Software Categorization via Knowledge Graph and Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing software platforms face challenges in categorizing software applications accurately, especially those downloaded directly from creators, as they often lack clear categories or are inaccurately classified, leading to difficulties in controlling access and time usage for users, particularly in family settings.
Innovation Solution
A system utilizing machine learning and knowledge graph techniques to determine the category of software applications based on features such as names, descriptions, and images, with a trained model generating categories and confidence scores, enabling controlled access and time usage management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If software applications are categorized manually, then categorization accuracy may be maintained for some applications, but productivity decreases due to the time-consuming nature of manual classification
Solution Approach 1:
The patent replaces manual mechanical categorization with an automated machine learning system. The ML model analyzes application features (names, descriptions, images) to automatically determine categories, eliminating the need for manual classification while maintaining or improving accuracy through consistent feature-based analysis.
Solution Approach 2:
The system enables applications to be self-categorized by automatically analyzing their own features and metadata. The ML model processes application information without human intervention, allowing the system to serve itself in the categorization task and significantly improving processing throughput.
2Ease of operation
If software applications downloaded directly from creators are used, then ease of operation improves for users, but reliability of category information deteriorates as these applications lack clear categories or have inaccurate classifications
Solution Approach 1:
The patent introduces a machine learning-based categorization system as an intermediary between applications and users. This intermediary automatically analyzes application features and assigns reliable categories, bridging the gap between easily accessible applications and accurate category information without requiring manual verification.
Solution Approach 2:
The system performs preliminary categorization analysis automatically when applications are downloaded or registered. By pre-processing and categorizing applications before user access, the system ensures that category information is reliable and ready for immediate use in access control decisions, eliminating the need for subsequent manual categorization.
3Object-affected harmful factors
If family accounts with access control features are implemented, then protection from inappropriate content is improved, but device complexity increases due to the need for categorization systems and access management
Solution Approach 1:
The patent changes the parameter of category determination from manual input to automated machine learning-based classification. This parameter change simplifies the system by replacing complex manual configuration interfaces with automated analysis, reducing the burden on users while maintaining comprehensive access control capabilities.
Data Source
AI summary
Methods and systems are provided for determining the category of a software application utilizing machine learning (ML) and knowledge graph techniques, and for controlling access to the application by a user based on the category and configured time restrictions for the user. The system includes a feature set extractor and a category predictor with a trained ML model. The trained ML model generates the category of the application based on a feature(s) of the application. The generated category is indicated in a data structure. An access request handler receives a request related to access to the application from a user device. A category determiner determines the category of the application from the data structure. A time usage manager determines an available time usage for the category and the specified user. The access arbiter responds to the request from the user device with the available time usage.