Language-specific search results
View Patent ↗Methods, systems and apparatus, including computer program products are described for ranking content items identified by a search engine and delivering corresponding search results. In one aspect, search engine user language preference data is stored in association with user content item selection records. Analysis of the records is performed to identify content items that appeal to users having common language preferences. Query results can be ranked based on the language preference of the current user and/or the user's query and data derived from the selection records.
1. A computer-implemented method comprising:
receiving a search query;
obtaining a query language of the search query;
obtaining search results responsive to the search query, wherein each search result identifies a respective content item of a plurality of content items,
wherein each content item is associated with a plurality of language presentation counts for a plurality of languages, each language presentation count for each particular language representing how many times a plurality of users having a language preference matching the particular language were presented with an opportunity to select the content item, and
wherein each content item is associated with a plurality of language selection counts for a plurality of languages, each language selection count for each particular language representing how many times a plurality of users having a language preference matching the particular language selected the content item when presented with an opportunity to select the content item;
obtaining a respective language selection weight for the query language for each of the plurality of content items, wherein the language selection weight for the query language for a content item is based on the language presentation count for the query language associated with the content item and the language selection count for the query language associated with the content item;
computing a respective score for each of the plurality content items, wherein the score is based on the language selection weight for each of the plurality of content items;
generating a ranking of a plurality of content items based at least in part on the respective scores; and
providing search results corresponding to the ranking of the plurality of content items in response to the search query.
2. The method of claim 1 , wherein the respective language selection weight for each of the plurality of content items represents a percentage of users having a language preference matching the query language who selected the content item upon being presented with an opportunity to select the content item.
3. The method of claim 1 , wherein computing the respective score for each of the plurality content items comprises adjusting, for each content item, an initial ranking score for the content item by the language selection weight for the content item.
4. The method of claim 1 , further comprising:
computing a domain-aggregated language presentation count for content items on a particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language were presented with a particular content item on the particular domain;
computing a domain-aggregated language selection count for content items on the particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language selected a particular content item on the particular domain when presented with an opportunity to select the particular content item; and
computing the language selection weight for each of the plurality of content items on the particular domain based on the domain-aggregated language presentation count and the domain-aggregated language selection count.
5. The method of claim 1 , further comprising providing a presentation of search results, wherein the presentation includes:
a first section that includes one or more search results that identify resources that are in a language corresponding to the query language; and
a second section that includes one or more of the search results corresponding to the ranking of the plurality of content items.
6. The method of claim 1 , wherein providing the search results in response to the search query comprises adding, to the search results, one or more top-ranked results that identify resources in a language corresponding to the query language.
7. The method of claim 1 , wherein the language selection weight for each of the plurality of content items is computed according to:
language selection weight=bias1+( A ·bias2)+( B ·bias3)
wherein:
A is a percentage of total users clicking on the content item having a language preference matching the query language;
B is a click through percentage of the content item for users having a language preference matching the query language; and
bias1, bias2, and bias3 are biasing factors.
8. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving a search query;
obtaining a query language of the search query;
obtaining search results responsive to the search query, wherein each search result identifies a respective content item of a plurality of content items,
wherein each content item is associated with a plurality of language presentation counts for a plurality of languages, each language presentation count for each particular language representing how many times a plurality of users having a language preference matching the particular language were presented with an opportunity to select the content item, and
wherein each content item is associated with a plurality of language selection counts for a plurality of languages, each language selection count for each particular language representing how many times a plurality of users having a language preference matching the particular language selected the content item when presented with an opportunity to select the content item;
obtaining a respective language selection weight for the query language for each of the plurality of content items, wherein the language selection weight for the query language for a content item is based on the language presentation count for the query language associated with the content item and the language selection count for the query language associated with for the content item;
computing a respective score for each of the plurality content items, wherein the score is based on the language selection weight for each of the plurality of content items;
generating a ranking of a plurality of content items based at least in part on the respective scores; and
providing search results corresponding to the ranking of the plurality of content items in response to the search query.
9. The system of claim 8 , wherein the respective language selection weight for each of the plurality of content items represents a percentage of users having a language preference matching the query language who selected the content item upon being presented with an opportunity to select the content item.
