Industry
Artificial Intelligence
Location
USA
Platform
Web
Cooperation
3+ years
About the project
This next-generation tool allows situational reasoning of application implementation. The software enables interactive design, specification, deployment, and ongoing maintenance of applications based on artificial neural networks. It focuses on the development of Cognitive Maps - frameworks able to leverage multiple technologies for data storage and manipulation, system modeling, and artificial intelligence. They are symbolic knowledge representations that fully support explainability through natural language interfaces.
Challenge
- To make the creation and managing of a cognitive map easy for the user on different devices.
- To make application architecture scalable and flexible for implementation of new features/different users’ requirements/systems.
- To make the creation and management of the decision table easy and clear for the user.
Solution
What helped us achieve the project goals: best practices for mind maps, user interfaces, and continuous integration; the usage of flexible app architecture solutions, development tools, and methodologies, rich preferences for customer personalization; best design practices for managing huge amounts of structured data.
Cognitive map
The creation and management of Cognitive Maps is a highly interactive task for users. Cognitive Maps evolve through feedback from visualizations that highlight relationships between goals and situations, show where the map needs to be expanded, changed, or reduced. Solution is designed to enable interactive creation with intuitive displays and ease-of-use features.
The Bayesian Network
The Bayesian Network (BN) user interface offers the following possibilities:
- Manual creation of BNs by creating Nodes and Links and entering BN Node/Link data.
- Automatic learning of a BN structure from user-supplied data (via CRex API).
- Automatic learning of BN node probability tables from user-supplied data (vis CRex API).
- Manual modification of the BN node structure, parameters (states, probability tables), and connections. In a Decision Table, use evaluation of a valid BN (via CRex API) to assess part of a Condition Clause and display the results of the evaluation.
Simulation Capabilities
When developing Cognitive Maps, users often simulate a running application so that they can examine the results and modify the Cognitive Map to achieve desired reasoning behavior. To do this, they use the Simulation capabilities that allow the user to do the following for a single complete and publishable Cognitive Map:
- Manual crea• Connect to a Microsoft SQL database containing data that are the inputs to a CRex application.tion of BNs by creating Nodes and Links and entering BN Node/Link data.
- Edit the input data.
- Visualize the results of the simulation in an embedded Microsoft Power BI display.
Technologies
React js
Redux
Styled components
.NET Core
SQL Server
Entity Framework
Business value
The solution merges the cognitive reasoning power of artificial intelligence, predictive analysis, and the performance of Big Data and cloud computing environments. The customers extensively use it for building their own high-level software across various industries, including gas and oil, finance, and government management.
Success!
We'll contact you very soon! Meanwhile, have a look at cooperation results with our clients and read their feedback on Clutch.
