Autonomous Item Generation

Abstract

An autonomous item generation system implements a trained machine learning model configured to output fabrication instructions for generating an item and metadata describing the item, automatically and independent of user input. Fabrication instructions output by the machine learning model are transmitted to a fabrication device for generating the item. The autonomous item generation system generates a listing for the item based on the metadata output by the machine learning model and publishes the listing to a virtual marketplace. Analytics data describing feedback for the item listing is used to generate training data for the machine learning model. The training data is input to the machine learning model, which causes the machine learning model to refine at least one control parameter according to a loss function that penalizes negative differences between predicted and observed feedback data for the item. The machine learning model with the refined parameter(s) is then used by the autonomous item generation system to generate fabrication instructions and metadata for an additional item.

What is claimed is: 
     
         1 . A method for autonomous item generation implemented by at least one computing device, the method comprising:
 generating, using at least one machine learning model, instructions for fabricating an item and metadata describing the item;   fabricating the item by communicating the instructions for fabricating the item to a fabrication device;   creating a listing for the item using the metadata;   publishing the listing to a virtual marketplace and obtaining analytics data describing one or more interactions with the listing via the virtual marketplace;   forming training data using the analytics data and modifying a parameter of the at least one machine learning model based on the training data; and   generating, using the at least one machine learning model with the modified parameter, instructions for fabricating a different item.   
     
     
         2 . The method of  claim 1 , wherein the method is performed automatically, and independent of user input. 
     
     
         3 . The method of  claim 1 , wherein the at least one machine learning model comprises a generative adversarial network. 
     
     
         4 . The method of  claim 1 , wherein the metadata describing the item includes at least one of a title for the listing and an item description for the listing. 
     
     
         5 . The method of  claim 1 , wherein the one or more interactions include at least one of a view of the listing, a purchase of the item, an indication of interest in the listing, or a share of the listing by a user of the virtual marketplace. 
     
     
         6 . The method of  claim 5 , wherein the analytics data comprises demographic information for the user of the virtual marketplace specifying at least one of an age of the user, a location associated with the user, a gender of the user, a user profile associated with the user, or historical interaction data for the user. 
     
     
         7 . The method of  claim 1 , wherein the fabrication device comprises a printer and the item comprises an art piece. 
     
     
         8 . The method of  claim 1 , wherein the fabrication device comprises one or more textile machines and the item comprises an article of clothing 
     
     
         9 . The method of  claim 1 , further comprising facilitating a transaction of the item via the virtual marketplace by receiving an indication of a purchasing user, verifying a transaction between the purchasing user and the virtual marketplace, identifying a plurality of shipping options for transporting the item to the purchasing user, selecting one of the plurality of shipping options, and causing shipment of the item to the purchasing user via the selected shipping option. 
     
     
         10 . A method for autonomous item generation implemented by at least one computing device, the method comprising:
 displaying a user interface that includes a control for specifying a machine learning model to be used in autonomously generating an item and a control for specifying an audience to be considered in generating the item;   receiving input at the user interface that specifies at least one of the machine learning model to be used or the audience to be considered in generating the item;   updating the user interface to display a preview representation of the item responsive to receiving the input;   receiving additional input that modifies at least one of the machine learning model to be used or the audience to be considered in generating the item; and   modifying the preview representation of the item responsive to receiving the additional input.   
     
     
         11 . The method of  claim 10 , wherein the machine learning model comprises a generative adversarial network trained to generate printing instructions for a three dimensional objet, the item comprises the three dimensional object, and the preview representation of the item comprises a digital rendering of the three dimensional object. 
     
     
         12 . The method of  claim 10 , wherein the machine learning model comprises a generative adversarial network trained to generate fabrication instructions for fabricating an article of clothing, the item comprises the article of clothing, and the preview representation of the item comprises a digital rendering of the article of clothing 
     
     
         13 . The method of  claim 10 , wherein the machine learning model comprises a generative adversarial network trained to generate printing instructions for a two dimensional piece of art, the item comprises the two dimensional piece of art, and the preview representation of the item comprises a digital rendering of the piece of art. 
     
     
         14 . The method of  claim 10 , wherein modifying the preview representation of the item comprises maintaining a visual appearance of the preview representation of the item and altering descriptive information for the item. 
     
     
         15 . A system for autonomous item generation comprising:
 one or more processors; and   a computer-readable storage medium having instructions stored thereon that are executable by the one or more processors to perform operations comprising:
 generating, using at least one machine learning model, instructions for fabricating an item and metadata describing the item; 
 fabricating the item by communicating the instructions for fabricating the item to a fabrication device; 
 creating a listing for the item using the metadata and publishing the listing to a virtual marketplace; 
 facilitating a transaction of the item by:
 receiving an indication of a user purchasing the item via the virtual marketplace; 
 verifying a payment for the item from the user; and 
 causing shipment of the item to the user; 
 
 forming training data from the transaction and modifying a parameter of the at least one machine learning model based on the training data; and 
 outputting the at least one machine learning model with the modified parameter. 
   
     
     
         16 . The system of  claim 15 , the operations further comprising performing the generating, the fabricating, the creating, the facilitating, the forming, and the outputting automatically, and independent of user input. 
     
     
         17 . The system of  claim 15 , the operations further comprising generating, using the at least one machine learning model with the modified parameter, instructions for fabricating a different item and metadata describing the different item. 
     
     
         18 . The system of  claim 15 , wherein the training data specifies demographic data associated with the user, the demographic data specifying one or more of an age, a gender, a location, or other user profile information for the user. 
     
     
         19 . The system of  claim 15 , wherein causing shipment of the item to the user comprises identifying a plurality of shipping options for shipping the item to the user, selecting one of the plurality of shipping options, and contracting with a shipping entity associated with the selected one of the plurality of shipping options to ship the item to the user. 
     
     
         20 . The system of  claim 15 , the operations further comprising identifying one or more similar listings published to the virtual marketplace, obtaining feedback data describing user interaction with the one or more similar item listings, generating additional training data from the feedback data, wherein modifying the parameter of the at least one machine learning model is further based on the additional training data.