Streaming App Resource Tuning Using ML Component Shutdown

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Streaming devices experience performance degradation due to resource contention from multiple applications running simultaneously, leading to delays, diminished video clarity, and system failures, which users often cannot manage efficiently without technical knowledge.

Innovation Solution

Implementing machine learning models to dynamically disable software components on streaming devices based on user preferences and device specifications, recommending and closing unnecessary applications and features to optimize performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple applications run simultaneously on streaming devices, then user functionality and versatility are improved, but device performance degrades due to resource contention

Engineering Contradiction:

ImprovefunctionalityVSAvoiddevice performance

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system automatically manages software components by detecting streaming application launches and dynamically closing unnecessary applications without user intervention. The machine learning model continuously monitors device state and autonomously makes decisions about which applications to close, enabling the device to self-optimize performance while maintaining versatility.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes the operational state of software components dynamically based on detected conditions. When a streaming application is detected, the system changes the state of other applications from running to closed, adjusting the resource allocation parameters to prioritize streaming performance while maintaining the ability to run multiple applications.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If users manually manage applications to optimize performance, then device performance is improved, but ease of operation deteriorates due to technical complexity

Engineering Contradiction:

Improvedevice performanceVSAvoiduser operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system eliminates the need for user intervention in application management by automatically detecting streaming application launches and closing unnecessary applications. The machine learning model processes device state information and autonomously executes optimization decisions, transforming a complex manual task into an automated self-service process.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The machine learning model acts as an intermediary between the user and the application management system. Instead of users directly managing applications, the ML model mediates by monitoring device state, predicting optimal application sets, and automatically executing closure decisions, simplifying the user experience while maintaining performance optimization.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If the system automatically closes software components, then device performance is improved, but adaptability deteriorates due to reduced application availability

Engineering Contradiction:

Improvedevice performanceVSAvoidapplication availability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts application availability based on real-time conditions. Rather than permanently closing applications, the system temporarily closes non-streaming applications when streaming is detected, and can reopen them when streaming ends. This dynamic behavior maintains performance during critical moments while preserving adaptability through conditional application availability.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the availability parameter of applications conditionally based on detected streaming state. Applications transition between available and closed states dynamically, allowing the system to optimize performance during streaming while maintaining application availability during non-streaming periods, thus balancing performance and adaptability.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250350804A1Machine learning based performance tuning of streaming devices

Publication Date: 2025.11.13 DISH NETWORK LLC

AI summary

Described herein are systems, methods, and media for managing streaming devices using machine learning models. In an embodiment, a method of managing streaming devices includes detecting that a streaming application is launched on a streaming device; recommending a set of software components for the streaming device, wherein the set of recommended software components includes the streaming application; determining a set of software components that are actually running on the streaming device; and closing at least one of the software components that are actually running but not in the set of recommended software components.