Non-binary gender filter

Abstract

Various embodiments utilize a machine learning-based approach to filter items, such as apparel items, based on non-binary gender styles. For example, an electronic catalog of apparel items can be assigned gender scores on a gender scale by a neural network trained to determine a gender score of an apparel item based on an image representation of the apparel item. The neural network may be trained on training data that includes images of various apparel items with gender designations. The apparel items in the electronic catalog are assigned a gender score attribute that reflects how masculine or feminine the apparel item may be. As such, the apparel items can be organized (e.g., sorted, filtered, ranked) based on a non-binary gender score in addition to other attributes, such as item type, size, color, brand, etc. Thus, a user can include non-binary gender style as a search or filtering criteria.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 generating a user interface for display at a client device, the user interface comprising a non-binary gender input element;   receiving a user input via the non-binary gender input element;   determining, based on the user input, a non-binary gender query value;   executing a search against a plurality of content items using at least the non-binary gender query value, the plurality of content items having respective non-binary gender values;   determining one or more content items from the plurality of content items responsive to the search; and   providing a reference to the one or more content items for display at the client device.   
     
     
         2 . The method of  claim 1 , further comprising:
 providing one or more additional filtering elements via the user interface;   receiving one or more additional filtering inputs from the client device; and   executing the search using the non-binary gender query value and the one or more additional filtering inputs.   
     
     
         3 . The method of  claim 1 , further comprising:
 providing, at the user interface, a slider as the non-binary gender input element; and   receiving a user manipulated position of the slider as the user input.   
     
     
         4 . The method of  claim 1 , further comprising:
 providing, at the user interface, a plurality of selectable images associated with different gender scores;   receiving a selection of one or more of the plurality of selectable images; and   determining the non-binary gender query value based at least in part on the one or more selected images.   
     
     
         5 . The method of  claim 1 , further comprising:
 receiving a user selection of one of the one or more displayed content items; and   associating the selected content item or the non-binary gender value of the selected content item with the non-binary gender query value.   
     
     
         6 . The method of  claim 1 , wherein the non-binary gender value is defined between a masculine end and a feminine end, and reflects how masculine or feminine an apparel item is as determined by a trained model. 
     
     
         7 . The method of  claim 1 , further comprising:
 training a model using training data comprising a plurality of content items with respective gender designations; and   using the trained model to assign the respective non-binary gender values to the plurality of content items.   
     
     
         8 . A system comprising:
 a processor; and   a memory device including instructions that, when executed by the processor, cause the system to:
 generate a user interface for display at a client device, the user interface comprising a non-binary gender input element; 
 receive a user input via the non-binary gender input element; 
 determine, based on the user input, a non-binary gender query value; 
 execute a search against a plurality of content items using at least the non-binary gender query value, the plurality of content items having respective non-binary gender values; 
 determine one or more content items from the plurality of content items responsive to the search; and 
 provide a reference to the one or more content items for display at the client device. 
   
     
     
         9 . The system of  claim 8 , wherein the instructions when executed further cause the system to:
 provide one or more additional filtering elements via the user interface;   receive one or more additional filtering inputs from the client device; and   execute the search using the non-binary gender query value and the one or more additional filtering inputs.   
     
     
         10 . The system of  claim 8 , wherein the instructions when executed further cause the system to:
 provide, at the user interface, a slider as the non-binary gender input element; and   receive a user manipulated position of the slider as the user input.   
     
     
         11 . The system of  claim 8 , wherein the instructions when executed further cause the system to:
 provide, at the user interface, a plurality of selectable images associated with different gender scores;   receive a selection of one or more of the plurality of selectable images; and   determine the non-binary gender query value based at least in part on the one or more selected images.   
     
     
         12 . The system of  claim 8 , wherein the instructions when executed further cause the system to:
 receive a user selection of one of the one or more displayed content items; and   associate the selected content item or the non-binary gender value of the selected content item with the non-binary gender query value.   
     
     
         13 . The system of  claim 8 , wherein the non-binary gender value is defined between a masculine end and a feminine end, and reflects how masculine or feminine an apparel item is as determined by a trained model. 
     
     
         14 . The system of  claim 8 , wherein the instructions when executed further cause the system to:
 train a model using training data comprising a plurality of content items with respective gender designations; and   use the trained model to assign the respective non-binary gender values to the plurality of content items.   
     
     
         15 . A computer-readable storage medium storing instructions, the instructions when executed by a processor causing the processor to:
 generate a user interface for display at a client device, the user interface comprising a non-binary gender input element;   receive a user input via the non-binary gender input element;   determine, based on the user input, a non-binary gender query value;   execute a search against a plurality of content items using at least the non-binary gender query value, the plurality of content items having respective non-binary gender values;   determine one or more content items from the plurality of content items responsive to the search; and   provide a reference to the one or more content items for display at the client device.   
     
     
         16 . The computer-readable storage medium of  claim 15 , wherein the instructions when executed further cause the processor to:
 provide one or more additional filtering elements via the user interface;   receive one or more additional filtering inputs from the client device; and   execute the search using the non-binary gender query value and the one or more additional filtering inputs.   
     
     
         17 . The computer-readable storage medium of  claim 15 , wherein the instructions when executed further cause the processor to:
 provide, at the user interface, a slider as the non-binary gender input element; and   receive a user manipulated position of the slider as the user input.   
     
     
         18 . The computer-readable storage medium of  claim 15 , wherein the instructions when executed further cause the processor to:
 provide, at the user interface, a plurality of selectable images associated with different gender scores;   receive a selection of one or more of the plurality of selectable images; and   determine the non-binary gender query value based at least in part on the one or more selected images.   
     
     
         19 . The computer-readable storage medium of  claim 15 , wherein the instructions when executed further cause the processor to:
 receive a user selection of one of the one or more displayed content items; and   associate the selected content item or the non-binary gender value of the selected content item with the non-binary gender query value.   
     
     
         20 . The computer-readable storage medium of  claim 15 , wherein the non-binary gender value is defined between a masculine end and a feminine end, and reflects how masculine or feminine an apparel item is as determined by a trained model.