US 12,288,034 B2
Automatically summarizing event-related data using artificial intelligence techniques
Bijan Kumar Mohanty, Austin, TX (US); Gregory Michael Ramsey, Seattle, WA (US); and Hung T. Dinh, Austin, TX (US)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jul. 27, 2022, as Appl. No. 17/874,755.
Prior Publication US 2024/0037316 A1, Feb. 1, 2024
Int. Cl. G06F 40/30 (2020.01); G06F 40/10 (2020.01); G06F 40/279 (2020.01); G06F 40/58 (2020.01); G06N 3/08 (2023.01); G10L 13/02 (2013.01)
CPC G06F 40/30 (2020.01) [G06F 40/10 (2020.01); G06F 40/279 (2020.01); G06F 40/58 (2020.01); G06N 3/08 (2013.01); G10L 13/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining text-based data and non-text-based data associated with at least one virtual event comprising one or more participants, wherein obtaining text-based data and non-text-based data comprises converting at least a portion of the non-text-based data to at least a portion of the text-based data by converting at least a portion of at least one image, corresponding to presentation materials within the at least one virtual event, to text using at least one mask region-based convolutional neural network (mask R-CNN) model in connection with one or more segmentation techniques, wherein the at least one mask R-CNN model comprises a multi-task network trained to predict at least one text localization output and at least one text recognition output from a same portion of the at least one image;
generating a content-related summarization of one or more of at least a portion of the text-based data and at least a portion of the non-text-based data using at least a first set of one or more artificial intelligence techniques;
generating a participant sentiment-related summarization associated with one or more of at least a portion of the text-based data and at least a portion of the non-text-based data using at least a second set of one or more artificial intelligence techniques; and
performing one or more automated actions based at least in part on one or more of the content-related summarization and the participant sentiment-related summarization;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.