Digital twin based systems and methods for business continuity plan and safe return to workplace

A system, comprising:

• a memory storing instructions;
• one or more communication interfaces;
• and
• one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
• receive an input data comprising epidemiological data of a population in one or more locations;
• model an instance of a stock and flow model for each of the one or more locations based on a plurality of employees and one or more offices of an organization associated with the one or more locations to obtain one or more instances of location specific stock and flow models;
• calculate, by the one or more instances of location specific stock and flow models, one or more location specific susceptible to exposure (s2e) rates, wherein the susceptible to exposure (s2e) rate of the one or more locations is calculated from a probability of contact and a learnable variable;
• apply, a statistical decay function, on the one or more location specific susceptible to exposure (s2e) rates and converting the one or more location specific s2e rates to one or more organization specific s2e rates to obtain one or more organization specific location wise s2e rates, wherein each of the one or more organization specific s2e rates corresponds to a specific location amongst the one or more locations, and wherein the one or more organization specific location wise s2e rates comprises differences in demographic characteristics, health profile related features, and pandemic specific behaviour of the plurality of employees of the organization and the one or more associated dependents;
• create at least one of (a) an employee-based digital twin based on (i) the epidemiological data, (ii) a demographic and health profile related features for the plurality of employees of the organization and the one or more associated dependents, (iii) the one or more organization specific location wise s2e rates, and (b) an office-based digital twin based on (i) the epidemiological data, (ii) the demographic and health profile related features for the plurality of employees of the organization and the one or more associated dependents, (iii) an office and infrastructure data, and (iv) the one or more organization specific location wise s2e rates, wherein the employee-based digital twin and the office-based digital twin are created by modeling information pertaining to employees comprising at least an age, a gender, one or more comorbidities, a vaccine status, dependents data, the one or more offices, one or more employee associated project details, one or more desks within one or more offices, and one or more facilities within the one or more offices, wherein the employee-based digital twin comprises a first set of Key Performance Indicators (KPIs) with an associated initial value, and wherein the office-based digital twin comprises a second set of Key Performance Indicators (KPIs) with an associated initial value, wherein the first set of KPIs and the second set of KPIs are encoded and projected as a part of a simulation dashboard;
• identify an updated value of a corresponding KPI comprised in the at least one of the first set of Key Performance Indicators (KPIs) and the second set of Key Performance Indicators (KPIs) based on a simulation of the at least one of the employee-based digital twin and the office-based digital twin respectively, wherein the updated value of a corresponding KPI comprised in the at least one of the first set of Key Performance Indicators (KPIs) and the second set of Key Performance Indicators (KPIs) is indicative of infection of one or more employees and dependents being predicted at one or more aggregation levels of the one or more offices of the organization, wherein the updated value for each KPI comprised in the first set of KPIs and the second set of KPIs is identified by:
• creating, the one or more employees and the one or more dependents as a plurality of agents in the agent-based fine-grained model (ABM) comprised in the employee-based digital twin and the office-based digital twin respectively;
• instantiating, the plurality of agents and an environment of the ABM, using data comprising the epidemiological data, the demographic, project and health profile related features for the plurality of employees of the organization and the one or more associated dependents, the office and infrastructure data and the one or more organization specific location wise s2e rates respectively;
• assigning, a specific comorbid for the plurality of agents in the ABM, using a probability distribution technique, obtained from a geography specific age wise and gender wise co-morbidity distribution of the data, wherein in the employee-based digital twin and the office-based digital twin, random movement behavior of the one or more employees is modelled and impact of infection due to movement within (i) one or more residences (ii) the one or more offices, and (iii) one or more public places captured using the one or more organization specific location wise s2e rates;
• simulating the ABM for interaction of the plurality of agents with each other and with the environment according to a specified behavior leading to an infection, wherein during the simulation of the ABM, one or more states and behaviors are modified using one or more interventions applied at one or more time stamps, wherein the fine-grained agent-based model represents employee and support staff as agents and allow the employee and the support staff to visit offices to simulate candidate WFO strategies, wherein the fine-grained agent-based model defines varied fine-grained intervention including varied occupancies on a specific date for all or specific office, opening/closing facilities in a specific office, and restricting occupancies within varied facilities;
• and
• identifying the updated value for each KPI comprised in at least one of the first set of KPIs and the second set of KPIs from the simulated ABM, wherein the updated value of the first set of KPIs and the second set of KPIs correspond to one or more infection results reported at the one or more aggregation levels;
• identifying an infection trend due to a variant on a geography following scenario of an earlier prediction with 2-3 weeks delay in an infection surge;
• and
• providing a hybrid modelling and simulation approach combining an agent-based fine-grained model (ABM) and a coarse-grained stock-and-flow model, and leverages past macro-level data pertaining to pandemic evolution in cities, states, and countries amenable for collective analysis.

