Application Prediction Model for Preloading Optimization

Solution Overview

Problem

Current methods for preloading applications on smart terminals are inaccurate, leading to excessive resource usage and increased power consumption, which affects the smoothness of the terminal's performance due to ignorance of association, time, and status information.

Innovation Solution

A method for establishing an application prediction model that collects and analyzes usage sequences and status information to train a machine learning model, predicting which applications will be launched next and optimizing resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If applications are preloaded in advance to improve launch speed, then application launch time is reduced, but storage space occupation and power consumption increase

Engineering Contradiction:

Improveapplication launch timeVSAvoidpower consumption

Core Design Contradiction:

Loss of timeVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by preloading applications in advance based on predicted user behavior patterns. The machine learning model analyzes historical usage data, time information, and status information to predict which applications the user is likely to launch next, then preloads those applications before they are actually needed, achieving fast launch times without loading unnecessary applications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts preloading parameters based on changing conditions. The machine learning model continuously updates its predictions by analyzing new usage patterns, time of day, device status, and other parameters. This allows the system to adapt the preloading strategy to current conditions, optimizing the balance between launch speed and resource consumption.

Inventive Principle:

Principle #35Parameter changes

2Loss of time

If applications are preloaded in advance to improve launch speed, then application launch time is reduced, but storage space occupation increases

Engineering Contradiction:

Improveapplication launch timeVSAvoidstorage space

Core Design Contradiction:

Loss of timeVSQuantity of substance

Solution Approach 1:

The system performs preliminary actions by preloading applications in advance based on predicted user behavior patterns. The machine learning model analyzes historical usage data, time information, and status information to predict which applications the user is likely to launch next, then preloads those applications before they are actually needed, achieving fast launch times without loading unnecessary applications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts preloading parameters based on changing conditions. The machine learning model continuously updates its predictions by analyzing new usage patterns, time of day, device status, and other parameters. This allows the system to adapt the preloading strategy to current conditions, optimizing the balance between launch speed and resource consumption.

Inventive Principle:

Principle #35Parameter changes

3Loss of time

If random applications are preloaded to reduce launch time, then some applications may launch faster, but terminal smoothness deteriorates due to excessive resource usage

Engineering Contradiction:

Improveapplication launch timeVSAvoidterminal smoothness

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system performs preliminary actions by preloading applications in advance based on predicted user behavior patterns. The machine learning model analyzes historical usage data, time information, and status information to predict which applications the user is likely to launch next, then preloads those applications before they are actually needed, achieving fast launch times without loading unnecessary applications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where the machine learning model continuously learns from actual user behavior to improve its predictions. By monitoring whether predicted applications are actually launched and adjusting the model accordingly, the system refines its predictions over time, improving accuracy and reducing unnecessary preloading that would harm terminal smoothness.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11442747B2Method for establishing applications-to-be preloaded prediction model based on preorder usage sequence of foreground application, storage medium, and terminal

Publication Date: 2022.09.13 NOKIA TECHNOLOGIES OY

AI summary

A method for establishing an application prediction model, a storage medium, and a terminal are provided. The method includes the following. In response to an operation switching an application previously running in the foreground to a first application currently running, a first preorder usage sequence of the first application currently running is collected as sample usage information. Applications launched within a time-window are monitored, and a preset number of applications launched first in the applications launched within the time-window are set as sample labels for the sample usage information. A predetermined machine learning model is trained based on the sample usage information and the sample labels for the sample usage information, to obtain the application prediction model.