US 11,750,897 B2
Generating sequential visual narratives
Nir Betan, Toronto (CA); Rebecca Eva Rose, Toronto (CA); and Brodie Hanbuch, Toronto (CA)
Assigned to STUDEO REALTY MARKETING INC., Markham (CA)
Appl. No. 16/645,401
Filed by STUDEO REALTY MARKETING INC., Toronto (CA)
PCT Filed Sep. 6, 2018, PCT No. PCT/IB2018/056817
§ 371(c)(1), (2) Date Mar. 6, 2020,
PCT Pub. No. WO2019/049068, PCT Pub. Date Mar. 14, 2019.
Claims priority of provisional application 62/555,376, filed on Sep. 7, 2017.
Prior Publication US 2020/0286130 A1, Sep. 10, 2020
Int. Cl. H04N 21/85 (2011.01); H04N 21/854 (2011.01); G06N 20/00 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06Q 30/0241 (2023.01); H04N 21/234 (2011.01); H04N 21/81 (2011.01); H04N 21/8549 (2011.01); G06F 18/24 (2023.01)
CPC H04N 21/854 (2013.01) [G06F 18/24 (2023.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06Q 30/0276 (2013.01); H04N 21/23418 (2013.01); H04N 21/812 (2013.01); H04N 21/8133 (2013.01); H04N 21/8549 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A system for generating a sequential visual narrative, comprising:
a processor;
a communications interface connected to the processor;
a memory connected to the processor, the memory to store instructions that are executable by the processor;
a media analyzer including instructions executable by the processor, the media analyzer to obtain media and descriptive data, the descriptive data pertaining to a subject of which a sequential visual narrative is to be generated, the media including at least first and second media units pertaining to the subject, and to categorize the first and second media units into narrative categories of a predetermined set of narrative categories;
a description generator including instructions executable by the processor, the description generator to process the descriptive data and the narrative categories of the first and second media units to generate a first natural language text description describing the subject in relation to one or both of the first media unit and the second media unit, wherein the first natural language text description includes a textual narrative of the descriptive data;
a visual display generator including instructions executable by the processor, the visual display generator to sequence the first and second media units in a narrative sequence, map the narrative sequence to a display layout, and to generate and output a visual display including the first natural language text description in visual association with one or both of the first and second media units in accordance with the display layout, wherein the description generator cooperates with the visual display generator to generate the first natural language text description; and
instructions to train a machine learning model to interpret usage of a plurality of devices that are operable to connect to the system via the communications interface;
wherein the visual display generator dynamically generates the narrative sequence, including determining a relative ordering of the first and second media units in the narrative sequence, using the machine learning model that is trained to interpret usage of the plurality of devices that are operable to connect to the system via the communications interface, wherein the narrative sequence is generated as specific to a user's device that connects to the system via the communications interface to receive output of generate the visual display.