Contextual ranking of photos and text in search
Aspects of the disclosure relate to determining relevant content in response to a request for information. One or more computing devices may receive a query requesting information regarding a place of interest and identify a first place which satisfies the query associated with a first database and a set of displayable content associated with the first place within a second database. The one or more computing devices may identify a subset of the displayable content for display in response to the query, the identification of the subset of displayable content comprising determining a ranking for each item of displayable content in the set of displayable content according to the query. The subset of displayable content and the first place may be provided for presentation on a client device.
1. A computer implemented method for determining relevant content in response to a request for information, the method comprising:
receiving, by one or more computing devices, a query requesting information regarding a place of interest;
identifying, by the one or more computing devices, a first place which satisfies the query associated with a first database and a set of displayable content associated with the first place within a second database;
identifying, by the one or more computing devices, a subset of the displayable content for display in response to the query, the identification of the subset of displayable content comprising determining a ranking for each item of displayable content in the set of displayable content according to the query, wherein determining the ranking for each item of displayable content in the set of displayable content comprises:
identifying particular attributes within the query,
determining, for each item of displayable content in the set of displayable content, using a machine learning classifier, one or more place attributes,
assigning, to each item of displayable content in the set of displayable content, a relevance score based on the one or more place attributes and the particular attributes, and
selecting one or more items of displayable content in the set of displayable content which are assigned the highest relevance scores to be the subset of displayable content; and
providing, by the one or more computing devices, the subset of displayable content and the first place for presentation on a client device.
2. The computer implemented method of claim 1 , wherein identifying the first place comprises:
identifying particular attributes within the query;
for each place in a set of places, determining one or more place attributes and assigning a relevance score based on the one or more place attributes and the particular attributes; and
selecting a place with the highest assigned relevance score as the first place.
3. The computer implemented method of claim 1 , further comprising:
identifying one or more additional places which satisfies the query within a first database and additional sets of displayable content associated with each of the one or more additional places within a second database;
identifying additional subsets of the additional sets of displayable content for display in response to the query, the identification of the additional subsets of displayable content comprising determining a ranking for each item of displayable content in the additional sets of displayable content based on the query; and
providing, by the one or more computing devices, the additional subset of displayable content and the one or more additional places.
4. The computer implemented method of claim 1 , wherein the ranking for each item of displayable content in the set of displayable content is weighted according to the one or more associated place attributes.
5. The computer implemented method of claim 1 , wherein the displayable content includes one or more of webpage addresses, contact information, business information, reviews, ratings, images, and social media accounts.
6. A system for determining relevant content in response to a request for information comprising:
one or more computing devices; and
memory storing instructions, the instructions executable by the one or more computing devices;
wherein the instructions comprise:
receiving a query requesting information regarding a place of interest;
identifying a first place which satisfies the query associated with a first database and a set of displayable content associated with the first place within a second database;
identifying a subset of the displayable content for display in response to the query, the identification of the subset of displayable content comprising determining a ranking for each item of displayable content in the set of displayable content according to the query wherein determining the ranking for each item of displayable content in the set of displayable content comprises:
identifying particular attributes within the query,
determining, for each item of displayable content in the set of displayable content, using a machine learning classifier, one or more place attributes,
assigning, to each item of displayable content in the set of displayable content, a relevance score based on the one or more place attributes and the particular attributes, and
selecting one or more items of displayable content in the set of displayable content which are assigned the highest relevance scores to be the subset of displayable content; and
providing the subset of displayable content and the first place for presentation on a client device.
7. The system of claim 6 , wherein identifying the first place comprises:
identifying particular attributes within the query;
for each place in a set of places, determining one or more place attributes and assigning a relevance score based on the one or more place attributes and the particular attributes; and
selecting a place with the highest assigned relevance score as the first place.
8. The system of claim 6 , further comprising:
identifying one or more additional places which satisfies the query within a first database and additional sets of displayable content associated with each of the one or more additional places within a second database;
identifying additional subsets of the additional sets of displayable content for display in response to the query, the identification of the additional subsets of displayable content comprising determining a ranking for each item of displayable content in the additional sets of displayable content based on the query; and
providing the additional subset of displayable content and the one or more additional places.
9. The system of claim 6 , wherein the ranking for each item of displayable content in the set of displayable content is weighted according to the one or more associated place attributes.
10. The system of claim 6 , wherein the displayable content includes one or more of webpage addresses, contact information, business information, reviews, ratings, images, and social media accounts.
11. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
receiving a query requesting information regarding a place of interest;
identifying a first place which satisfies the query associated with a first database and a set of displayable content associated with the first place within a second database;
identifying a subset of the displayable content for display in response to the query, the identification of the subset of displayable content comprising determining a ranking for each item of displayable content in the set of displayable content according to the query, wherein determining the ranking for each item of displayable content in the set of displayable content comprises:
identifying particular attributes within the query,
determining, for each item of displayable content in the set of displayable content, using a machine learning classifier, one or more place attributes,
assigning, to each item of displayable content in the set of displayable content, a relevance score based on the one or more place attributes and the particular attributes, and
selecting one or more items of displayable content in the set of displayable content which are assigned the highest relevance scores to be the subset of displayable content; and
providing the subset of displayable content and the first place for presentation on a client device.
12. The non-transitory computer-readable medium of claim 11 , wherein identifying the first place comprises:
identifying particular attributes within the query;
for each place in a set of places, determining one or more place attributes and assigning a relevance score based on the one or more place attributes and the particular attributes; and
selecting a place with the highest assigned relevance score as the first place.
13. The non-transitory computer-readable medium of claim 11 , further comprising:
identifying one or more additional places which satisfies the query within a first database and additional sets of displayable content associated with each of the one or more additional places within a second database;
identifying additional subsets of the additional sets of displayable content for display in response to the query, the identification of the additional subsets of displayable content comprising determining a ranking for each item of displayable content in the additional sets of displayable content based on the query; and
providing the additional subset of displayable content and the one or more additional places.
14. The non-transitory computer-readable medium of claim 11 , wherein the ranking for each item of displayable content in the set of displayable content is weighted according to the one or more associated place attributes.