US 12,273,312 B2
Systems and methods for detecting offensive content in a single responsive message
Trisha N. Prabhu, Naperville, IL (US)
Filed by Trisha N. Prabhu, Naperville, IL (US)
Filed on Mar. 29, 2024, as Appl. No. 18/622,061.
Application 18/622,061 is a continuation of application No. 17/900,866, filed on Aug. 31, 2022.
Application 17/900,866 is a continuation in part of application No. 17/393,540, filed on Aug. 4, 2021, granted, now 11,706,176, issued on Jul. 18, 2023.
Application 17/393,540 is a continuation of application No. 16/372,140, filed on Apr. 1, 2019, granted, now 11,095,585, issued on Aug. 17, 2021.
Application 16/372,140 is a continuation of application No. 15/187,674, filed on Jun. 20, 2016, granted, now 10,250,538, issued on Apr. 2, 2019.
Application 15/187,674 is a continuation in part of application No. 14/738,874, filed on Jun. 13, 2015, granted, now 9,686,217, issued on Jun. 20, 2017.
Claims priority of provisional application 62/012,296, filed on Jun. 14, 2014.
Prior Publication US 2024/0244021 A1, Jul. 18, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 51/063 (2022.01); G06F 3/04817 (2022.01); G06F 3/04842 (2022.01); H04L 51/046 (2022.01); H04L 51/212 (2022.01); H04L 51/52 (2022.01)
CPC H04L 51/212 (2022.05) [G06F 3/04817 (2013.01); G06F 3/04842 (2013.01); H04L 51/046 (2013.01); H04L 51/063 (2013.01); H04L 51/52 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A method for identifying and deleting offensive message content shared using an application comprising:
obtaining, by one or more computer, content of a responsive message that is received, by the one or more computer, after an initial message provided by a user device, wherein the responsive message includes content that is a response to content of the initial message;
providing, by the one or more computer, content of the responsive message as an input to a machine learning model that has been trained to predict a likelihood that an initial message includes offensive content based on processing of responsive message content from a message that was provided in response to the initial message;
processing, by the one or more computer, the obtained content of the responsive message through the machine learning model to generate output data indicating a likelihood that the initial message includes offensive content;
determining, by the one or more computer and based on the generated output data, whether the initial message likely includes offensive content; and
based on a determination, by the one or more computer, that the generated output data indicates that the initial message likely includes offensive content:
generating, by the one or more computer, notification data that, when processed by the user device, causes the user device to display a plurality of selectable options, wherein the plurality of selectable options includes a first selectable option prompting the user to delete the initial message and a second selectable option prompting the user to not delete the initial message;
transmitting, by the one or more computer, to the generated notification data to the user device;
receiving, by the one or more computer, data corresponding to a selection of the first selectable option; and
in response to receiving data corresponding to a selection of the first selectable option, deleting, by the one or more computer, the initial message, wherein deleting the initial message prevents further viewing of the initial message using the application.