Microsoft technology licensing, llc (20240134972). OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS simplified abstract
Contents
- 1 OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
Organization Name
microsoft technology licensing, llc
Inventor(s)
Laurent Boue of Peteh Tikva (IL)
OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240134972 titled 'OPTIMIZING INTELLIGENT THRESHOLD ENGINES IN MACHINE LEARNING OPERATIONS SYSTEMS
Simplified Explanation
The abstract of the patent application describes a machine learning model based on extreme value theory (EVT) that identifies anomalous data samples by generating outlier scores and comparing them to a threshold determined by a risk factor.
- Machine learning model based on extreme value theory (EVT) mechanism
- Threshold determined by the ML model based on a risk factor
- Outlier score generated for the sample
- Comparison of outlier score to the threshold to identify anomalies
- Schema updated based on investigation results
Potential Applications
This technology could be applied in various industries such as finance, cybersecurity, and healthcare for detecting anomalies in data sets.
Problems Solved
1. Efficient identification of anomalous data samples 2. Improved risk assessment based on outlier detection
Benefits
1. Enhanced data security 2. Early detection of potential risks 3. Automation of anomaly detection process
Potential Commercial Applications
"Anomaly Detection Technology for Enhanced Data Security"
Possible Prior Art
There are existing anomaly detection methods based on statistical analysis and machine learning algorithms, but the specific combination of EVT mechanism and risk factor threshold determination may be novel.
Unanswered Questions
How does the EVT mechanism improve anomaly detection compared to traditional methods?
The abstract mentions the use of an extreme value theory (EVT) mechanism in the machine learning model, but it does not provide specific details on how this mechanism enhances anomaly detection.
What types of anomalies can be effectively detected using this technology?
While the abstract describes the process of identifying anomalous data samples, it does not specify the range or types of anomalies that can be effectively detected using this technology.
Original Abstract Submitted
a sample of data, including a risk factor, is selected by a machine learning (ml) model of an extreme value theory (evt) mechanism. a threshold is determined by the ml model based on the risk factor, an outlier score is generated for the sample, and the outlier score is compared to the threshold. the sample is identified as anomalous based on the generated outlier score being greater than the threshold. a schema comprising results of an investigation into the sample and the risk factor is updated based on the received schema.
