SRU Neural Network Application Preloading for Terminal Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing application preloading methods on terminal devices are inefficient due to the lack of consideration for application usage association and timing information, leading to inaccurate predictions and increased resource usage, which affects user experience and power consumption.

Innovation Solution

A method utilizing a simple recurrent unit (SRU) neural network model to establish an application predictive model based on usage timing association records, allowing for the preloading of applications that are likely to be used next by analyzing historical usage patterns and filtering out invalid records to optimize resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If more applications are preloaded in advance, then application availability and user experience are improved, but storage space consumption and power consumption increase

Engineering Contradiction:

Improveapplication availabilityVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary action by predicting which applications will be needed in the future and preloading only those specific applications before the user actually needs them. The SRU neural network model analyzes historical usage patterns and timing information to forecast future application usage, allowing the system to prepare only the necessary applications in advance rather than preloading all applications indiscriminately.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter of preloading strategy from static (preloading all applications) to dynamic (preloading predicted applications based on usage patterns). By using the SRU model to process usage timing association records and generate probability values, the system adapts the preloading decisions based on actual user behavior patterns, thereby reducing unnecessary power consumption while maintaining application availability.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If more applications are preloaded in advance, then application availability is improved, but storage space consumption increases

Engineering Contradiction:

Improveapplication availabilityVSAvoidstorage space

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter of preloading strategy from static (preloading all applications) to dynamic (preloading predicted applications based on usage patterns). By using the SRU model to process usage timing association records and generate probability values, the system adapts the preloading decisions based on actual user behavior patterns, thereby reducing unnecessary storage space consumption while maintaining application availability.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If traditional preloading methods are used without considering usage timing association, then implementation simplicity is maintained, but prediction accuracy deteriorates

Engineering Contradiction:

Improveimplementation complexityVSAvoidprediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces simple mechanical preloading mechanisms with an intelligent prediction system based on the SRU neural network model. Instead of using basic rules or heuristics to determine what to preload, the system substitutes a machine learning-based approach that processes usage timing association records to generate accurate probability predictions, thereby significantly improving prediction accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The SRU neural network model acts as an intermediary between raw usage data and preloading decisions. It processes usage timing association records through multiple layers of computation, extracting meaningful patterns and generating probability values that guide the preloading process. This intermediary model enables accurate predictions while maintaining a relatively simple overall system architecture.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11042386B2Method for preloading application, terminal device, and medium

Publication Date: 2021.06.22 GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

AI summary

A method for preloading an application, a terminal device, and a medium are provided. The method for preloading an application includes the following. An application predictive model is obtained by training a simple recurrent unit (SRU) neural network model according to multiple groups of usage timing association records. Usage status information of applications of a terminal of at least two past time points of a next time point is acquired. Probability values of launching the applications are acquired from the application predictive model by processing the usage status information of the applications with the application predictive model. An application to-be-launched at the next time point is determined according to the probability values and the application to-be-launched is preloaded.