US 12,354,150 B2
Systems and methods for ingesting task data from a browser for task facilitation services
Yoky Matsuoka, Los Altos Hills, CA (US); and Nitin Viswanathan, San Francisco, CA (US)
Assigned to Yohana LLC, Palo Alto, CA (US)
Filed by Yohana LLC, Palo Alto, CA (US)
Filed on Sep. 7, 2022, as Appl. No. 17/930,354.
Claims priority of provisional application 63/241,253, filed on Sep. 7, 2021.
Prior Publication US 2023/0076327 A1, Mar. 9, 2023
Int. Cl. G06Q 30/00 (2023.01); G06F 9/48 (2006.01); G06F 9/54 (2006.01); G06Q 10/1093 (2023.01); G06Q 30/0601 (2023.01); H04L 67/306 (2022.01); H04L 67/50 (2022.01)
CPC G06Q 30/0631 (2013.01) [G06F 9/4831 (2013.01); G06F 9/54 (2013.01); G06Q 10/1097 (2013.01); H04L 67/306 (2013.01); H04L 67/535 (2022.05)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving website data for a website from a browser executed on a user computing device associated with a user;
extracting multimedia content from the website data, wherein the multimedia content is extracted by performing a scraping or parsing operation on the website data;
accessing a task prediction model configured to identify tasks likely to be performed by or on behalf of the user;
processing the multimedia content to generate a task recommendation for a task of the user, wherein processing the multimedia content includes applying the task prediction model to the multimedia content to generate the task recommendation;
transmitting an indication corresponding to the task recommendation, wherein, when the indication is received by a computing device, the computing device is enabled to approve the task recommendation to generate a task corresponding to the task recommendation in a task facilitation service;
receiving interaction data indicating an approval or a rejection of the task recommendation; and
updating the task prediction model based on the interaction data, wherein the task prediction model is updated to improve accuracy in identifying future tasks that are likely to be performed by or on behalf of the user.