Google patents system to save screen parts using AI grouping

1. A computing system, the system comprising: one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising: obtaining, via an overlay interface at the operating system level of a user computing device, content provided for display, wherein the content comprises a plurality of different visual features, wherein the overlay interface is configured to obtain content across a plurality of different applications provided by the user computing device; obtaining, via the overlay interface, a user input, wherein the user input is descriptive of a selection of a sub-portion of the content, wherein the sub-portion of the content comprises at least a subset of visual features of the plurality of visual features; generating a selected content dataset, wherein the selected content dataset comprises visual data and source data, wherein the visual data is descriptive of particular visual features associated with the sub-portion of the content, and wherein the source data is descriptive of a source of the content; processing the selected content dataset with a generative model to determine a content grouping for the selected content dataset, wherein the content grouping is descriptive of one or more other content snippets determined to be associated with the selected content dataset; and storing the selected content dataset with the content grouping.