Graph Data Block Scheduling via Precomputed Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large graphs need to be divided into subgraphs for storage, leading to reduced graph calculation performance due to low graph data scheduling efficiency.
Innovation Solution
A graph data processing method that acquires target graph data, compiles statistics to divide it into graph data blocks, determines boundary values and weights for each block, and stores these values in memory to schedule the graph data during calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Volume of stationary object
If large graph data is divided into multiple subgraphs for storage, then storage space is saved, but graph calculation performance deteriorates due to low scheduling efficiency
Solution Approach 1:
The patent pre-calculates and stores boundary values and weights for each graph data block during the data preparation phase. These pre-computed scheduling parameters enable the system to quickly identify and retrieve required subgraphs during calculation without performing complex scheduling operations at runtime, thus resolving the contradiction between storage efficiency and calculation performance
Solution Approach 2:
The patent implements a self-service scheduling mechanism where each graph data block contains its own boundary value and weight information. During calculation, the system can independently determine which blocks to schedule based on these embedded metadata without requiring centralized coordination or complex scheduling algorithms, improving both scheduling efficiency and calculation performance
2Ease of manufacture
If graph data is divided into subgraphs, then storage management becomes easier, but scheduling time increases
Solution Approach 1:
Boundary values and weights are pre-calculated and stored with each graph data block during the data preparation phase. This preliminary action eliminates the need for complex scheduling computations at runtime, reducing scheduling time while maintaining easy storage management through the use of these pre-computed parameters
3Device complexity
If traditional graph data division methods are used, then implementation is simple, but scheduling accuracy is low
Solution Approach 1:
The patent introduces two key parameters - boundary values and weights - to characterize each graph data block. These parameter changes transform the simple division approach into a more sophisticated scheduling system where boundary values enable precise block identification and weights provide scheduling priorities, significantly improving scheduling accuracy while maintaining reasonable implementation complexity
Data Source
AI summary
A graph data processing method includes: acquiring target graph data to be processed; compiling statistics on the target graph data according to a first preset rule, so as to divide the target graph data into a plurality of graph data blocks and determine a boundary value and weight of each of the plurality of graph data blocks; and storing the boundary value and weight of each of the plurality of graph data blocks in a corresponding memory according to a second preset rule, so as to schedule the target graph data during a graph calculation process by use of the boundary values and the weights.