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause a method for business continuity plan and safe return to workplace by:

• receiving an input data comprising epidemiological data of a population in one or more locations;
• modelling an instance of a stock and flow model for each of the one or more locations based on a plurality of employees and one or more offices of an organization associated with the one or more locations to obtain one or more instances of location specific stock and flow models;
• calculating, by the one or more instances of location specific stock and flow models, one or more location specific susceptible to exposure (s2e) rates, wherein the susceptible to exposure (s2e) rate of the one or more locations is calculated from a probability of contact and a learnable variable;
• applying, a statistical decay function, on the one or more location specific susceptible to exposure (s2e) rates and converting the one or more location specific s2e rates to one or more organization specific s2e rates to obtain one or more organization specific location wise s2e rates, wherein each of the one or more organization specific s2e rates corresponds to a specific location amongst the one or more locations, and wherein the one or more organization specific location wise s2e rates comprises differences in demographic characteristics, health profile related features, and pandemic specific behaviour of the plurality of employees of the organization and the one or more associated dependents;
• creating at least one of (a) an employee-based digital twin based on (i) the epidemiological data, (ii) a demographic and health profile related features for the plurality of employees of the organization and the one or more associated dependents, (iii) the one or more organization specific location wise s2e rates, and (b) an office-based digital twin based on (i) the epidemiological data, (ii) the demographic and health profile related features for the plurality of employees of the organization and the one or more associated dependents, (iii) an office and infrastructure data, and (iv) the one or more organization specific location wise s2e rates, wherein the employee-based digital twin and the office-based digital twin are created by modeling information pertaining to employees comprising at least an age, a gender, one or more comorbidities, a vaccine status, dependents data, the one or more offices, one or more employee associated project details, one or more desks within one or more offices, and one or more facilities within the one or more offices, wherein the employee-based digital twin comprises a first set of Key Performance Indicators (KPIs) with an associated initial value, and wherein the office-based digital twin comprises a second set of Key Performance Indicators (KPIs) with an associated initial value, wherein the first set of KPIs and the second set of KPIs are encoded and projected as a part of a simulation dashboard;
• and
• identifying an updated value of a corresponding KPI comprised in the at least one of the first set of Key Performance Indicators (KPIs) and the second set of Key Performance Indicators (KPIs) based on a simulation of the at least one of the employee-based digital twin and the office-based digital twin respectively, wherein the updated value of a corresponding KPI comprised in the at least one of the first set of Key Performance Indicators (KPIs) and the second set of Key Performance Indicators (KPIs) is indicative of infection of one or more employees and dependents being predicted at one or more aggregation levels of the one or more offices of the organization, wherein the step of identifying the updated value for each KPI comprised in the first set of KPIs and the second set of KPIs comprises:
• creating, the one or more employees and the one or more dependents as a plurality of agents in the agent-based fine-grained model (ABM) comprised in the employee-based digital twin and the office-based digital twin respectively;
• instantiating, the plurality of agents and an environment of the ABM, using data comprising the epidemiological data, the demographic, project and health profile related features for the plurality of employees of the organization and the one or more associated dependents, the office and infrastructure data and the one or more organization specific location wise s2e rates respectively;
• assigning, a specific comorbid for the plurality of agents in the ABM, using a probability distribution technique, obtained from a geography specific age wise and gender wise co-morbidity distribution of the data, wherein in the employee-based digital twin and the office-based digital twin, random movement behavior of the one or more employees is modelled and impact of infection due to movement within (i) one or more residences (ii) the one or more offices, and (iii) one or more public places captured using the one or more organization specific location wise s2e rates;
• simulating the ABM for interaction of the plurality of agents with each other and with the environment according to a specified behavior leading to an infection, wherein during the simulation of the ABM, one or more states and behaviors are modified using one or more interventions applied at one or more time stamps, wherein the fine-grained agent-based model represents employee and support staff as agents and allow the employee and the support staff to visit offices to simulate candidate WFO strategies, wherein the fine-grained agent-based model defines varied fine-grained intervention including varied occupancies on a specific date for all or specific office, opening/closing facilities in a specific office, and restricting occupancies within varied facilities;
• identifying the updated value for each KPI comprised in at least one of the first set of KPIs and the second set of KPIs from the simulated ABM, wherein the updated value of the first set of KPIs and the second set of KPIs correspond to one or more infection results reported at the one or more aggregation levels;
• identifying an infection trend due to a variant on a geography following scenario of an earlier prediction with 2-3 weeks delay in an infection surge;
• and
• providing a hybrid modelling and simulation approach combining an agent-based fine-grained model (ABM) and a coarse-grained stock-and-flow model, and leverages past macro-level data pertaining to pandemic evolution in cities, states, and countries amenable for collective analysis.