Presenting search results in a dynamically formatted graphical user interface
A content provider can provide content, such as advertisements or other promotional material, to a recipient. A distribution system of the content provider can receive a query and select one or more advertisements and a user interface for presenting the advertisements based on the query, information associated with the user, a set of queries received from the user, and/or other information. A model for selecting the user interface can be generated by serving available user interfaces randomly or pseudo-randomly and monitoring user interaction with the served user interfaces. The model can be updated during regular use based on the performance of the user interfaces.
1. A computing system, comprising:
one or more processors; and
one or more non-transitory computer readable media that collectively store instructions that when executed by the one or more processors cause the one or more processors to perform operations, the operations comprising:
receiving, from a user computing device associated with a user, a query comprising one or more search terms;
selecting one or more search results responsive to the query;
providing, to a machine-learning model, a request for a user interface selection and information including at least one of one or more queries received from the user, a category of each of the one or more queries, demographic information of the user, advertisement conversion rates, predicted click through rates, previous interaction information for the user associated with the query, or a type of the query;
receiving, as an output of the machine-learning model in response to the request, a selection of a first user interface format, the first user interface format being selected by the machine-learning model based at least in part on the information or being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use;
transmitting instructions causing the user computing device to render a graphical user interface having the first user interface format for presenting at least a portion of the one or more search results; and
providing the machine-learning model at least one of interaction information indicative of interaction of the user with the first user interface format or the type of the query for updating the machine-learning model.
2. The computing system of claim 1 , further comprising:
receiving a set of rules for selecting user interfaces for displaying query results; and
initially training the machine-learning model for selecting user interfaces based on the set of rules,
wherein providing, to the machine-learning model, the request for the user interface selection comprises providing, to the machine-learning model, the request for the user interface selection after initially training the machine-learning model.
3. The computing system of claim 1 , wherein receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format comprises receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format, the first user interface format being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use.
4. The computing system of claim 1 , wherein providing, to the machine-learning model, the request for the user interface selection and the information comprises providing, to the machine-learning model, the request for the user interface selection and the information, the information comprising one or both of the previous interaction information for the user associated with the query or the type of the query.
5. The computing system of claim 4 , wherein the machine-learning model is configured to dynamically generate the first user interface format based at least in part on the one or both of the previous interaction information or the type of the query.
6. The computing system of claim 4 , wherein the previous interaction information for the user comprises at least one of a user selection of one or more previous search results, an indication that the user hovered over the one or more previous search results, a number of related queries received from the user, or merchants, advertisers, or advertisement that receive a highest amount of clicks from the user.
7. The computing system of claim 4 , wherein the machine-learning model is configured to select, based at least in part on the one or both of the previous interaction information or the type of the query, the first user interface format from two or more user interface formats, each of the two or more user interface formats comprising a corresponding template for displaying specified content of the one or more search results.
8. The computing system of claim 4 , wherein demographic information of the user is provided to the machine-learning model with the one or both of the previous interaction information or the type of the query.
9. The computing system of claim 1 , the operations further comprising determining if each of the one or more search results corresponds to the first user interface format selected,
wherein transmitting the instructions causing the user computing device to render the graphical user interface comprises transmitting the instructions causing the user computing device to render the graphical user interface having the first user interface format for presenting the one or more search results that correspond to the first user interface format.
10. The computing system of claim 9 , wherein the operations further comprise changing the one or more search results that differ from the first user interface format to correspond to the first user interface format.
11. The computing system of claim 1 , wherein the operations further comprise determining the type of the query based on the search terms.
12. The computing system of claim 1 , wherein the operations further comprise:
transmitting, to the user computing device, one or more selected advertisements for presentation with the one or more search results.
13. The computing system of claim 1 , wherein the one or more search results comprise advertisements.
14. One or more non-transitory computer readable media that collectively store instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:
receiving, from a user computing device associated with a user, a query comprising one or more search terms;
selecting one or more search results responsive to the query;
providing, to a machine-learning model for selecting user interfaces, a request for a user interface selection and information including at least one of one or more queries received from the user, a category of each of the one or more queries, demographic information of the user, advertisement conversion rates, predicted click through rates, previous interaction information for the user associated with the query, or a type of the query;
receiving, as an output of the machine-learning model in response to the request, a selection of a first user interface format, the first user interface format being selected by the machine-learning model based at least in part on the information or being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use;
transmitting instructions causing the user computing device to render a graphical user interface having the first user interface format for presenting at least a portion of the one or more search results; and
providing the machine-learning model at least one of interaction information indicative of interaction of the user with the first user interface format or the type of the query for updating the machine-learning model.
15. The one or more non-transitory computer readable media of claim 14 , wherein the operations further comprise:
receiving a set of rules for selecting user interfaces for displaying query results; and
initially training the machine-learning model for selecting user interfaces based on the set of rules,
wherein providing, to the machine-learning model, the request for the user interface selection comprises providing, to the machine-learning model, the request for the user interface selection after initially training the machine-learning model.
16. The one or more non-transitory computer readable media of claim 14 , wherein receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format comprises receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format, the first user interface format being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use.
17. The one or more non-transitory computer readable media of claim 14 , wherein providing, to the machine-learning model, the request for the user interface selection comprises providing, to the machine-learning model, one or both of previous interaction information for the user associated with the query or the type of the query.
18. A method to select a user interface format for presenting one or more search results responsive to a query, the method comprising:
by a computing system:
receiving, from a user computing device associated with a user, a query comprising one or more search terms;
selecting one or more search results responsive to the query;
providing, to a machine-learning model for selecting user interfaces, a request for a user interface selection and information including at least one of one or more queries received from the user, a category of each of the one or more queries, demographic information of the user, advertisement conversion rates, predicted click through rates, previous interaction information for the user associated with the query, or a type of the query;
receiving, as an output of the machine-learning model in response to the request, a selection of a first user interface format, the first user interface format being selected by the machine-learning model based at least in part on the information or being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use;
transmitting instructions causing the user computing device to render a graphical user interface having the first user interface format for presenting at least a portion of the one or more search results; and
providing the machine-learning model at least one of interaction information indicative of interaction of the user with the first user interface format or the type of the query for updating the machine-learning model.
19. The method of claim 18 , wherein receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format comprises receiving, as the output of the machine-learning model in response to the request, the selection of the first user interface format, the first user interface format being selected randomly or pseudo-randomly by the machine-learning model from user interface formats having performance information indicating infrequent or no previous use.
20. The method of claim 18 , wherein providing, to the machine-learning model, the request for the user interface selection comprises providing, to the machine-learning model, one or both of previous interaction information for the user associated with the query or the type of the query.