METHOD AND APPARATUS FOR THE RETRIEVAL OF SIMILAR PLACES

• US 20110109435A1
• Filed: 11/12/2009
• Published: 05/12/2011
• Est. Priority Date: 11/12/2009
• Status: Active Grant

• Current Assignee: HERE Global B.V. (HERE Holding Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Waldaukat, Mark, Bickel, Steffen, Siemen, Peter, Kruppa, Hannes
• Granted Patent: US 10,001,384 B2
• Time in Patent Office: Days
• US Class Current: 340/8.1
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04W 4/02 Services making use of location information

Abstract

An approach is provided for determining the similarity between a reference point-of-interest and similarity candidate points-of-interest. Data specifying a reference point-of-interest and location data of a search region are received. A reference vector specifying a plurality of features associated with the reference point-of-interest is retrieved. A plurality of candidates for similar points-of-interest are determined based, at least in part, on the search region. A similarity score is determined for each of the candidates. A list of one or more similar points-of-interest is generated based on the similarity scores.

Claims

1. A method comprising:

receiving data specifying a reference point-of-interest and location data of a search region;

retrieving a reference vector specifying a plurality of features associated with the reference point-of-interest;

determining a plurality of candidates for similar points-of-interest based, at least in part, on the search region;

determining a similarity score for each of the candidates; and

generating a list of one or more similar points-of-interest based on the similarity scores.

2. A method of claim 1, further comprising:

retrieving a candidate feature vector, for each of the candidates, specifying a plurality of features respectively associated with the candidates, wherein the determining the similarity scores is further based on the respective candidate feature vectors.

3. A method of claim 2, further comprising:

retrieving a weighting vector associated with the reference point-of-interest, wherein the determining the similarity scores comprises computing the inner vector product of the weighting vector, the reference vector, and the respective candidate feature vectors.

4. A method of claim 3, further comprising:

receiving user data specifying points-of-interest considered similar from a user equipment;

retrieving feature vectors respectively associated with the specified points-of-interest; and

modifying the weighting vector based on the feature vectors of the respective specified points-of-interest.

5. A method of claim 1, further comprising:

selecting one of the candidates for presentation based on the similarity scores, wherein the one candidate is associated with candidate data describing the candidate; and

causing, at least in part, actions leading to the presentation of the candidate data.

6. A method of claim 1, wherein the features comprise classification features, tag features, price features, ratings features, text-based description features, or a combination thereof.

7. A method of claim 1, wherein the data is received from a user equipment and the search region is determined based on a location of the user equipment.

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,

receive data specifying a reference point-of-interest and location data of a search region;

retrieve a reference vector specifying a plurality of features associated with the reference point-of-interest;

determine a plurality of candidates for similar points-of-interest based, at least in part, on the search region;

determine a similarity score for each of the candidates; and

generate a list of one or more similar points-of-interest based on the similarity scores.

9. An apparatus of claim 8, wherein the apparatus is further caused, at least in part, to:

retrieve a candidate feature vector, for each of the candidates, specifying a plurality of features respectively associated with the candidates, wherein the determining the similarity scores is further based on the respective candidate feature vectors.

10. An apparatus of claim 9, wherein the apparatus is further caused, at least in part, to:

retrieve a weighting vector associated with the reference point-of-interest, wherein the determining the similarity scores comprises computing the inner vector product of the weighting vector, the reference vector, and the respective candidate feature vectors.

11. An apparatus of claim 10, wherein the apparatus is further caused, at least in part, to:

receive user data specifying points-of-interest considered similar from a user equipment;

retrieve feature vectors respectively associated with the specified points-of-interest; and

modify the weighting vector based on the feature vectors of the respective specified points-of-interest.

12. An apparatus of claim 8, wherein the apparatus is further caused, at least in part, to:

select one of the candidates for presentation based on the similarity scores, wherein the one candidate is associated with candidate data describing the candidate; and

cause, at least in part, actions leading to the presentation of the candidate data.

13. An apparatus of claim 8, wherein the features comprise classification features, tag features, price features, ratings features, text-based description features, or a combination thereof.

14. An apparatus of claim 8, wherein the data is received from a user equipment and the search region is determined based on a location of the user equipment.

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:

receiving data specifying a reference point-of-interest and location data of a search region;

retrieving a reference vector specifying a plurality of features associated with the reference point-of-interest;

determining a plurality of candidates for similar points-of-interest based, at least in part, on the search region;

determining a similarity score for each of the candidates; and

generating a list of one or more similar points-of-interest based on the similarity scores.

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

retrieving a candidate feature vector, for each of the candidates, specifying a plurality of features respectively associated with the candidates, wherein the determining the similarity scores is further based on the respective candidate feature vectors.

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

retrieving a weighting vector associated with the reference point-of-interest, wherein the determining the similarity scores comprises computing the inner vector product of the weighting vector, the reference vector, and the respective candidate feature vectors.

18. A computer-readable storage medium of claim 17, wherein the apparatus is caused, at least in part, to further perform:

receiving user data specifying points-of-interest considered similar from a user equipment;

retrieving feature vectors respectively associated with the specified points-of-interest; and

modifying the weighting vector based on the feature vectors of the respective specified points-of-interest.

19. A computer-readable storage medium of claim 15, wherein the apparatus is caused, at least in part, to further perform:

selecting one of the candidates for presentation based on the similarity scores, wherein the one candidate is associated with candidate data describing the candidate; and

causing, at least in part, actions leading to the presentation of the candidate data.

20. A computer-readable storage medium of claim 15, wherein the features comprise classification features, tag features, price features, ratings features, text-based description features, or a combination thereof.