Crowd Flow Motifs for Data Traffic Prediction Without History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data traffic prediction methods in telecommunication networks rely heavily on historical data, making it difficult to predict network traffic accurately in areas lacking sufficient historical data, and existing methods struggle with low accuracy and dependence on subjective experience or high data requirements.
Innovation Solution
Perform traffic autonomous zone division based on geographic information and crowd flow data to identify sub-areas, determine crowd flow motifs and features, and use a pre-trained prediction model to forecast data traffic, independent of historical data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data traffic prediction is performed based on historical traffic data using time sequence rules, then prediction can be conducted in areas with sufficient historical data, but prediction cannot be performed in areas lacking historical traffic data
Solution Approach 1:
The patent introduces crowd flow data as an intermediary element that mediates between geographic information and traffic prediction. By using crowd flow motifs extracted from crowd flow data as a bridge, the system can predict traffic in areas without historical traffic data, thus resolving the contradiction between prediction reliability and adaptability to new areas
Solution Approach 2:
The patent changes the input parameters from historical traffic data to crowd flow data and geographic information. By extracting crowd flow motifs as new feature parameters, the system enables prediction in areas without historical traffic data while maintaining prediction capability through alternative parameter representations
2Measurement precision
If traffic prediction relies on accumulation of high-quality historical traffic data, then prediction accuracy can be maintained in areas with sufficient data, but the method becomes ineffective for areas without historical data
Solution Approach 1:
The patent performs preliminary extraction of crowd flow motifs from crowd flow data before traffic prediction. By pre-processing crowd flow data to extract meaningful motion patterns, the system eliminates the need for historical traffic data accumulation while maintaining prediction accuracy through pre-extracted feature representations
Solution Approach 2:
The patent substitutes the mechanical data accumulation process with a computational approach using crowd flow motif extraction. Instead of mechanically accumulating historical traffic data, the system uses algorithmic extraction of crowd flow patterns from crowd flow data, replacing data accumulation with intelligent feature extraction
3Ease of manufacture
If conventional traffic prediction methods are used, then existing infrastructure can be utilized, but the methods require subjective experience and high data requirements leading to low accuracy
Solution Approach 1:
The patent enables the system to automatically extract crowd flow motifs and generate prediction models without requiring subjective human expertise. The automated extraction of crowd flow patterns from crowd flow data allows the system to serve itself, eliminating dependence on expert knowledge while improving prediction accuracy through objective data-driven features
Data Source
AI summary
A traffic prediction method includes performing traffic autonomous zone division on a to-be-predicted geographic area based on geographic information data of the geographic area and crowd flow data of the geographic area to obtain a plurality of sub-areas; determining, for any sub-area, a crowd flow motif in the sub-area based on geographic information data of the sub-area and crowd flow data of the sub-area, where the crowd flow motif indicates a multi-point crowd motion pattern in the sub-area; determining a crowd flow feature of the sub-area based on the crowd flow motif; and predicting data traffic of the sub-area based on the crowd flow feature of the sub-area to obtain a data traffic prediction result of the sub-area.