Method of determining a likely geographical location

• US 20050060430A1
• Filed: 10/07/2003
• Published: 03/17/2005
• Est. Priority Date: 08/13/2003
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Whereonearth Ltd. (Apollo Global Management, Inc.)
• Inventors: Patel, Devesh, Riise, Soren
• Granted Patent: US 8,280,624 B2
• Time in Patent Office: Days
• US Class Current: 709/245
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

A method of determining a likely geographical location for which a user of a computer desires further information based on submitted criteria comprising the steps of: the user submitting criteria including a locality name; identifying from the criteria the locality name; returning, in dependence on the locality name, a probability that the locality name is associated with a geographical location.

Claims

1. A method of determining a likely geographical location for which a user of a computer desires further information based on submitted criteria comprising the steps of:

the user submitting criteria including a locality name;

identifying from the criteria the locality name;

returning, in dependence on the locality name, a probability that the locality name is associated with a geographical location.

2. A method according to claim 1, wherein the locality name returns a probability of the locality name being associated with each of a plurality of geographic locations.

3. A method according to claim 1, wherein the search criteria includes a plurality of locality names and the method comprises the steps of:

identifying each of the locality names and returning, in dependence on each locality name, a probability that each of the locality names is associated with a geographical location; and

combining the returned probabilities to return a probability that the plurality of location names is associated with a geographical location.

4. A method according to claim 3, wherein the locality names return a probability of the locality name being associated with each of a plurality of geographic locations.

5. A method according to claim 3, wherein the returned probability is derived from a combination of each of the probabilities returned for each of the locality names.

6. A method according to claim 1, wherein a set of probabilities are provided between a plurality of locality names and a plurality of geographic locations, there being a probability linking a locality name to one or more of the geographic locations.

7. A method according to claim 1, wherein the computer of the user is part of a network and has a network address, the network address being mapped to a geographical location, the method comprising the further step of weighting a returned probability in dependence on the mapped geographical location indicated by the network address.

8. A method according to claim 7, wherein the network is the Internet and the network address is the IP address of the computer.

9. A method according to claim 1, wherein the computer is one of the group consisting of:

a desktop PC, a portable PC, a Personal Digital Assistant (PDA), a mobile telephone and a mobile communication device.

10. A method according to claim 1, comprising the further step of making a determination as to the geographic location being sought by the user in response to the or each returned probability.

11. A method according to claim 1, wherein the probabilities linking a locality name to one or more of the geographic locations are configured in a look-up table between locality names and geographic locations.

12. A method according to claim 1, wherein the probability is returned as a vector probability.

13. A method according to claim 1, wherein the probabilities linking a locality name to one or more of the geographic locations, the locality names and the geographic locations are configured in a decision graph.

14. A method according to claim 1, wherein the probabilities linking a locality name to one or more of the geographic locations, the locality names and the geographic locations are configured in a neural network having an output layer comprising the or each returned probability.

15. A method according to claim 1, wherein the or each returned probability is open to weighting by a genetic algorithm.

16. A method of determining a likely geographical location of a network user based on criteria submitted by the user, the method comprising the steps of:

holding geographic location information mapped from a user'"'"'s computer network address;

monitoring submitted criteria including a locality name;

determining if the locality name is a sub-location within the geographic location indicated by the geographic location information mapped from a user'"'"'s network address;

refining the geographic location information mapped from a user'"'"'s network address to indicate a probability that the user is located in the sub-location.

17. A location module to determine a likely geographical location for which a user of a computer desires further information based on submitted criteria, the module comprising:

an input to receive criteria submitted by the user including a locality name;

a comparator to identify from the criteria the locality name;

a processor to return, in dependence on the locality name, a probability that the locality name is associated with a geographical location.

18. A location module to refined a likely geographical location of a network user based on criteria submitted by the user, the location module comprising:

a store to hold geographic location information mapped from a user'"'"'s computer network address; and

a processor to monitor criteria submitted by the user including a locality name and to determine if the locality name is a sub-location within the geographic location indicated by the geographic location information mapped from a user'"'"'s network address and to refined the geographic location information mapped from a user'"'"'s network address to indicate a probability that the user is located in the sub-location.