Location search using dynamic regions generated based on service data
View Patent ↗Systems and methods for improving a location search process are provided. A networked system accesses trip data associated with the POI. The networked system receives an indication of a search being performed at a user device and detects a location of the user device. The networked system accesses an index in a data storage. From the index, the networked system determines a region identifier that corresponds to the location of the user device, the region identifier identifying a dynamically generated region in which to perform the search. Based on a search term, the networked system performs the search in the dynamically generated region corresponding to the region identifier. The networked system then causes presentation of a result of the search on the user device.
1. A system comprising:
one or more hardware processors; and
a memory storing instructions that, when executed by the one or more hardware processors, causes the one or more hardware processors to perform operations comprising:
receiving an indication of a search being performed at a user device;
detecting a location of the user device;
accessing an index in a data storage;
determining, from the index, a region identifier that corresponds to the location of the user device, the region identifier identifying a dynamically generated region in which to perform the search;
based on a search term, performing the search in the dynamically generated region corresponding to the region identifier; and
causing presentation of a result of the search on the user device.
2. The system of claim 1 , wherein the operations further comprise generating the dynamically generated region, the generating comprising:
accessing trip data;
for a particular locale, generating a plurality of location clusters, each location cluster representing an area to which a threshold number of users traveled from the particular locale; and
grouping the plurality of location clusters to form the dynamically generated region for the particular locale.
3. The system of claim 2 , wherein the generating the cluster comprises using the K-means clustering algorithm.
4. The system of claim 2 , wherein the generating the cluster comprise using the density-based spatial clustering of applications with noise (DBSCAN) algorithm.
5. The system of claim 1 , wherein the operations further comprise generating the dynamically generated region, the generating comprising:
accessing trip data;
for a particular locale, determining a number of trips from the particular locale to each of a plurality of previously classified areas;
ranking the plurality of previously classified areas based on the number of trips from the particular locale;
selecting a top number of previously classified areas based on the ranking; and
grouping the top number of previously classified areas to form the dynamically generated region for the particular locale.
6. The system of claim 5 , wherein the plurality of previously classified areas is classified based on a zip code, congressional district, neighborhood, city, or county.
7. The system of claim 1 , wherein the operations further comprise generating the index, the generating the index comprising indexing each point of interest (POI) or address in the data storage with a region identifier that corresponds to a region for a particular locale that the POI or address is located within.
8. The system of claim 1 , wherein:
the search term comprises a portion of a name of a point of interest (POI) or a portion of an address; and
the causing presentation of the result comprises presenting the result as suggestions for completing the name of the POI or the address.
9. The system of claim 1 , wherein:
the search term comprises a selection of a category; and
the causing presentation of the result comprises presenting the result as suggestions for a point of interest (POI).
10. A method comprising:
receiving an indication of a search being performed at a user device;
detecting a location of the user device;
accessing an index in a data storage;
determining, from the index, a region identifier that corresponds to the location of the user device, the region identifier identifying a dynamically generated region in which to perform the search;
based on a search term, performing, by one or more hardware processors, the search in the dynamically generated region corresponding to the region identifier; and
causing presentation of a result of the search on the user device.
11. The method of claim 10 , further comprising generating the dynamically generated region, the generating comprising:
accessing trip data;
for a particular locale, generating a plurality of location clusters, each location cluster representing an area to which a threshold number of users traveled from the particular locale; and
grouping the plurality of location clusters to form the dynamically generated region for the particular locale.
12. The method of claim 11 , wherein the generating the cluster comprises using the K-means clustering algorithm.
13. The method of claim 11 , wherein the generating the cluster comprise using the density-based spatial clustering of applications with noise (DBSCAN) algorithm.
14. The method of claim 10 , further comprising generating the dynamically generated region, the generating comprising:
accessing trip data;
for a particular locale, determining a number of trips from the particular locale to each of a plurality of previously classified areas;
ranking the plurality of previously classified areas based on the number of trips from the particular locale;
selecting a top number of previously classified areas based on the ranking; and
grouping the top number of previously classified areas to form the dynamically generated region for the particular locale.
15. The method of claim 14 , wherein the plurality of previously classified areas is classified based on a zip code, congressional district, neighborhood, city, or county.
16. The method of claim 10 , further comprising generating the index, the generating the index comprising indexing each point of interest (POI) or address in the data storage with a region identifier that corresponds to a region for a particular locale that the POI or address is located within.
17. The method of claim 10 , wherein:
the search term comprises a portion of a name of a point of interest (POI) or a portion of an address; and
the causing presentation of the result comprises presenting the result as suggestions for completing the name of the POI or the address.
18. The method of claim 10 , wherein:
the search term comprises a selection of a category; and
the causing presentation of the result comprises presenting the result as suggestions for a point of interest (POI).
19. A non-transitory machine-storage medium storing instructions that, when executed by one or more processors of a machine, cause the one or more processors to perform operations comprising: receiving an indication of a search being performed at a user device; detecting a location of the user device; accessing an index in a data storage; determining, from the index, a region identifier that corresponds to the location of the user device, the region identifier identifying a dynamically generated region in which to perform the search; based on a search term, performing the search in the dynamically generated region corresponding to the region identifier; and causing presentation of a result of the search on the user device.
20. A non-transitory machine-storage medium of claim 19 , wherein the operations further comprise: generating the dynamically generated region; and generating the index, the generating the index comprising indexing each point of interest (POI) or address in the data storage with a region identifier that corresponds to a region for a particular locale that the POI or address is located within.