more topics to which the search relates and (ii) determined geolocations of businesses or services in a determined geographic area within a predetermined distance proximate to the detected geolocation of the user device of the user;

selecting the candidate advertisements based on the ranking criteria selected and electronically storing in a candidate advertisement database on the network the candidate advertisements in two or more electronic storage bucket locations, where the candidate advertisement are sorted in the electronic storage bucket locations by higher and lower rankings;

selecting and retrieving from the candidate advertisement database, by a weighted advertisement rotation algorithm processing at the data processing system, candidate advertisements for one or more advertisers where the candidate advertisement database includes at least one or more of an advertisement database having subscription advertisements stored and an advertisement database having pay-per-call advertisements stored using a single API to create an advertisement candidate pool, the retrieving based on (a) the context of the user, (b) the detected geolocation of the user device and (c) the search request

where selecting and retrieving includes one or more of,

processing one or more of filtering logic based on business rules of a publisher and scoring using a ranking function based on business value, and

where selecting and retrieving includes one or more of,

processing intermediate sorting logic using one or more of a weighted sort and a fixed sort and processing a final sorting based on geo-relevance and search request;

ranking, with a geo-relevant sorting technique of the weighted advertisement rotation algorithm, a set of the candidate advertisements according to the identified geosensitivity level of the publisher based in part on respective distances between one or more locations, of the advertisers, corresponding to the candidate advertisements and the detected geolocation of the user device of the user; and

providing, by the advertising platform, visible indicia of, one or more, top ranked advertisements from the ranked set of candidate advertisements to the user interface of a display device of the user device and displaying the visible indicia on the display with the user interface for user interaction.

16. The non-transitory computer-readable storage medium of claim 15, additionally comprising:

wherein rankings for each of the set of advertisements is determined using a criterion selected based at least in part on a primary search category for the search request and an input geo accuracy of the search request.

20. The non-transitory computer-readable storage medium of claim 15, wherein the geosensitivity level further specifies a pre-selected level of importance accorded to distance for qualifying advertisements, the pre-selected level being a most important factor, a least important factor, or a factor that is neither a most important factor nor a least important factor.

22. The non-transitory computer-readable storage medium of claim 15, wherein:

the closer a location associated with an advertisement of the set of candidate advertisements is to the detected geolocation of the user device of the user, the higher the advertisement is ranked in the set of candidate advertisements.

17. A data processing system, comprising:

memory storing at least one advertisement database;

at least one processor coupled to access the memory, the at least

one processor configured to;

receive over a network information from a publisher by an advertising platform comprising a data processing system, said data processing system including a processor configured to process logic to determine user context, select and retrieve candidate advertisements and send advertisements, wherein;

the information corresponds to a search request initiated by a user at a user interface communicable with a media channel; and

the publisher is associated with provisioning of the media channel;

detect a geolocation, by a position detection device, of a user device of the user;

determine a context of the user by logging ad performance data based on user interaction data with a set of advertisements and adding ad performance data based on user interaction data to historical data records at a historical performance database, and establishing user preferences based on assessment of the historical data records;

receive a publisher geosensitivity level at a user interface processing at the advertiser platform and storing the publisher geosensitivity level to a publisher profile stored at an advertiser platform database;

access the publisher profile for the publisher and identifying the geosensitivity level, among a plurality of defined geosensitivity levels, of the publisher, wherein the geosensitivity level specifies a level of importance, among a plurality of defined levels of importance, that a location has on ranking advertisements

select the candidate advertisements, by a weighted advertisement rotation algorithm processing at the data processing system where a weight is assigned based on relative spending of advertisers and ad impressions are rotated based on assigned weight, the selection being based at least in part on (a) the geosensitivity level of the publisher identified based on the publisher profile and based at least in part on (b) a first search category identified by the data processing system for the search request, the first search category corresponding to (i) a set of one or more topics to which the search relates and (ii) determined geolocations of businesses or services in a determined geographic area within a predetermined distance proximate to the detected geolocation of the user device of the user;

select the candidate advertisements based on the ranking criteria selected and electronically storing in a candidate advertisement database on the network the candidate advertisements in two or more electronic storage bucket locations, where the candidate advertisement are sorted in the electronic storage bucket locations by higher and lower rankings;

select and retrieve from the candidate advertisement datatbase, by a weighted advertisement rotation algorithm processing at the data processing system, candidate advertisements where the candidate advertisement database includes at least one or more of an advertisement database having subscription advertisements stored and an advertisement database having pay-per-call advertisements stored using a single API to create an advertisement candidate pool, the retrieving based on (a) the context of the user, (b) the detected geolocation of the user device and (c) the search request,

where selecting and retrieving includes one or more of, processing one or more of filtering logic based on business rules of a publisher and scoring using a ranking function based on business value, and

where selecting and retrieving includes one or more of, processing intermediate sorting logic using one or more of a weighted sort and a fixed sort and processing a final sorting based on geo-relevance and search request;

rank, with a geo-relevant sorting technique of the weighted advertisement rotation algorithm, a set of the candidate advertisements according to the identified geo-sensitivity level of the publisher based in part on respective distances between one or more locations, of the advertisers, corresponding to the candidate advertisements and the detected geolocation of the user device of the user; and

provide, by the advertising platform, visible indicia of, one or more, top ranked advertisements from the ranked set of candidate advertisements to the user interface of a display device and displaying the visible indicia on the display with the user interface of the user device for user interaction.

18. The data processing system of claim 17, wherein the at least one processor is additionally configured to perform operations further comprising:

wherein rankings for each of the set of advertisements is determined using a criterion selected based at least in part on a primary search category for the search request and an input geo accuracy of the search request.

23. The data processing system of 17, wherein:

the closer a location associated with an advertisement of the set of candidate advertisements is to the detected geolocation of the user device of the user, the higher the advertisement is ranked in the set of candidate advertisements.