Recommending destinations of map-related requests using categorization
View Patent ↗A system anticipates one or more destinations that a user may be interested in requesting. Using parameters such as time of day, day of week, and user device location, the system categorizes users according to current user parameters. Categories, which may be predefined by the system, are organized according to similar destination types. In some embodiments, the system determines variety scores indicative of whether a user is likely to select a destination that the user has requested before or more likely to select a new destination, within a selected category. The system uses the determined categories and variety scores to select a list of destinations to suggest to the user.
1. A computer-implemented method, comprising:
determining a set of parameters associated with a user of a user device, the parameters including a timeframe for a trip;
selecting a set of trip categories, based on prior destinations of the user at a similar timeframe and further based on the determined parameters;
for each of the selected trip categories:
determining a variety score associated with the selected trip category for the user based on the determined parameters and based on information about past behavior of the user; and
generating a set of destinations to recommend to the user for the selected trip category including user-specific destinations the user has visited and general population destinations the user has not visited but that other users have visited, wherein the variety score is used to determine a portion of the set that are user-specific destinations and a portion of the set that are general population destinations; and
transmitting one or more destinations from each of the generated sets of destinations associated with the selected trip categories to the user device for presentation to the user wherein the presentation includes user-selectable graphical interface components, each component representative of a destination.
2. The computer-implemented method of claim 1 , wherein the parameters include one or more of a time of day, a day of week, and a location of a user device of the user.
3. The computer-implemented method of claim 1 , wherein selecting a set of trip categories based on the determined parameters comprises:
determining, for each category, a frequency of the category at the timeframe by determining a percentage of times that the user requested a trip to a destination associated with the category within the timeframe; and
selecting the one or more trip categories based on the frequency of the most frequently used category.
4. The computer-implemented method of claim 1 , wherein one or more of the generated destinations are selected from destinations of each selected trip category based on the frequency of the trip category at the timeframe.
5. The computer-implemented method of claim 1 , wherein the variety score for a user within a selected trip category is based on a ratio of the number of times that the user has requested a destination the user has never requested before within the selected trip category and within the current timeframe to the number of times the user has requested any destination within the selected category and within the current timeframe.
6. The computer-implemented method of claim 1 , wherein the general population destinations of users within a category include destinations of past trips that are associated with the same category as the current user, and that were requested by users other than the current user.
7. The computer-implemented method of claim 1 , wherein recommending one or more of the determined destinations to the user comprises:
transmitting one or more of the determined destinations to a user device; and
presenting one or more of the transmitted destinations to the user such that the user may select a destination without entering an address, the presentation occurring without the user interacting with an application on the user device.
8. A non-transitory computer-readable storage medium storing computer program instructions executable by one or more processors of a system to perform steps comprising:
determining a set of parameters associated with a user of a user device, the parameters including a timeframe for a trip;
selecting a set of trip categories, based on prior destinations of the user at a similar timeframe and further based on the determined parameters;
for each of the selected trip categories:
determining a variety score associated with the selected trip category for the user based on the determined parameters and based on information about past behavior of the user; and
generating a set of destinations to recommend to the user for the selected trip category including user-specific destinations the user has visited and general population destinations the user has not visited but that other users have visited, wherein the variety score is used to determine a portion of the set that are user-specific destinations and a portion of the set that are general population destinations; and
transmitting one or more destinations from each of the generated sets of destinations associated with the selected trip categories to the user device for presentation to the user wherein the presentation includes user-selectable graphical interface components, each component representative of a destination.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the parameters include one or more of a time of day, a day of week, and a location of a user device of the user.
10. The non-transitory computer-readable storage medium of claim 8 , wherein selecting a set of trip categories based on parameters comprises:
determining, for each category, a frequency of the category at the timeframe by determining a percentage of times that the user requested a trip to a destination associated with the category within the timeframe; and
selecting the one or more trip categories based on the frequency of the most frequently used category.
11. The non-transitory computer-readable storage medium of claim 8 , wherein one or more of the generated destinations are selected from destinations of each selected trip category based on the frequency of the trip category at the timeframe.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the variety score for a user within a selected trip category is based on a ratio of the number of times that the user has requested a destination the user has never requested before within the selected trip category and within the current timeframe to the number of times the user has requested any destination within the selected category and within the current timeframe.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the general population destinations of users within a category include destinations of past trips that are associated with the same category as the current user, and that were requested by users other than the current user.
14. The non-transitory computer-readable storage medium of claim 8 , wherein recommending one or more of the determined destinations to the user comprises:
transmitting one or more of the determined destinations to a user device; and
presenting one or more of the transmitted destinations to the user such that the user may select a destination without entering an address, the presentation occurring without the user interacting with an application on the user device.
15. A computer system comprising:
one or more computer processors for executing computer program instructions; and
a non-transitory computer-readable storage medium storing instructions executable by the one or more computer processors to perform steps comprising:
determining a set of parameters associated with a user of a user device, the parameters including a timeframe for a trip;
selecting a set of trip categories, based on prior destinations of the user at a similar timeframe and further based on the determined parameters;
for each of the selected trip categories:
determining a variety score associated with the selected trip category for the user based on the determined parameters and based on information about past behavior of the user; and
generating a set of destinations to recommend to the user for the selected trip category including user-specific destinations the user has visited and general population destinations the user has not visited but that other users have visited, wherein the variety score is used to determine a portion of the set that are user-specific destinations and a portion of the set that are general population destinations; and
transmitting one or more destinations from each of the generated sets of destinations associated with the selected trip categories to the user device for presentation to the user wherein the presentation includes user-selectable graphical interface components, each component representative of a destination.
16. The computer system of claim 15 , wherein the parameters include one or more of a time of day, a day of week, and a location of a user device of the user.
17. The computer system of claim 15 , wherein selecting a set of trip categories based on the determined parameters comprises:
determining, for each category, a frequency of the category at the timeframe by determining a percentage of times that the user requested a trip to a destination associated with the category within the timeframe; and
selecting the one or more trip categories based on the frequency of the most frequently used category.
18. The computer system of claim 15 , wherein one or more of the generated destinations are selected from destinations of each selected trip category based on the frequency of the trip category at the timeframe.
19. The computer system of claim 15 , wherein the variety score for a user within a selected trip category is based on a ratio of the number of times that the user has requested a destination the user has never requested before within the selected trip category and within the current timeframe to the number of times the user has requested any destination within the selected category and within the current timeframe.
20. The computer system of claim 15 , wherein recommending one or more of the determined destinations to the user comprises:
transmitting one or more of the determined destinations to a user device; and
presenting one or more of the transmitted destinations to the user such that the user may select a destination without entering an address, the presentation occurring without the user interacting with an application on the user device.