Systems, computer-implemented methods, and computer-readable media to target internet-based services on a geographic location

• US 9,143,541 B1
• Filed: 11/16/2012
• Issued: 09/22/2015
• Est. Priority Date: 11/17/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Szamonek, Zoltan, Duleba, Krzysztof
• Primary Examiner(s): Louie, Oscar
• Assistant Examiner(s): Ton, Da T
• Application Number:
  US13/679,590
• Time in Patent Office: 1,040 Days
• Field of Search: 709/204, 709220-228, 709/238, 709/245, 707 3- 5, 707/722, 707/723, 707/754, 707/768, 707/830
• US Class Current: 1/1
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

Systems, computer-implemented methods, and computer-readable media are provided to target internet-based services on a geographic location relating to a plurality of candidate geographic locations. A targeted geographic location may be provided based on usefulness, to a user probabilistically located among the plurality of candidates, of internet-based services being targeted thereon. From a first server, a plurality of candidate geographic locations may be obtained, each of which may be associated with a client IP address and a plurality of candidate confidence levels. A plurality of route-utility factors for each respective candidate geographic location, a plurality of probabilistic utility scores for each respective candidate geographic location, and an aggregate probabilistic utility score may be determined for each candidate geographic location. Further, a geographic location having an aggregate probabilistic utility score satisfying preselected criteria may be selected and transmitted to a second server so that geographically-targeted internet-based services can be provided.

Claims

1. A method to provide internet-based services targeted to a geographic location, the method comprising:

receiving a request from a user to provide internet-based services based on a target geographic location;

obtaining a plurality of candidate geographic locations associated with the user, each candidate geographic location being associated with a respective candidate confidence level;

calculating, with a computer, for one of the candidate geographic locations, a respective aggregate probabilistic utility score, the aggregate probabilistic utility score being based, at least in part, on distances from the respective candidate geographic location to the other candidate geographic locations and the confidence level scores of the other candidate geographic locations;

selecting a geographic location based, at least in part, on the aggregate probabilistic utility score from among the candidate geographic locations; and

providing internet-based services to the user targeting the selected geographic location.

2. The method of claim 1, wherein calculating an aggregate probabilistic utility score further comprises:

obtaining a route-utility factor indicative of the burden of traveling from the respective candidate geographic location to one of the other candidate geographic locations; and

calculating the aggregate probabilistic utility score based on the route-utility factor.

3. The method of claim 2, wherein the route-utility factor is based, at least in part, on a driving distance between the respective candidate geographic location to the one of the other candidate geographic locations.

4. The method of claim 2, wherein the route-utility factor is based, at least in part, on an estimated driving time between the respective candidate geographic location to the one of the other candidate geographic locations.

5. The method of claim 1, wherein calculating an aggregate probabilistic utility score further comprises:

obtaining utility scores for each of the other candidate geographic locations, the utility scores being uniquely associated with the respective candidate geographic location; and

calculating the aggregate probabilistic utility score based, at least in part, on the utility scores.

6. The method of claim 5, wherein the utility scores for each of the other candidate geographic locations decrease exponentially as a function of the distance from the respective candidate geographic location.

7. The method of claim 5, wherein calculating the aggregate probabilistic utility score based, at least in part, on the utility scores further comprises:

combining the candidate confidence level for the respective candidate geographic location with the utility scores.

8. The method of claim 5, wherein calculating the aggregate probabilistic utility score based, at least in part, on the utility scores further comprises:

for each of the other candidate geographic locations, weighting the utility scores with the candidate confidence level of that candidate geographic location; and

summing the weighted the utility scores and the candidate confidence level of the respective candidate geographic location.

9. The method of claim 1, wherein the aggregate probabilistic utility score A for the respective candidate geographic location d is calculated according to the equation:

10. The method of claim 1, further comprising:

calculating an aggregate probabilistic utility score for each of the candidate geographic locations, and

wherein providing internet-based services to the user further comprises ranking web resources in accordance with the aggregate probabilistic utility score by;

selecting the candidate geographic location with the highest aggregate probabilistic utility score as a targeted geographic location; and

responsive to the selection, ranking web resources associated with the targeted geographic location higher than the associated web resources would ranked absent the selection.

