Collaborative Decision System Using Dynamic Knowledge Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing decision-making systems struggle to handle complex, dynamic scenarios with multiple factors, conflicting goals, and uncertainty, often resulting in inefficient and risky outcomes due to their inability to adapt to changing conditions and incorporate human perspectives effectively.
Innovation Solution
A system and method for collaborative decision-making that uses deep learning, reinforcement learning, and artificial intelligence to calculate intermediate steps, establish decision-making flows, generate and modify decision spaces, and create knowledge graphs, while integrating human agent validation to select decisions in dynamically changing environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional decision-making systems are used, then simplicity and ease of operation are maintained, but the ability to handle complex dynamic scenarios and adapt to changing conditions deteriorates
Solution Approach 1:
The decision-making system is segmented into multiple specialized modules: a decision space generation module that creates possible decisions, a decision knowledge graph module that stores relationships, a reinforcement learning module that evaluates decisions, and a human agent integration module. Each module handles specific aspects of the complex decision-making process, allowing the system to manage complexity through functional decomposition while maintaining high adaptability to dynamic scenarios.
Solution Approach 2:
The system implements dynamic decision spaces that are continuously updated based on changing environmental conditions and new information. The decision knowledge graph is dynamically modified as new relationships are discovered, and the reinforcement learning model adapts its policies in real-time. This dynamic nature enables the system to handle complex scenarios where conditions change over time while the modular architecture manages the resulting complexity.
2Productivity
If automated decision-making is implemented, then processing speed and productivity are improved, but the ability to comprehend real-life situations and arrive at accurate conclusions deteriorates
Solution Approach 1:
The system introduces a decision knowledge graph as an intermediary structure that bridges automated processing and accurate real-life comprehension. The knowledge graph stores structured relationships between entities, attributes, and decisions, enabling the system to process information quickly while maintaining contextual understanding. Human agents also serve as intermediaries, validating and refining automated decisions to ensure accuracy in complex real-life scenarios.
Solution Approach 2:
The reinforcement learning component implements continuous feedback loops where decisions are evaluated based on their outcomes, and this feedback is used to improve future decision-making. The system learns from past decisions and adjusts its policies accordingly, maintaining high processing speed while improving accuracy over time through iterative learning from real-life outcomes.
3Reliability
If human agents are involved in decision validation, then decision accuracy and reliability are improved, but the time required for decision-making increases
Solution Approach 1:
The system applies partial human involvement rather than requiring full human validation for all decisions. Human agents review and validate only critical decisions or those flagged by the reinforcement learning model as requiring human judgment. For routine or low-risk decisions, the automated system operates independently, maintaining high reliability for critical decisions while minimizing time loss through selective human engagement.
4Measurement precision
If the system processes all available data, then measurement precision and decision accuracy are improved, but the loss of time due to data processing increases
Solution Approach 1:
The system extracts and processes only the most relevant features and data elements needed for decision-making rather than processing all available data. The decision space generation module identifies key attributes and entities, and the reinforcement learning model focuses on evaluating decisions based on critical factors. This selective extraction maintains high measurement precision for decision-relevant data while reducing overall processing time by excluding unnecessary information.
Data Source
AI summary
Disclosed is a system and a method for collaborative decision making in dynamically changing environment. A query corresponding to a problem is received from a user. Further, one or more intermediate steps required to reach a decision is calculated based on metadata associated to the problem. A decision-making flow is established for the one or more intermediate steps required to reach the decision. It may be noted that the decision-making flow corresponds to a sequence for execution of the one or more intermediate steps. Further, a decision space comprising one or more decision options is generated. The decision space is dynamically modified based on one or more uncertain events. A decision knowledge graph depicting modifications in the decision space is generated. Further, the decision space and the decision knowledge graph are updated. Finally, the decision is selected based on the updated decision knowledge graph and the updated decision space.