US 12,106,860 B1
Systems and methods for regulating provision of messages with content from disparate sources based on risk and feedback data
Sudheer Guttikonda, Edison, NJ (US); William Morse, New York, NY (US); Chuanhan Qiu, New York, NY (US); and Austin Speier, Brooklyn, NY (US)
Assigned to Click Therapeutics, Inc., New York, NY (US)
Filed by Click Therapeutics, Inc., New York, NY (US)
Filed on Oct. 9, 2023, as Appl. No. 18/377,905.
Int. Cl. G16H 50/30 (2018.01); G16H 20/10 (2018.01); G16H 20/70 (2018.01); G16H 50/20 (2018.01)
CPC G16H 50/30 (2018.01) [G16H 20/10 (2018.01); G16H 20/70 (2018.01); G16H 50/20 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A system for configuring generation of digital therapeutic content for provision, comprising:
one or more processors coupled with memory, configured to:
receive, via a user interface, a text input including one or more parameters identifying an audience for which digital therapeutic content is to be generated and at least one domain of a plurality of domains with which to test the digital therapeutic content for validation, the plurality of domains comprising a medical domain and a regulatory domain;
identify a plurality of content items, each content item generated by a respective generative transformer model of a plurality of generative transformer models using a prompt that is created based on the text input;
select, from a plurality of validation models for the plurality of domains, a a validation model corresponding to the at least one domain;
apply the validation model to each content item of the plurality of content items to determine a corresponding score indicating a degree of validity associated with the at least one domain;
select, from the plurality of content items, a content item generated by a generative transformer model of the plurality of generative transformer models, responsive to the corresponding score of the content item satisfying a threshold;
present, via the user interface, the content item including the respective digital therapeutic content;
receive, via the user interface, a response identifying at least a portion of the content item to be modified; and
provide feedback data generated using the response to update at least one of the validation model or the generative transformer model.