11. The method of claim 1, further comprising:

calculating an aggregate probabilistic utility score for each of the candidate geographic locations, and

wherein providing internet-based services to the user further comprises ranking web resources in accordance with the aggregate probabilistic utility score by;

selecting as targeted geographic locations candidate geographic locations with aggregate probabilistic utility scores exceeding a threshold; and

responsive to the selection, ranking web resources associated with the targeted geographic locations higher than the associated web resources would ranked absent the selection.

12. The method of claim 1, wherein calculating an aggregate probabilistic utility score further comprises:

obtaining a trip-utility factor indicative of utility of a trip to one of the other candidate geographic locations to the user irrespective of distance; and

calculating the aggregate probabilistic utility score based on the trip-utility factor.

13. The method of claim 1, wherein calculating an aggregate probabilistic utility score further comprises:

obtaining a destination-utility factor indicative of utility of one of the other candidate geographic locations to the user irrespective of distance; and

calculating the aggregate probabilistic utility score based on the trip-utility factor.

14. The method of claim 13, wherein the destination-utility factor is determined based on user preferences.

15. The method of claim 1, wherein:

receiving a request to select a target geographic location to provide internet-based services to a user comprises receiving a text search query from the user; and

calculating for one of the candidate geographic locations, a respective aggregate probabilistic utility score further comprises selecting a utility-decay rate based on text of the text search query, the utility-decay rate indicating the rate at which a utility score for a candidate geographic location decays as a function of distance.

16. The method of claim 1, further comprising:

identifying an interstitial geographic location between candidate geographic locations; and

wherein the aggregate probabilistic utility score is based, at least in part, on distances to the interstitial geographic location.

17. The method of claim 1, wherein:

each of the plurality of candidate confidence levels express a relative probability that a corresponding candidate geographic location includes a positional location of a client device associated with the user;

obtaining a plurality of candidate geographic locations associated with the user further comprises;

obtaining an IP address from the client device of the user; and

querying a geolocation repository with the IP address to obtain candidate geographic locations and associated confidence levels;

the candidate geographic locations include cities;

receiving a request from a user to provide internet-based services comprises receiving a text search query; and

providing internet-based services to the user further comprises ranking web pages geocoded to the cities according to the aggregate probabilistic utility score and relevance of the web page to the text search query.

18. The method of claim 1, wherein providing internet-based services to the user further comprises:

selecting an advertisement to present to the use based, at least in part, on the aggregate probabilistic utility score; and

presenting the selected advertisement to the user.

19. A system to provide internet-based services targeted on a targeted geographic location, the system comprising:

one or more processors; and

non-transitory computer-readable storage medium having stored thereon a set of executable instructions that, when executed by the one or more processors, causes the system to perform the following operations comprising;

receiving a request from a user to provide internet-based services based on a target geographic location;

obtaining a plurality of candidate geographic locations associated with the user, each candidate geographic location being associated with a respective candidate confidence level;

calculating, with a computer, for one of the candidate geographic locations, a respective aggregate probabilistic utility score, the aggregate probabilistic utility score being based, at least in part, on distances from the respective candidate geographic location to the other candidate geographic locations and the confidence level scores of the other candidate geographic locations;

selecting a geographic location based, at least in part, on the aggregate probabilistic utility score from among the candidate geographic locations; and

providing internet-based services to the user targeting the selected geographic location.

20. A tangible, non-transitory, machine-readable medium storing instructions that when executed by a computer system, cause the computer system to perform operations comprising:

receiving a request from a user to provide internet-based services based on a target geographic location;

obtaining a plurality of candidate geographic locations associated with the user, each candidate geographic location being associated with a respective candidate confidence level;

calculating, with a computer, for one of the candidate geographic locations, a respective aggregate probabilistic utility score, the aggregate probabilistic utility score being based, at least in part, on distances from the respective candidate geographic location to the other candidate geographic locations and the confidence level scores of the other candidate geographic locations;

selecting a geographic location based, at least in part, on the aggregate probabilistic utility score from among the candidate geographic locations; and

providing internet-based services to the user targeting the selected geographic location.