Determining and presenting attributes for search
AssigneeAdobe Inc.
InventorsMichele Saad, Robert William Burke, Jr., Irgelkha Mejia, Ronald Eduardo Oribio
Life of this patent
Estimating the term…
Abstract
A search system determines a hierarchy of attributes for a set of search results and returns the search results based on a top-ranked attribute. The search system identifies item listings based on a search input and determines attributes of the item listings. A machine learning model generates a hierarchy of the attributes. The search results are provided based on a top-ranked attribute from the hierarchy of the attributes.
Claims15
One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
- identifying, by at least one of one or more servers of a search system, a plurality of item listings based on a search input;
- providing, by at least one of the one or more servers of the search system, data based on the search input and the plurality of item listings as input to a machine learning model trained on attributes of item listings from user interaction data from the search system, the user interaction data comprising at least one of:
- search data, browse data, item review data, and item return data;
- generating, by the machine learning model, a ranking of attributes for the plurality of item listings, wherein the machine learning model determines the ranking of the attributes based at least in part on analysis of differences in attribute values among the plurality of item listings to determine an extent to which attributes distinguish the plurality of item listings from one another, and wherein the machine learning model determines the ranking of the attributes based at least in part on analysis of information visible in search snippets for the plurality of item listings to determine an extent to which attributes are apparent from the search snippets;
- and
- providing, by at least one of the one or more servers of the search system, one or more search results for presentation on a user device based on the ranking of the attributes.
A search system having one or more servers comprising:
- one or more processors;
- and
- one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, causes the search system to perform operations comprising:
- identifying, by at least one of the one or more servers of the search system, a plurality of item listings based on a search input;
- providing, by at least one of the one or more servers of the search system, data based on the search input and the plurality of item listings as input to a model trained on attributes of item listings from user interaction data from the search system, the user interaction data comprising at least one of:
- search data, browse data, item review data, and item return data;
- generating, by the model, a ranking of attributes for the plurality of item listings, wherein the model determines the ranking of the attributes based at least in part on analysis of differences in attribute values among the plurality of item listings to determine an extent to which attributes distinguish the plurality of item listings from one another, and wherein the model determines the ranking of the attributes based at least in part on analysis of information visible in search snippets for the plurality of item listings to determine an extent to which attributes are apparent from the search snippets;
- and
- providing, by at least one of the one or more servers of the search system, a plurality of search results corresponding to item listings of the plurality of item listings with a visual indication of a value of a top-ranked attribute based on the ranking of the attributes.
Dependencies are inferred from the claim text.