Location awareness search assistance system and method
A location-aware search assist capability identifies location-aware search query suggestions using location information associated with the location-aware search query suggestions. A user's search query input and location and a location associated with each location-aware search query suggestion candidates may be used to identify a set of search query suggestions for presentation to the user. Location-aware search query suggestion candidates may be ranked in accordance with a closeness of each one's location to the user's location. The ranking may be performed using a score, such as a popularity score associated with each search query suggestion candidate. The location-aware search query suggestion candidates having a location closer to the user's location may be promoted by adjusting each candidate's popularity score upward, and the search query suggestion candidates that are farther away from the user's location may be demoted by adjusting each such candidate's popularity score downward.
1 . A method comprising:
receiving, via a computing device, search query input of a user;
selecting, via the computing device and from a corpus of search queries, a set of search queries using the search query input of the user, at least a portion of a search query selected from the set matching at least a portion of the search query input of the user, each search query in the set having a respective popularity score and a respective geographic location;
making, via the computing device, a determination that the respective geographic location of a first search query from the set is closer to a geographic location of the user than the respective geographic location of a second search query from the set;
promoting, via the computing device, based on the determination, the first search query over the second search query in a ranking of the set of search queries based on respective popularity scores of each search query, the promoting of the first search query over the second search query in the ranking being based on an adjusted popularity score and comprising either adjusting the respective popularity score of the first search query upward or adjusting the respective popularity score of the second search query downward;
selecting, via the computing device, a number of the search queries as candidate search query suggestions using the ranking of the set of search queries; and
making, via the computing device, the number of search queries available as candidate search query suggestions to the user in response to the search query input of the user.
2 . The method of claim 1 , further comprising:
determining, via the computing device and for each search query of the set of search queries, a popularity score using a frequency of occurrence of the search query in a number of search query logs.
3 . The method of claim 1 , further comprising:
identifying, via the computing device, the respective geographic location of a search query in the set using a trained model and a set of features determined for the search query.
4 . The method of claim 3 , the identifying further comprising:
analyzing, by the computing device, information associated with the search query and determining the set of features based on the analysis.
5 . The method of claim 4 , the set of features comprising information indicating a level of confidence that the information associated with the search query is indicative of the respective geographic location.
6 . The method of claim 4 , the set of features comprising information indicating a level of scope of a geographic location detected among the information associated with the search query.
7 . The method of claim 4 , the set of features comprising information indicating whether or not a geographic location detected among the information associated with the search query corresponds to a point of interest.
8 . The method of claim 4 , the set of features comprising a probability that the search query has a local intent.
9 . The method of claim 4 , the set of features comprising a probability that the search query has a travel intent.
10 . The method of claim 4 , the information associated with the search query comprising terms of the search query.
11 . The method of claim 10 , the set of features comprising information indicating the number of terms of the search query indicating geographic location information.
12 . The method of claim 1 , further comprising:
determining, by the computing device, the geographic location of the user using information received from the user's device.
13 . The method of claim 12 , the received information comprising an IP address.
14 . The method of claim 12 , the received information comprising GPS information of the user's device.
15 . A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:
receiving search query input of a user;
selecting, from a corpus of search queries, a set of search queries using the search query input of the user, at least a portion of a search query selected from the set matching at least a portion of the search query input of the user, each search query in the set having a respective popularity score and a respective geographic location;
making a determination that the respective geographic location of a first search query from the set is closer to a geographic location of the user than the respective geographic location of a second search query from the set;
promoting, based on the determination, the first search query over the second search query in a ranking of the set of search queries based on respective popularity scores of each search query, the promoting of the first search query over the second search query in the ranking being based on an adjusted popularity score and comprising either adjusting the respective popularity score of the first search query upward or adjusting the respective popularity score of the second search query downward;
selecting a number of the search queries as candidate search query suggestions using the ranking of the set of search queries; and
making the number of search queries available as candidate search query suggestions to the user in response to the search query input of the user.
16 . The non-transitory computer-readable storage medium of claim 15 , the method further comprising:
determining, for each search query of the set of search queries, a popularity score using a frequency of occurrence of the search query in a number of search query logs.
17 . The non-transitory computer-readable storage medium of claim 15 , further comprising:
identifying the respective geographic location of a search query in the set using a trained model and a set of features determined for the search query.
18 . The non-transitory computer-readable storage medium of claim 17 , the identifying further comprising:
analyzing information associated with the search query and determining the set of features based on the analysis.
19 . The non-transitory computer-readable storage medium of claim 18 , the information associated with the search query comprising terms of the search query.
20 . A system comprising:
a computing device comprising a processor and a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising:
receiving logic executed by the processor for receiving search query input of a user;
selecting logic executed by the processor for selecting, from a corpus of search queries, a set of search queries using the search query input of the user, at least a portion of a search query selected from the set matching at least a portion of the search query input of the user, each search query in the set having a respective popularity score and a respective geographic location;
making logic executed by the processor for making a determination that the respective geographic location of a first search query from the set is closer to a geographic location of the user than the respective geographic location of a second search query from the set;
promoting logic executed by the processor for promoting, based on the determination, the first search query over the second search query in a ranking of the set of search queries based on respective popularity scores of each search query, the promoting of the first search query over the second search query in the ranking being based on an adjusted popularity score and comprising either adjusting the respective popularity score of the first search query upward or adjusting the respective popularity score of the second search query downward;
selecting logic executed by the processor for selecting a number of the search queries as candidate search query suggestions using the ranking of the set of search queries; and
making logic executed by the processor for making the number of search queries available as candidate search query suggestions to the user in response to the search query input of the user.