Grouped Data Comparison for Reliable Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting anomalies in data sets are prone to human error, lack standardization, and are inefficient due to the overwhelming quantity of data entries, leading to high false positives and false negatives, and inaccurate performance metrics.
Innovation Solution
A centralized system that groups data entries based on shared selection criteria, uses machine learning models to identify anomalies, and generates performance metrics, reducing computational load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional manual methods are used to detect anomalies in data entries, then reviewers can examine data entries, but the process is slow, error-prone, and cannot accurately detect anomalies due to human error and inability to comprehensively analyze various relevant data entries
Solution Approach 1:
The patent replaces the manual mechanical review process with an automated computer-based system that uses algorithms to access, group, and analyze data entries. This substitution eliminates human error while maintaining high processing speed, allowing comprehensive analysis of multiple relevant data entries simultaneously to accurately detect anomalies.
2Reliability
If reviewers manually group and compare data entries to detect anomalies, then some analysis can be performed, but the large quantity of data entries makes the process overwhelming and cumbersome
Solution Approach 1:
The patent automatically segments and groups data entries based on shared characteristics and relationships, organizing large volumes of data into manageable groups that can be systematically analyzed. This automated segmentation reduces the complexity of the analysis process while ensuring comprehensive coverage of all relevant data entries for reliable anomaly detection.
3Ease of operation
If manual methods are used to analyze data entries, then reviewers can provide performance metrics, but the variability of values and information across data entries makes it challenging to develop standardized techniques
Solution Approach 1:
The patent transforms unstructured variable data into standardized formats by automatically normalizing values and information across different data entries. This parameter transformation enables consistent application of analysis rules and algorithms, making the data analysis process standardized while maintaining the ability to accurately measure and compare performance metrics across diverse data sets.
Data Source
AI summary
A computer-implemented method of accessing, by one or more processors, database tables that include a first row storing a first set of data that includes selection criteria values and first data values and a second row storing a second set of data that includes the selection criteria values and second data values. After determining the first and second sets of data share the selection criteria, the method groups the first and second row to generate a grouped row that indicates a comparison of data based on certain data formats. The method iteratively performs the grouping across the database tables to generate a plurality of grouped rows which are incremented by a counter value to reflect the total number of grouped rows. The method generates a performance metric based on the counter value incremented.