Test bed design from customer system configurations using machine learning techniques

摘要

Designing a test bed for testing a computer product includes (1) obtaining customer configuration data describing different system configurations in which the computer product is used, (2) preprocessing the customer configuration data to generate structured customer configuration, (3) applying a classification to the structured customer configuration data to separate the distinct system configurations into groupings according to similarity in one or more of the system attributes among members of each group, and (4) for each grouping, identifying a representative system configuration to be used for testing and generating a corresponding set of test bed definition data describing the representative system configuration to enable implementation. The classification may employ clustering analysis, and supplementary and/or backup techniques may be included.