US 11,948,694 B2
Controlling compartmental flows in epidemiological modeling based on mobility data
Vishrawas Gopalakrishnan, Cambridge, MA (US); Sayali Navalekar, Westford, MA (US); James H. Kaufman, San Jose, CA (US); Simone Bianco, San Francisco, CA (US); Kun Hu, Santa Clara, CA (US); Ajay Ashok Deshpande, Pleasantville, NY (US); Sarah Kefayati, San Francisco, CA (US); Ujwal Reddy Moramganti, Ashburn, VA (US); George Sirbu, Saline, MI (US); Xuan Liu, Yorktown Heights, NY (US); Raman Srinivasan, Plano, TX (US); and Pan Ding, New York, NY (US)
Filed by Merative US L.P., Ann Arbor, MI (US)
Filed on May 12, 2021, as Appl. No. 17/318,027.
Prior Publication US 2022/0367067 A1, Nov. 17, 2022
Int. Cl. G06Q 30/00 (2023.01); G06N 20/00 (2019.01); G16H 50/50 (2018.01); G16H 50/80 (2018.01)
CPC G16H 50/80 (2018.01) [G06N 20/00 (2019.01); G16H 50/50 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A method, in a data processing system comprising at least one processor and at least one memory coupled to the at least one processor and having instructions executed by the at least one processor to specifically configure the at least one processor to execute the method comprising:
performing machine learning training of an isolation rate prediction AI computer model to generate a trained isolation rate prediction AI model that predicts an isolation rate of a biological population;
receiving isolation data from one or more data source computing systems, wherein the isolation data comprises mobility data providing data indicating a measure of mobility of the biological population;
executing the trained isolation rate prediction AI model on input features extracted from the isolation data to generate a predicted isolation rate;
executing a compartmental epidemiological computer model comprising a plurality of compartments representing states of a population with regard to an infectious disease, to simulate a progression of the infectious disease; and
controlling, during execution of the compartmental epidemiological computer model, a flow of portions of the monitored population from at least one first compartment to at least one second compartment in the compartmental epidemiological computer model based on the predicted isolation rate.