US 11,941,051 B1
System for performing programmatic operations using an image-based query language
Sundarrajan Raman, Chennai (IN)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Jun. 24, 2021, as Appl. No. 17/357,698.
Int. Cl. G06F 16/783 (2019.01); G06F 16/732 (2019.01); G06N 20/00 (2019.01); G06V 40/16 (2022.01)
CPC G06F 16/784 (2019.01) [G06F 16/7335 (2019.01); G06N 20/00 (2019.01); G06V 40/161 (2022.01); G06V 40/172 (2022.01); G06T 2207/30201 (2013.01); G06T 2207/30242 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system, comprising:
a computing device operable to execute a computing application, the computing device comprising a processor configured to generate a call in a programming language of the computing application, the call requesting a feature of videos stored in a media repository; and
a query system comprising:
a network interface configured to receive the call generated by the computing device; and
a processor communicatively coupled to the network interface and configured to:
determine a command associated with obtaining the feature requested by the call, wherein the determined command corresponds to an image analysis to perform on at least a portion of the stored videos in order to determine the requested feature;
determine, based at least in part on the determined command, an artificial intelligence model to execute on at least the portion of the stored videos;
determine, by executing the determined artificial intelligence model, a model output comprising the requested feature; and
provide, in the programming language of the computing application, an indication of the requested feature;
wherein:
the network interface is further configured to receive a video associated with the call generated by the computing device and a list of individuals anticipated to be appearing in the video;
the request for the feature comprises a request for a yes/no indication of whether each individual of the list of individuals appears in the video; and
the processor is further configured to:
determine the command as a face identification command;
determine the artificial intelligence model as a person identification model;
apply the person identification model to the received video, thereby determining identities of individuals appearing in the received video;
determine, for each individual of the list of individuals, whether the individual appears in the video by comparing the determined identities to the list of individuals; and
provide, in the programming language of the computing application, the yes/no indication of whether each individual of the list of individuals appears in the video.