top of page

Digital Transformation with Information Digital Twins

We are information architects. We provide Information and Human Digital Twins to automate and optimize complex decisions in a variety of domains such as healthcare, logistics, human wellbeing or human-machine teaming.

We Offer our Services from


How to Start-The Information Digital Twin Prototype


A prototype is the most straightforward approach to assess the usefulness of a new technology. The prototype in the case of an Information Digital Twin, IDT/Human Digital Twin, HDT is an information model (the Information Heat Map, IHM) that enables the basic functions of a digital twin: anticipate performance deviation and suggest potential corrective actions.

A prototype of Patient-HDT, for example, would provide an early assessment of a patient's health condition, patient-specific health risks and potential treatment options, which could then be forwarded to the patient's physician to shorten the anamnesis time and improve diagnostic and treatment quality.

A digital twins-enabled Human-Machine Team (HMT) prototype would create the elements of an HMT Platform that mimics an online game environment in which team members communicate with one another and complete tasks using their HDT/IDT as their avatars. 

A Shipment-DT prototype, for example, would forecast shipment progress, potential delays, or cost variances and recommend remedial actions to maintain delivery windows.

As shown in the preceding example, an IDT/HDT prototype illustrates the practicality of the IDT/HDT ideas in specific instances. The true synergy, however, is obtained by using IDTs/HDTs across an entire population (patients with various conditions and needs, or all shipments across a supply chain.) which necessitates the introduction of Digital Twin Platforms that enables multiple, dependent smart scenarios.

From Strategy to Digital Twin Platforms


Services Overview
Feasibility studies and Transformation Strategy to evaluate the value and impact of deploying Information/Human Digital Twins (IDT/HDT) to support specific procedures or operations.
2. An information architecture that depicts how data can be delivered, managed, and analyzed to enable and integrate IDTs/HDTs in complex environments.
3. The core applications, algorithms, and methodologies necessary to enable IDTs/HDTs, their incorporation into Social AI Platforms and their continuous adaptation and learning.


Information Digital Twins Feasibility


Because digital twins (DT) are still a relatively new technology, we start by assisting our customers in answering a few basic questions to enable informed transformation strategy definition. For instance:

- Are DT the best technology for our transformation goals?

- What value can we expect from DT?

- Do we have the right data to support DT?

- Do we have the infrastructure to deploy and sustain DT?

- What are the change management implications?

This evaluation is provided as a short report, without obligation as it also helps us better understand our customers and their domains.

AI Scenario Design

Digital Twins-Based Transformation Strategy

Deliverables, DT-Transformation Strategy, Scenario architecture, Scenario events and events' supporting parameters

Social Scenarios

Digital transformation can be done in many ways, but using digital twins (DT) to digitize operations need to be based on scenarios. That is, the area that needs to be digitalized must first be described in terms of different specific scenarios. Then, one or more digital twins are used to support the various scenarios. This is necessary to ensure effectiveness and scalability of the approach. 

From the point of view of AI, identifying scenarios makes it much easier to learn the patterns and regularities that any AI solution needs to work effectively.


  • Accordingly, our first step is to define an initial DT-Transformation strategy scope, expected value and required governance. ​

  • Define the scenarios within the scope. 

  • For each scenario in scope, identify the events to be managed by the digital twins. (See the Shipment Digital Twin or the Human-Machine Teaming use cases as examples for scenario designs)

  • Define the parameters/data relevant to each event, their sources and access/transformation requirements. 

The DT-Transformation strategy provides structured insights necessary for effective decisions-making regarding transformation feasibility, expected value, involved effort and project structure.

Defining and scoping the "right" scenarios and events to digitize and automate remains an art we have mastered over many years of expertise in architecting and integrating complex enterprise and business intelligence solutions

Scenario Information Model

 Deliverables, Scenario information architecture, Information Heat Map (IHM)

Reference Events Model (REM)

After defining a scenario or a use case to be enabled and automated by digital twins, and once the events in scope have been identified, the next step is to develop a Information Heat Map (IHM), which captures and represents the scenario parameters (Supply Chain Example). Depending on the number of events in a scenario and the related parameters, the IHM can be defined in a table-based environment (Excel, Sheets, or a small database).


However, IHMs representing multiple scenarios are defined in a business intelligence environment (BI) as multidimensional information cubes. 


Once the parameters' historical data is uploaded according to the IHM data structure, the significance of each parameter in predicting the scenario desired outcomes are then provided and used to calculate the best course of action to achieve the scenario objective. 

Information Design
Learning & Optimization

Information Digital Twins-Based Sceanrio Optimization

Deliverables, Deployed scenarios in the Social AI Platform with necessary Information Digital Twins

Big Data Blue.png

As illustrated in the detailed use cases, scenario events (e.g., specific illness risk, child abuse, shipment delay, or human casualty events) result from the interactions of hundreds of parameters over an extended time period.


The learning and optimization phase is thus focused on learning the patterns of interaction between the numerous parameters that affect an event and rely on them to enhance the event prediction and optimize the scenario performance by manipulating the identified patterns. This step relies heavily on machine learning to derive knowledge from the IHM, the numerous IDTs and their overall interactions with the platform.

Information Digital Twins-Based Automation

Deliverables, Automated social AI scenarios

Decision automation

After identifying and optimizing the many interaction patterns underlying the various events, the final step in maturing the Social AI Platform is to automate some of the decisions required to improve a scenario's outcome, or minimize risk events occurrences.


The logic for decision automation is implemented across the various IDTs. Once an IDT identifies an event of interest and based on the IDT's user-specific interaction patterns, the IDT provides a recommendation or initiates an action to raise or decrease the likelihood of that event according to the user's preferences and the scenario's objective.

Decision Automation
bottom of page