Patent · US Active

Code review comment generation via retrieval-augmented transformer with chunk cross-attention

US12169715B2 · kind B2 · utility

1Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 5, 2022
Grant dateDec 17, 2024
Priority date
Expiry dateFeb 9, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0985
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A retrieval-augmented neural transformer model with chunk cross-attention predicts a code review given a proposed source code change, represented as a code diff hunk, and a set of historical code review comments. The code diff hunk represents proposed edits to a source code snippet with its surrounding context that has not been changed. The historical code review comments are associated with code edits that are semantically similar to the proposed source code changes. The code diff hunk is partitioned into chunks which are used to find semantically similar historical code review comments. The set of historical code review comments is aggregated and used to guide the model in makings its predictions.

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