Location based ranking of real world locations
View Patent ↗An online booking system allows users to creates, search, and book listings of goods or services. When a user searches for listings, the listings are ranked at least in part based on a location relevance score including at least one of a city relevance subscore, a neighborhood subscore, and a distance subscore. Generally, the city relevance subscore quantifies the probability that a searching user may have actually intended to look for listings in a city other than the city specified in a search query. Generally, the neighborhood relevance subscore quantifies the popularity of specific neighborhoods within a city as a replacement or addition to the distance subscore that determines a real world distance between a listing's real world location and a location specified in a search query.
1. A computer-implemented method for operating a computer-implemented location search engine, the computer-implemented method comprising:
receiving a search query from a user interface presented at a client device associated with a user, the search query including a query city, the user interface corresponding to an input interface of the computer implemented location search engine;
accessing, by one or more processors operating the computer-implemented location search engine, a plurality of candidate listings available for booking by the user, each of the candidate listings located in one of a plurality of listing cities, at least one of the listing cities being different from the query city;
accessing, by the one or more processors operating the computer-implemented location search engine, a plurality of historical bookings in the plurality of listing cities;
determining, by the one or more processors operating the computer-implemented location search engine, a city relevance score for each of the candidate listings, the city relevance score for a listing being determined based on the plurality of historical bookings, the city relevance score indicating a probability that the user will book a listing in the listing city given (i) the query city included in the search query and (ii) the historical bookings in the listing city;
determining, by the one or more processors operating the computer-implemented location search engine, a ranked order for the candidate listings based at least in part on the city relevance score;
generating, by the one or more processors operating the computer-implemented location search engine, one or more listings according to the ranked order, the one or more listings being outputs of the computer implemented location search engine; and
providing the one or more listings for display at the user interface presented at the client device associated with the user, the provided listings comprises at least one candidate listing that is located in a city different from the query city.
2. The computer-implemented method of claim 1 , wherein the city relevance score for one of the candidate listings whose listing city is different from the query city is determined based on a subset of the plurality of historical bookings, the subset including historical bookings in the listing city of the one of the candidate listings that were initiated from historical queries that specified the query city.
3. The computer-implemented method of claim 2 , further comprising:
adjusting, by the one or more processors operating the computer-implemented location search engine, the city relevance score for the one of the candidate listings based on a second subset of the plurality of historical bookings, the second subset including historical bookings in the listing city of the one of the candidate listings that were initiated from historical queries that specified the listing city of the one of the candidate listings.
4. The computer-implemented method of claim 1 , wherein the city relevance score for one of the candidate listings is determined further based on a number of candidate listings in the listing city of the one of the candidate listings.
5. The computer-implemented method of claim 1 , wherein the city relevance score for one of the candidate listings is determined further based on a number of candidate listings in the listing city of the one of the candidate listings and a total number of candidate listings.
6. The computer-implemented method of claim 1 , wherein the ranked order is further based on distance relevance scores for the plurality of the candidate listings, each of the candidate listings having a distance relevance score.
7. The computer-implemented method of claim 6 , wherein the distance relevance score of one of the plurality of the candidate listings is determined based on a distance between the query city and a location of the one of the plurality of the candidate listings.
8. The computer-implemented method of claim 6 , wherein the distance relevance score of one of the plurality of the candidate listings is determined based on a non-linear function of distance.
9. The computer-implemented method of claim 1 , wherein the ranked order is further based on neighborhood relevance scores for neighborhoods in the query city, each of the neighborhoods having a neighborhood relevance score that is determined based on historical bookings of the neighborhood that were initiated from historical queries that specified the query city.
10. The computer-implemented method of claim 9 , wherein the ranked order concerning candidate listings of the plurality of candidate listings that are not located in the query city are not adjusted by the neighborhood relevance scores.
11. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause a computer-implemented location search engine to perform operations, the instructions comprising instructions to:
receive a search query from a user interface presented at a client device associated with a user, the search query including a query city, the user interface corresponding to an input interface of the computer implemented location search engine;
access a plurality of candidate listings available for booking by the user, each of the candidate listings located in one of a plurality of listing cities, at least one of the listing cities being different from the query city;
access a plurality of historical bookings in the plurality of listing cities;
determine a city relevance score for each of the candidate listings, the city relevance score for a listing being determined based on the plurality of historical bookings, the city relevance score indicating a probability that the user will book a listing in the listing city given (i) the query city included in the search query and (ii) the historical bookings in the listing city;
determine a ranked order for the candidate listings based at least in part on the city relevance score;
generate one or more listings according to the ranked order, the one or more listings being outputs of the computer implemented location search engine; and
provide the one or more listings for display at the user interface presented at the client device associated with the user, the provided listings comprises at least one candidate listing that is located in a city different from the query city.
12. The non-transitory computer readable storage medium of claim 11 , wherein the city relevance score for one of the candidate listings whose listing city is different from the query city is determined based on a subset of the plurality of historical bookings, the subset including historical bookings in the listing city of the one of the candidate listings that were initiated from historical queries that specified the query city.
13. The non-transitory computer readable storage medium of claim 12 , wherein the instructions further cause the one or more processors to:
adjust the city relevance score for the one of the candidate listings based on a second subset of the plurality of historical bookings, the second subset including historical bookings in the listing city of the one of the candidate listings that were initiated from historical queries that specified the listing city of the one of the candidate listings.
14. The non-transitory computer readable storage medium of claim 11 , wherein the city relevance score for one of the candidate listings is determined further based on a number of candidate listings in the listing city of the one of the candidate listings.
15. The non-transitory computer readable storage medium of claim 11 , wherein the city relevance score for one of the candidate listings is determined further based on a number of candidate listings in the listing city of the one of the candidate listings and a total number of candidate listings.
16. The non-transitory computer readable storage medium of claim 11 , wherein the ranked order is further based on distance relevance scores for the plurality of the candidate listings, each of the candidate listings having a distance relevance score.
17. The non-transitory computer readable storage medium of claim 16 , wherein the distance relevance score of one of the plurality of the candidate listings is determined based on a distance between the query city and a location of the one of the plurality of the candidate listings.
18. The non-transitory computer readable storage medium of claim 16 , wherein the distance relevance score of one of the plurality of the candidate listings is determined based on a non-linear function of distance.
19. The non-transitory computer readable storage medium of claim 11 , wherein the ranked order is further based on neighborhood relevance scores for neighborhoods in the query city, each of the neighborhoods having a neighborhood relevance score that is determined based on historical bookings of the neighborhood that were initiated from historical queries that specified the query city.
20. The non-transitory computer readable storage medium of claim 19 , wherein the ranked order concerning candidate listings of the plurality of candidate listings that are not located in the query city are not adjusted by the neighborhood relevance scores.