US 12,406,289 B2
Techniques for automatic filling of an input form to generate a listing
Gilad Eliyhau Fuchs, Kfar Saba (IL); Haggai Roitman, Yokneam Ilit (IL); and Matan Mandelbrod, Pardes Hana (IL)
Assigned to EBAY INC., San Jose, CA (US)
Filed by eBay Inc., San Jose, CA (US)
Filed on May 24, 2022, as Appl. No. 17/752,652.
Prior Publication US 2023/0385887 A1, Nov. 30, 2023
Int. Cl. G06Q 30/0601 (2023.01); G06F 16/958 (2019.01); G06F 40/174 (2020.01); G06F 40/205 (2020.01); G06F 40/284 (2020.01); G06N 3/044 (2023.01); G06N 3/0464 (2023.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/0603 (2013.01) [G06F 40/174 (2020.01); G06F 40/205 (2020.01); G06F 40/284 (2020.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating a listing for an item, the method comprising:
receiving, via a user interface associated with an online marketplace, a request to generate the listing for the item, the request comprising a natural language text input as a title for the listing;
based on the natural language text input, determining a plurality of missing item description attributes that are missing from the natural language text input;
generating, based at least in part on inputting the natural language text to a transformer-based machine learning model, a predicted value for a first missing item description attribute and a predicted value for a second missing item description attribute of the plurality of missing item description attributes, the predicted values being unspecified in the natural language text and describing a feature associated with the item as produced, the generating comprising:
determining a set of possible predicted values for the first missing item description attribute and a set of possible predicted values for the second missing item description attribute;
assigning a probability to each possible predicted value; and
selecting the predicted value for the first missing item description attribute and the predicted value for the second missing item description attribute based on the respective predicted value having a highest probability in the set of possible predicted values;
causing presentation of a listing creation form that displays an attribute-predicted value pair corresponding to the first missing item description attribute having the predicted value for the first missing item description attribute, an approve icon to approve the attribute-predicted value pair, and a decline icon to decline the attribute-predicted value pair;
based in part on an indication of a selection of the approve icon, updating the probability of each possible predicted value of the set of possible predicted values for the second missing item description attribute and selecting a new predicted value for the second missing item description attribute based on the updated probability;
generating the listing comprising at least the predicted value for the first missing item description attribute; and
causing presentation, via the user interface associated with the online marketplace, of the listing comprising at least the predicted value for the first missing item description attribute.