17962078. MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS - 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 Original Abstract Submitted
MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Prerana Dharmesh Gambhir of San Jose CA (US)
Sharena Meena Pari-monasch of Union City CA (US)
Khoa Dang Nguyen of Murphy TX (US)
Yiming Shi of Milpitas CA (US)
Yongchang Dong of San Jose CA (US)
MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17962078 titled 'MACHINE LEARNING FOR IDENTIFYING IDLE SESSIONS
Simplified Explanation
The abstract describes systems and methods for identifying and evicting idle sessions in a cloud-based service using a machine learning model trained to classify active sessions. The model receives parameters related to active sessions, applies rules to classify them, and outputs the classification. Idle sessions classified by the model can then be evicted from the service.
- Machine learning model trained to classify active sessions
- Receives parameters related to active sessions as input
- Applies rules to determine classification of active sessions
- Outputs classification for each active session
- Utilized in cloud-based service to classify active sessions
- Evicts idle sessions based on classification
Potential Applications
The technology can be applied in various cloud-based services to efficiently manage and optimize resources by identifying and evicting idle sessions.
Problems Solved
1. Efficient resource management in cloud-based services 2. Reduction of unnecessary load on servers due to idle sessions
Benefits
1. Improved performance and resource utilization 2. Cost savings by eliminating unnecessary sessions 3. Enhanced user experience through better service availability
Potential Commercial Applications
Optimizing cloud-based services in industries such as e-commerce, SaaS, and online gaming to enhance user experience and reduce operational costs.
Possible Prior Art
Prior art may include similar systems and methods for session management in cloud-based services, but specific details would need to be researched to identify any relevant prior art.
Unanswered Questions
How does the machine learning model handle different types of sessions with varying parameters?
The machine learning model is trained to classify active sessions based on a variety of parameters, but it is unclear how it handles sessions with different characteristics and how it adapts to new types of sessions.
What measures are in place to ensure the accuracy and reliability of the classification output for active sessions?
It is important to understand the validation process and quality control mechanisms implemented to ensure that the classification output for active sessions is accurate and reliable.
Original Abstract Submitted
Systems and methods for identifying and evicting idle sessions include training a machine learning model as a session classifying model to learn rules for classifying active sessions between clients and the cloud-based service. The session classifying model is trained to receive a plurality of parameters pertaining to the document associated with an active session as input and to apply the rules to the plurality of parameters to determine a classification for the active session and to provide an output indicative of the classification for the active session. The session classifying model is then utilized in the cloud-based service to classify the active sessions. The active sessions classified as idle sessions may then be evicted from the cloud-based service.