10. The system of claim 8 , wherein computing the respective score for each of the plurality of content items comprises adjusting, for each content item, an initial ranking score for the content item by the language selection weight for the content item.
11. The system of claim 8 , wherein the operations further comprise:
computing a domain-aggregated language presentation count for content items on a particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language were presented with a particular content item on the particular domain;
computing a domain-aggregated language selection count for the content items on the particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language selected a particular content item on the particular domain when presented with an opportunity to select the particular content item;
computing the language selection weight for each of the plurality of content items on the particular domain based on the domain-aggregated language presentation count and the domain-aggregated language selection count.
12. The system of claim 8 , wherein the operations further comprise providing a presentation of search results, wherein the presentation includes:
a first section that includes one or more search results that identify resources that are in a language corresponding to the query language; and
a second section that includes one or more of the search results corresponding to the ranking of the plurality of content items.
13. The system of claim 8 , wherein providing the search results in response to the search query comprises adding, to the search results, one or more top-ranked results that identify resources in a language corresponding to the query language.
14. The system of claim 8 , wherein the language selection weight for each of the plurality of content items is computed according to:
language selection weight=bias1+( A ·bias2)+( B ·bias3)
wherein:
A is a percentage of total users clicking on the content item having a language preference matching the query language;
B is a click through percentage of the content item for users having a language preference matching the query language; and
bias1, bias2, and bias3 are biasing factors.
15. A computer program product, encoded on one or more non-transitory computer storage media, comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
receiving a search query;
obtaining a query language of the search query;
obtaining search results responsive to the search query, wherein each search result identifies a respective content item of a plurality of content items,
wherein each content item is associated with a plurality of language presentation counts for a plurality of languages, each language presentation count for each particular language representing how many times a plurality of users having a language preference matching the particular language were presented with an opportunity to select the content item, and
wherein each content item is associated with a plurality of language selection counts for a plurality of languages, each language selection count for each particular language representing how many times a plurality of users having a language preference matching the particular language selected the content item when presented with an opportunity to select the content item;
obtaining a respective language selection weight for the query language for each of the plurality of content items, wherein the language selection weight for the query language for a content item is based on the language presentation count for the query language associated with the content item and the language selection count for the query language associated with the content item;
computing a respective score for each of the plurality content items, wherein the score is based on the language selection weight for each of the plurality of content items;
generating a ranking of a plurality of content items based at least in part on the respective scores; and
providing search results corresponding to the ranking of the plurality of content items in response to the search query.
16. The computer program product of claim 15 , wherein the respective language selection weight for each of the plurality of content items represents a percentage of users having a language preference matching the query language who selected the content item upon being presented with an opportunity to select the content item.
17. The computer program product of claim 15 , wherein computing the respective score for each of the plurality of content items comprises adjusting, for each content item, an initial ranking score for the content item by the language selection weight for the content item.
18. The computer program product of claim 15 , wherein the operations further comprise:
computing a domain-aggregated language presentation count for content items on a particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language were presented with a particular content item on the particular domain;
computing a domain-aggregated language selection count for the content items on the particular domain, wherein the domain-aggregated language presentation count represents how many times a plurality of users having a language preference matching the query language selected a particular content item on the particular domain when presented with an opportunity to select the particular content item;
computing the language selection weight for each of the plurality of content items on the particular domain based on the domain-aggregated language presentation count and the domain-aggregated language selection count.
19. The computer program product of claim 15 , wherein the operations further comprise providing a presentation of search results, wherein the presentation includes:
a first section that includes one or more search results that identify resources that are in a language corresponding to the query language; and
a second section that includes one or more of the search results corresponding to the ranking of the plurality of content items.
20. The computer program product of claim 15 , wherein providing the search results in response to the search query comprises adding, to the search results, one or more top-ranked results that identify resources in a language corresponding to the query language.
21. The computer program product of claim 15 , wherein the language selection weight for each of the plurality of content items is computed according to:
language selection weight=bias1+( A ·bias2)+( B ·bias3)
wherein:
A is a percentage of the total users clicking on the content item having a language preference matching the query language;
B is a click through percentage of the content item for users having a language preference matching the query language; and
bias1, bias2, and bias3 are biasing factors.