Data processing method and device

Abstract

The embodiment of the invention provides a data processing method and device, and the method comprises the steps: determining an evaluation score of initial data in an initial data set; determining initial seed data from the initial data according to the evaluation score; performing variation on parameter values of parameters in the initial seed data according to preset variables to obtain updated data after variation; determining a preset processing strategy according to the update data and the initial seed data, and determining target seed data and a target variable according to the preset processing strategy; and determining target data according to the target seed data and the target variable. According to the data processing method, the number of times that a certain seed participates in variation is limited by introducing a preset variable, and operation of a'false optimization 'seed blocking algorithm is avoided; and the optimal target seed data is continuously selected as the initial seed data of the next iteration according to a preset processing strategy to carry out parameter tuning, so that the parameter tuning efficiency and the parameter tuning effect are improved.

Description

technical field [0001] The embodiment of this specification relates to the field of computer technology, in particular to a data processing method. Background technology [0002] The operating system kernel, compiler, database and other scenarios all have tuning requirements for parameters. More effective parameter settings can optimize the service performance and improve the overall service quality. However, the above fields involve a large number of parameters, which may be as high as hundreds of dimensions. [0003] At present, both traditional parameter tuning methods often rely on experienced engineers to manually tune according to domain knowledge; However, high-dimensional parameters bring great challenges to manual tuning, which may not only lead to low efficiency of parameter tuning, but also affect the effect of parameter tuning. summary of the invention [0004] In view of this example, this specification provides a data processing method. One or more embodiments of t...

AI Technical Summary

Problems solved by technology

However, the above-mentioned fields involve a large number of parameters, which may be as high as hundreds or even thousands of dimensions.

[0003] At present, both traditional parameter tuning methods often rely on experienced engineers to perform manual tuning based on domain knowledge; however, high-dimensional parameters bring great challenges to manual tuning, which may not only lead to low efficiency of parameter tuning, but also affect Parameter tuning effect

Images