Abstract: Provided is a computer-implemented method to find similar sets to a selected query set within a collection of sets, wherein each set represents a process. Each set is transformed to a representation in a vector space. Moreover, each set comprises a prefix. The method comprises creating and storing a data structure representing an inverted metric index in a storage device. The similar sets to the selected query set are identified by a probing step followed by a candidate verifying step. In the probing step, the inverted metric index is filtered by means of a predefined subspace of the vector space. In the candidate verifying step, each set of the filtered inverted metric index is identified as a similar set if its distance value is smaller or equal to a predefined distance threshold value.

Abstract: Provided is a computer-implemented method to find similar sets to a selected query set within a collection of sets, wherein each set represents a process. Each set is transformed to a representation in a vector space. Moreover, each set comprises a prefix. The method comprises creating and storing a data structure representing an inverted metric index in a storage device. The similar sets to the selected query set are identified by a probing step followed by a candidate verifying step. In the probing step, the inverted metric index is filtered by means of a predefined subspace of the vector space. In the candidate verifying step, each set of the filtered inverted metric index is identified as a similar set if its distance value is smaller or equal to a predefined distance threshold value.