ML-Based Condition Identification in Rules Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying legal actions or risks within rules-based systems, such as legal systems, require substantial human involvement and are costly, time-consuming, and pose information security risks due to the need for merging and transferring sensitive data across insecure networks.
Innovation Solution
A computer-implemented method using machine learning to identify conditions in a rules-based system by processing data elements into a graph data structure, evaluating them against predefined conditions, and outputting alerts, which includes pseudonymizing entity identifiers to maintain security and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human review and data merging methods are used to identify legal actions or risks, then identification accuracy can be maintained, but the process becomes costly, time-consuming, and creates information security risks
Solution Approach 1:
The patent replaces manual human review processes with an automated machine learning system that processes data elements through trained models. The system substitutes human analysts with computational algorithms that can rapidly evaluate data against learned patterns, maintaining identification accuracy while dramatically reducing processing time and eliminating the need for manual data merging across insecure networks
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw data and legal action identification. This intermediary processes data elements through trained representations, enabling automated decision-making that replicates human analytical capabilities without requiring actual human involvement or secure data transfer, thus resolving the contradiction between accuracy and efficiency
2Measurement precision
If human review and data merging methods are used to identify legal actions or risks, then identification accuracy can be maintained, but information security risks increase due to transferring sensitive data across insecure networks
Solution Approach 1:
The patent introduces a machine learning model as an intermediary that processes data locally without requiring transfer across insecure networks. The model learns from training data and then operates independently to evaluate new data elements, eliminating the security vulnerability of transferring sensitive information while maintaining identification accuracy through the learned representations
Solution Approach 2:
The patent creates a computational copy of human analytical capabilities through trained machine learning models. Instead of moving actual sensitive data across networks for human review, the system replicates the decision-making process in a secure, automated form that operates on local data, thus maintaining accuracy while eliminating information security risks associated with data transfer
3Productivity
If machine learning models are used to identify conditions in rules-based systems, then processing speed and cost-effectiveness improve, but the models may amplify biases and produce incorrect outputs based on statistical probability rather than relational reasoning
Solution Approach 1:
The patent changes the operational parameters of machine learning by integrating it with rules-based systems. The model outputs are not final decisions but rather inputs to rule-based evaluation, changing how the system processes information from purely statistical to a hybrid approach that maintains reliability while preserving processing speed advantages
Solution Approach 2:
The patent positions the machine learning model as an intermediary that generates probabilistic assessments, which then feed into a rules-based system for final determination. This intermediary role allows the ML model to provide speed advantages while the rules-based layer ensures reliability by applying logical reasoning and relational constraints to the model's outputs
4Reliability
If traditional methods are used to identify legal actions or risks, then information security can be maintained through controlled data access, but substantial human involvement increases costs and reduces efficiency
Solution Approach 1:
The patent replaces manual human review processes with automated machine learning systems that inherently maintain security by processing data locally without requiring transfer or sharing. This substitution eliminates the need for controlled data access protocols while dramatically improving processing efficiency, as automated systems can handle volumes of data that would be prohibitively expensive to review manually
Data Source
AI summary
A computing system and method for machine learning-based identification of a condition defined in a rules-based system are provided. A method includes receiving data elements extracted from a record. The method includes processing the data elements, including identifying in the data elements features including one or more of: an entity; a relationship between the entity and another entity; and, attributes of the relationship. A state data structure is compiled based on the entity, relationship and attributes of the relationship identified in the data elements. The state data structure represents the relationship between the entity and another entity. The state data structure is evaluated for occurrence of a condition defined in a rules-based system, including continually or periodically receiving further data elements and evaluating the further data elements against the state data structure for occurrence of the condition. An alert is output when the occurrence is identified or approximated.