Patent · US Active

Methods and apparatus for recommending computer program updates utilizing a trained model

US11003444B2 · kind B2 · utility

4Cited by
0References
25Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 28, 2019
Grant dateMay 11, 2021
Priority date
Expiry dateJul 19, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N7/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An apparatus includes a software parser to generate a plurality of abstract syntax trees based on a plurality of software files, the ASTs including subtrees corresponding to a plurality of functions of the software files, a subtree encoder to generate a plurality of code vectors representative of one or more semantic properties of the subtrees, a function identifier to determine a plurality of clusters for the subtrees and assign a cluster identifier and a function label to the subtrees, a tree database to store the subtrees and map the plurality of subtrees to respective ones of cluster identifiers and function names, and a processor to: train a model based on a feature vector and the plurality of clusters stored in the tree database and predict the cluster identifier for the subtrees, based on the trained model, to identify a name of the function.

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