Patent · US Active

Method and system for process identification using data mining

US12242569B1 · kind B1 · utility

0Cited by
6References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 19, 2019
Grant dateMar 4, 2025
Priority date
Expiry dateNov 30, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06Q40/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for identifying a process includes storing formatted data, generating aggregated traces by preprocessing the formatted data, encoding each of the aggregated traces using a respective atomic word, generating a subset of aggregated traces by compressing the aggregated traces, clustering the subset of aggregated traces, and labeling the clusters. A system includes a processor and a memory including instructions that when executed cause the system to store formatted data, generate traces, encode the traces to an atomic word, generate a subset traces, cluster the subset traces, and label the clusters. A non-transitory computer readable medium containing program instructions that when executed, cause a computer system to store formatted data, generate traces, encode the traces to an atomic word, generate a subset traces, cluster the subset traces, and label the clusters.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.