一种结合直方图与元学习的基数估计方法及系统

By combining histograms and meta-learning methods, and employing feature extraction and adaptive encoding, the bias problem of database cardinality estimation in complex query scenarios is solved, achieving fast and accurate cardinality estimation, reducing training costs, and improving the adaptability and versatility of the model.

CN117909845BActive Publication Date: 2026-07-17SHANDONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANDONG UNIV
Filing Date
2024-01-17
Publication Date
2026-07-17

Smart Images

  • Figure CN117909845B_ABST
    Figure CN117909845B_ABST
Patent Text Reader

Abstract

本发明提出了一种结合直方图与元学习的基数估计方法及系统，涉及数据库查询优化的基数估计领域，对待估计的SQL语句进行特征提取和自适应编码，得到特征向量；将特征向量输入到训练好的多元决策器，输出直方图、元学习两种方法的适配概率，选择适配概率高的方法进行基数估计，得到最终的基数估计值；本发明将直方图与元学习方法结合，融合直方图方法“估得快”与学习方法“估得准”的优点，从精度、性能两方面综合优化基数估计方法；同时利用元学习方法训练基数估计器模型，将其与数据库基数估计方法结合，创新元学习应用场景的同时，也使得基数估计器能够适应不同的查询场景，提高估计器的通用性，节省训练的时间成本。
Need to check novelty before this filing date? Find Prior Art