Risk Behavior Recognition via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional risk monitoring systems for network behaviors face inefficiencies due to rule vulnerabilities and the resource-intensive nature of rule engines, leading to increased developer workload and computer system burden.
Innovation Solution
A method and apparatus that acquire user behavior data, determine a risk coefficient for specific behavior links through short-term, historical, and team risk calculations, and judge the riskiness of these links without manual rule remediation, thereby improving efficiency and reducing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a rule engine is used to monitor network behaviors, then risk identification capability is provided, but developer workload increases and efficiency decreases due to continuous rule updates
Solution Approach 1:
The system performs self-learning by automatically analyzing behavior data and generating risk rules without human intervention. The machine learning model continuously trains on new data, enabling the system to self-update and adapt to emerging risks, eliminating the need for developers to manually create and maintain rules.
Solution Approach 2:
The patent replaces the mechanical rule engine approach with a machine learning-based system. Instead of manually configuring and updating rules, the system uses algorithms to automatically learn patterns from behavior data, substituting human-driven rule creation with automated computational learning.
2Reliability
If a rule engine is deployed for risk monitoring, then behavior analysis is enabled, but computer system resources are consumed
Solution Approach 1:
The patent replaces the resource-intensive rule engine with a machine learning model that processes behavior data more efficiently. The learning model consolidates multiple rule evaluations into unified predictive computations, reducing the computational overhead and resource consumption while maintaining analysis capability.
3Reliability
If manual rule updates are performed to address rule vulnerabilities, then risk coverage is improved, but time consumption increases
Solution Approach 1:
The system automatically detects rule vulnerabilities and generates updated rules through continuous learning from behavior data. The machine learning model identifies emerging risk patterns and adapts the risk assessment model accordingly, eliminating manual rule updates and the time they consume.
Solution Approach 2:
The system performs preliminary learning and adaptation by continuously training on new behavior data before actual risk assessment is needed. This proactive approach ensures the model is already prepared to handle emerging risks, eliminating the need for reactive rule updates when vulnerabilities are discovered.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The present application discloses a method and an apparatus for identifying a risky behavior to solve the problem of low efficiency in the prior art caused by remedying a rule vulnerability during identification of a network behavior risk. The method includes: acquiring behavior data of a user; selecting a specific behavior link from the behavior data; determining a risk coefficient of the specific behavior link in the behavior data; and judging, according to the risk coefficient, whether the specific behavior link is risky.