Google llc (20240305534). Scalable Mixed-Effect Modeling and Control simplified abstract
Contents
Scalable Mixed-Effect Modeling and Control
Organization Name
Inventor(s)
Ali Nasiri Amini of Redwood City CA (US)
Zheng Zhao of San Jose CA (US)
Di-Fa Chang of Cupertino CA (US)
Scalable Mixed-Effect Modeling and Control - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240305534 titled 'Scalable Mixed-Effect Modeling and Control
The present disclosure describes a method for analyzing session data in a networked environment using a mixed effects model.
- Obtaining session data descriptive of user sessions in the networked environment.
- Initializing a mixed effects model to describe first and second effects on the distribution of the session data.
- Optimizing a weighted objective over subsets of the session data, adjusting the contribution of the second effect with respect to the first effect.
- Updating the mixed effects model based on the optimized weighted objective.
Potential Applications: - This technology can be applied in analyzing user behavior in online platforms. - It can be used in optimizing network performance based on user session data.
Problems Solved: - Provides a method for analyzing complex session data in a networked environment. - Helps in understanding the impact of different effects on the distribution of session data.
Benefits: - Improved insights into user behavior in networked environments. - Enhanced optimization of network performance based on data analysis.
Commercial Applications: - This technology can be utilized by online platforms to enhance user experience and optimize network performance.
Questions about the technology: 1. How does the mixed effects model improve the analysis of session data in a networked environment? 2. What are the key advantages of optimizing a weighted objective over subsets of session data?
Original Abstract Submitted
in an example aspect, the present disclosure provides for an example method including obtaining session data descriptive of one or more user sessions in the networked environment; initializing a mixed effects model configured to describe a first effect and a second effect on a distribution of the session data; optimizing a weighted objective over a plurality of subsets of the session data, the weighted objective comprising a weighting parameter configured to adjust, respectively for the plurality of subsets of the session data, a contribution of the second effect with respect to the first effect; and updating the mixed effects model based on the optimized weighted objective.
