Service Data Prediction Accuracy via Abnormal Scenario Influence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional service data prediction methods have low accuracy due to the inability to effectively account for abnormal scenarios, leading to unreliable future service data predictions.
Innovation Solution
A service data processing method that involves acquiring historical service data, determining a historical cycle, obtaining comparative service data, calculating service data differences, and assessing abnormal scenario influence values to improve prediction accuracy by incorporating these influences into the prediction model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional service data prediction methods are used, then the prediction process is simple, but the prediction accuracy is low
Solution Approach 1:
The patent segments the service data into normal data and abnormal data based on deviation from expected patterns. The prediction process is divided into multiple stages: acquiring historical service data, identifying abnormal scenarios, calculating influence values, and generating predictions. This segmentation allows the system to handle complex data patterns systematically while improving accuracy without overwhelming complexity.
Solution Approach 2:
The patent performs preliminary actions by pre-identifying abnormal scenarios and calculating their influence values before generating the final prediction. The system proactively identifies deviations from expected service patterns and quantifies their impact, allowing the prediction model to incorporate these factors in advance. This preliminary analysis of abnormal conditions enables more accurate predictions while maintaining a structured, manageable process.
2Reliability
If historical service data is analyzed without considering abnormal scenarios, then the analysis process is simple, but the prediction reliability is low
Solution Approach 1:
The patent applies local quality by treating abnormal data points differently from normal data. Instead of uniform processing, the system identifies specific abnormal scenarios (such as service outages, data corruption, or pattern deviations) and assigns them special influence values. This localized attention to problematic areas allows the system to improve reliability by addressing specific reliability issues without processing every data point with equal complexity.
Solution Approach 2:
The patent introduces an intermediary mechanism in the form of influence value calculations that mediate between raw historical data and final predictions. The system calculates influence values as intermediate representations that capture the impact of abnormal scenarios, then uses these intermediaries to adjust predictions. This intermediary layer simplifies the overall process by transforming complex abnormal data patterns into manageable influence factors that can be systematically applied to predictions.
Data Source
AI summary
A service data processing method includes: acquiring a historical service data sequence of historical service data arranged in chronological order; determining a historical cycle to which the historical service data belongs, acquiring a reference service data sequence in a reference cycle corresponding to the historical cycle, and obtaining first comparative service data based on the reference service data sequence; acquiring a first service data difference between the historical service data and the first comparative service data; acquiring a reference data difference, and determining abnormal scenario influence values corresponding to the historical service data based on the first service data difference and the reference data difference; arranging the abnormal scenario influence values corresponding to the historical service data in chronological order to obtain a scenario influence value sequence; and determining target service data based on the historical service data sequence and the scenario influence value sequence.