US 11,886,803 B1
Assistive digital form authoring
Arneh Jain, Calicut (IN); Salil Taneja, Noida (IN); Puneet Mangla, Faridabad (IN); and Gaurav Ahuja, Delhi (IN)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Jan. 12, 2023, as Appl. No. 18/153,595.
Int. Cl. G06F 17/00 (2019.01); G06F 40/174 (2020.01); G06F 40/40 (2020.01)
CPC G06F 40/174 (2020.01) [G06F 40/40 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processing device, form data describing a plurality of different digital forms;
identifying, by the processing device, based on the form data, a plurality of candidate search outputs for a plurality of search inputs;
generating, by the processing device, a group of candidate embedding vectors in a latent space corresponding to the plurality of candidate search outputs, the generating performed using a machine learning model;
receiving, by the processing device, input data describing a subsequent search input associated with a digital form;
generating, by the processing device, an input embedding vector that represents the subsequent search input in the latent space using the machine learning model;
identifying, by the processing device, a candidate embedding vector included in the group of candidate embedding vectors based on a distance between the input embedding vector and the identified candidate embedding vector in the latent space; and
generating, by the processing device, an indication of a search output associated with the digital form for display in a user interface based on the identified candidate embedding vector.