Incorporating geographical locations in a search process
First Claim
1. A method, comprising:
- by one or more computing devices, accessing a search query and a document identified in response to the search query;
determining a probability that the search query has a local intent relating to a first geographical location;
wherein in response to the probability meeting or exceeding a threshold probability value;
determining a first minimum bounding region enclosing the first geographical location;
computing a threshold location value for the first geographical location based on a combination of the probability and a normalized population of the first geographical area;
extracting one or more second geographical locations from the document;
for the one or more second geographical locations,determining a second minimum bounding region enclosing the one or more second geographical locations;
computing a distance between the first minimum bounding region and the second minimum bounding region; and
in response to determining that the distance is greater than the threshold location value, discarding the document by not including the document in a search result identified in response to the search query.
9 Assignments
0 Petitions
Accused Products
Abstract
In one embodiment, accessing a search query and a document identified in response to the search query; extracting a first geographical location from the search query or from information associated with a user issuing the search query or a device used by the user to issue the search query; determining a first minimum bounding region enclosing the first geographical location; computing a threshold for the first geographical location; extracting one or more second geographical locations from the document; for one of the second geographical locations, determining a second minimum bounding region enclosing the one second geographical location; computing a distance between the first minimum bounding region and the second minimum bounding region; and if the distance is greater than the threshold, then discarding the document by not including the document in a search result identified in response to the search query.
17 Citations
31 Claims
-
1. A method, comprising:
-
by one or more computing devices, accessing a search query and a document identified in response to the search query; determining a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value; determining a first minimum bounding region enclosing the first geographical location; computing a threshold location value for the first geographical location based on a combination of the probability and a normalized population of the first geographical area; extracting one or more second geographical locations from the document; for the one or more second geographical locations, determining a second minimum bounding region enclosing the one or more second geographical locations; computing a distance between the first minimum bounding region and the second minimum bounding region; and in response to determining that the distance is greater than the threshold location value, discarding the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (2, 3, 4, 5, 31)
-
-
6. A method, comprising:
- by one or more computing devices,
accessing a search query and a document identified in response to the search query; determining a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value; computing a threshold location value for the first geographical location based on a combination of the probability and a population density of the first geographical location; constructing a first location feature for the search query based on the first geographical location and a location hierarchy, wherein the first location feature comprises the first geographical location; extracting one or more second geographical locations from the document; constructing a second location feature for the document based on the one or more second geographical locations and the location hierarchy, wherein the second location feature comprises one or more of the one or more second geographical locations; comparing the first location feature and the second location feature and with respect to the threshold location value; and in response to determining that there is no match between any geographical location of the first location feature and the one or more of the one or more geographical locations of the second location feature, discarding the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (7, 8, 9, 10)
- by one or more computing devices,
-
11. A system, comprising:
-
a memory comprising instructions executable by one or more processors; and one or more processors coupled to the memory to execute the instructions, the instructions being operable to; access a search query and a document identified in response to the search query; determine a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value, the instructions being further operable to; determine a first minimum bounding region enclosing the first geographical location; compute a threshold location value for the first geographical location based on a combination of the probability and a population density of the first geographical location; extract one or more second geographical locations from the document; for one or more of the one or more second geographical locations, determine a second minimum bounding region enclosing the one or more second geographical locations; compute a distance between the first minimum bounding region and the second minimum bounding region; and in response to determining that the distance is greater than the threshold location value, the instructions being further operable to discard the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A system, comprising:
-
a memory comprising instructions executable by one or more processors; and one or more processors coupled to the memory and operable to execute the instructions, the one or more processors being operable when executing the instructions to; access a search query and a document identified in response to the search query; determine a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value, the instructions being further operable to; construct a first location feature for the search query based on the first geographical location and a location hierarchy, wherein the first location feature comprises the first geographical location; extract one or more second geographical locations from the document; construct a second location feature for the document based on the one or more second geographical locations and the location hierarchy, wherein the second location feature comprises one or more of the one or more second geographical locations; compute a threshold location value for the first geographical location based on a combination of the probability and a population density of the first geographical location; compare the first location feature and the second location feature and with respect to the threshold location value; and in response to determining there is no match between any geographical location of the first location feature and the one or more of the one or more second geographical locations of the second location feature, discard the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (17, 18, 19, 20)
-
-
21. One or more computer-readable non-transitory storage media embodying software executable by one or more computer systems to:
-
access a search query and a document identified in response to the search query; determine a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value; determine a first minimum bounding region enclosing the first geographical location; compute a threshold location value for the first geographical based on a combination of the probability and a population density of the first geographical location; extract one or more second geographical locations from the document; for one or more of the one or more second geographical locations, determine a second minimum bounding region enclosing the one or more of the one or more second geographical locations; compute a distance between the first minimum bounding region and the second minimum bounding region; and in response to determining that the distance is greater than the threshold, discard the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (22, 23, 24, 25)
-
-
26. One or more computer-readable non-transitory storage media embodying software executable by one or more computer systems to:
-
access a search query and a document identified in response to the search query; determine a probability that the search query has a local intent relating to a first geographical location; wherein in response to the probability meeting or exceeding a threshold probability value, the instructions are further operable to; construct a first location feature for the search query based on the first geographical location and a location hierarchy, wherein the first location feature comprises the first geographical location; extract one or more second geographical locations from the document; construct a second location feature for the document based on the one or more second geographical locations and the location hierarchy, wherein the second location feature comprises one or more of the one or more second geographical locations; compute a threshold location value for the first geographical location based on a combination of the probability and a population density of the first geographical location; compare the first location feature and the second location feature and with respect to the threshold value; and in response to determining that there is no match between any geographical location of the first location feature and any geographical location of the second location feature, discard the document by not including the document in a search result identified in response to the search query. - View Dependent Claims (27, 28, 29, 30)
-
Specification