Method for analyzing and ranking venues
A technique is disclosed for ranking venues and for providing a user with one or more of the ranked venues. To do so, a data processing system trains a model during a first, training sequence, by using a training dataset of past check-ins that were made by users visiting venues. The trained model, representing a learned hypothesis, represents venues that are ranked according to their relevance to users who are also represented by the model. During a second, run-time sequence, the system receives real-time geolocation data that represents users and generates a set of candidate venues for a user by determining venues that are nearby the geolocation of the user. The system then ranks the generated candidate venues by applying the learned hypothesis. One or more of the ranked venues can be provided to a user's wireless terminal, for example, where they can be presented as venue recommendations.
1. A method comprising:
collecting, by a data-processing system, a geolocation, detected by a positioning device, of a user terminal of a first user;
receiving, by the data-processing system, a calendrical time identifier comprising indicia indicating an instance in which the first user was at the detected geolocation;
generating, by the data-processing system, a non-empty set of candidate venues based at least in part on the detected geolocation of the first user and the calendrical time identifier in response to the data-processing system determining that the candidate venues are within a predetermined distance of the detected geolocation of the first user;
determining a set of venue categories based at least in part on the calendrical time identifier, wherein the calendrical time identifier indicates a time of day;
including in the non-empty set of candidate venues and/or excluding from the non-empty set of candidate venues, one or more candidate venues based at least in part on the determined set of venue categories so that the non-empty set of candidate venues are determined by the data-processing system based in part on the time of day and the indicia indicating the instance in which the first user was at the detected geolocation indicated by the calendrical time identifier;
ranking the candidate venues, by the data-processing system, based on applying, to the candidate venues, a hypothesis that is learned from locations, detected by the positioning device, of one or more venues visited by at least one of i) the first user and ii) one or more additional users, wherein the hypothesis incorporates a rule of preferring a visited venue to a non-visited venue;
providing, by the data-processing system, visible indicia denoting one or more of the ranked candidate venues to a display device of the user terminal; and
generating, by the data-processing system, an electronic map indicating a detected current geolocation of the user terminal of the first user in relation to a detected location of a highest ranked venue, denoted as a recommended venue to the first user, of the ranked candidate venues and providing the generated electronic map to the display device for display of the electronic map by the user terminal, the recommended venue is determined to be a venue previously visited by one of the one or more additional users, but which was not previously visited by the first user.
2. The method of claim 1 wherein an upper bound is applied to the rank of a matrix that represents the hypothesis.
3. The method of claim 1 , wherein the ranking is also based on the calendrical time identifier.
4. The method of claim 1 further comprising receiving, by the data-processing system, an indication of commercial exposure of the first user, wherein the ranking is also based on the commercial exposure.
5. The method of claim 1 , wherein the ranking is performed in a manner that excludes all venues visited by the first user and the rule is applied to venues visited by the one or more additional users.
6. The method of claim 1 , wherein the predetermined distance comprises a predefined radius of an area of proximity around the geolocation of the first user.
7. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion configured to collect a geolocation, detected by a positioning device, of a user terminal of a first user;
an executable portion configured to receive a calendrical time identifier comprising indicia indicating an instance in which the first user was at the detected geolocation;
an executable portion configured to generate a non-empty set of candidate venues based at least in part on the detected geolocation of the first user and the calendrical time identifier in response to determining that the candidate venues are within a predetermined distance of the detected geolocation of the first user;
an executable portion configure to determine a set of venue categories based at least in part on the calendrical time identifier, wherein the calendrical time identifier indicates a time of day;
an executable portion configured to include in the non-empty set of candidate venues and/or exclude from the non-empty set of candidate venues, one or more candidate venues based at least in part on the determined set of venue categories so that the non-empty set of candidate venues are determined based in part on the time of day and the indicia indicating the instance in which the first user was at the detected geolocation indicated by the calendrical time identifier;
an executable portion configured to rank the candidate venues based on the received calendrical time identifier and on applying, to the candidate venues, a hypothesis that is learned from locations, detected by the positioning device, of one or more venues visited by at least one of i) the first user and ii) one or more additional users;
an executable portion configured to provide visible indicia denoting one or more of the ranked candidate venues to a display device of the user terminal; and
an executable portion configured to generate an electronic map indicating a detected current geolocation of the user terminal of the first user in relation to a detected location of a highest ranked venue, denoted as a recommended venue to the first user, of the ranked candidate venues and provide the generated electronic map to the display device for display of the electronic map by the user terminal, the recommended venue is determined to be a venue previously visited by one of the one or more additional users, but which was not previously visited by the first user.
8. The computer program product of claim 7 wherein an upper bound is applied to the rank of a matrix that represents the hypothesis.
9. The computer program product of claim 7 further comprising:
an executable portion configured to receive an indication of commercial exposure of the first user, wherein the ranking is also based on the commercial exposure.
10. The computer program product of claim 9 wherein the indication identifies a commercial category.
11. The computer program product of claim 7 , wherein the ranking is performed to exclude all venues visited by the first user and the hypothesis is learned from the locations of the one or more venues visited by the one or more additional users.
12. The computer program product of claim 7 , wherein the hypothesis incorporates a rule of preferring a visited venue to a non-visited venue.
13. 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 processor, cause the apparatus to at least:
collect a geolocation, detected by a positioning device, of a user terminal of a first user;
receive a calendrical time identifier comprising indicia indicating an instance in which the first user was at the detected geolocation;
generate a non-empty set of candidate venues based at least in part on the detected geolocation of the first user and the calendrical time identifier in response to determining that the candidate venues are within a predetermined distance of the detected geolocation of the first user;
determine a set of venue categories based at least in part on the calendrical time identifier, wherein the calendrical time identifier indicates a time of day;
include in the non-empty set of candidate venues and/or exclude from the non-empty set of candidate venues, one or more candidate venues based at least in part on the determined set of venue categories so that the non-empty set of candidate venues are determined based in part on the time of day and the indicia indicating the instance in which the first user was at the detected geolocation indicated by the calendrical time identifier;
rank the candidate venues based on applying, to the candidate venues, a hypothesis that is learned from locations, detected by the positioning device, of one or more venues visited by at least one of i) the first user and ii) one or more additional users;
provide visible indicia denoting one or more of the ranked candidate venues to a display device of the user terminal; and
generate an electronic map indicating a detected current geolocation of the user terminal of the first user in relation to a detected location of a highest ranked venue, denoted as a recommended venue to the first user, of the ranked candidate venues and provide the generated electronic map to the display device for display of the electronic map by the user terminal, the recommended venue is determined to be a venue previously visited by one of the one or more additional users, but which was not previously visited by the first user.
14. The apparatus of claim 13 , wherein the ranking is also based on the calendrical time identifier.
15. The apparatus of claim 13 , wherein the computer program code are further configured to, with the processor, cause the apparatus to:
receive an indication of commercial exposure of the first user, wherein the ranking is also based on the commercial exposure.
16. The apparatus of claim 13 , wherein the memory and computer program code are further configured to, with the processor, cause the apparatus to:
perform the ranking to exclude all venues visited by the first user and the hypothesis is learned from the locations of the one or more venues visited by the one or more additional users.
17. The apparatus of claim 13 , wherein the hypothesis incorporates a rule of preferring a visited venue to a non-visited venue.