MICROSOFT TECHNOLOGY LICENSING, LLC (20240256418). EFFICIENT SINGLE USER METRIC USAGE FOR HIGH PRECISION SERVICE INCIDENT DETECTION simplified abstract
Contents
EFFICIENT SINGLE USER METRIC USAGE FOR HIGH PRECISION SERVICE INCIDENT DETECTION
Organization Name
MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s)
Myriam Titon of Jerusalem (IL)
Izhak Mashiah of Qirya Ono (IL)
Yosef Asaf Levi of Tel Aviv (IL)
EFFICIENT SINGLE USER METRIC USAGE FOR HIGH PRECISION SERVICE INCIDENT DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240256418 titled 'EFFICIENT SINGLE USER METRIC USAGE FOR HIGH PRECISION SERVICE INCIDENT DETECTION
Simplified Explanation: The patent application describes a system for detecting service incidents in a cloud computing platform using anomaly detection and supervised learning techniques.
- Key Features and Innovation:
* Utilizes unsupervised anomaly detection to identify anomalies in user metrics related to service calls. * Trains a supervised learning classifier to filter and classify anomaly detection results based on anomaly scores. * Learns features from anomaly scores at different resolution levels to improve incident detection accuracy.
- Potential Applications:
* Cloud service providers can use this technology to proactively detect and address service incidents. * Enterprises relying on cloud services can benefit from improved incident detection and resolution.
- Problems Solved:
* Enhances the efficiency of detecting service incidents in a cloud computing environment. * Provides a more accurate and automated method for identifying anomalies in user metrics.
- Benefits:
* Early detection of service incidents leads to faster resolution and improved service reliability. * Reduces downtime and potential disruptions for cloud service users.
- Commercial Applications:
* Title: Cloud Service Incident Detection System * This technology can be applied in various industries such as e-commerce, healthcare, and finance to ensure uninterrupted service delivery. * Market Implications: Increased customer satisfaction and loyalty due to proactive incident detection and resolution.
- Prior Art:
Prior research in anomaly detection and supervised learning techniques in cloud computing environments may provide insights into similar approaches.
- Frequently Updated Research:
Stay updated on advancements in anomaly detection algorithms and supervised learning models for cloud service incident detection.
- Questions about Cloud Service Incident Detection:
* What are the key benefits of using anomaly detection in cloud service incident detection? * How does supervised learning improve the accuracy of incident classification in cloud computing platforms?
Original Abstract Submitted
systems and methods for service incident detection in a cloud computing platform. according to an example implementation, the incident detection system retrieves a single user metric corresponding to a service call to a resource on which the service is dependent and uses unsupervised anomaly detection to detect anomalies indicative of a service incident. detected anomalies include an anomaly score indicating a level of anomality. additionally, a supervised learning classifier is trained and used to filter/classify the anomaly detection results based on features corresponding to the anomaly score. the features are learned based on characteristic dimensions, distribution, and statistics of anomaly scores of the user metric at different resolution/aggregation levels. anomaly detection results are classified as an incident or not an incident. a report is generated for a determined incident.