본문 바로가기
  • Home

A Similarity-Based Framework for Goal-Aware Sequential Action Recommendation: Unifying Rule-Based Logic and Semantic Vector Space

  • Journal of Software Forensics
  • Abbr : JSF
  • 2026, 22(2), pp.205~215
  • DOI : 10.29056/jsf.2026.06.18
  • Publisher : Korea Software Assessment and Valuation Society
  • Research Area : Engineering > Computer Science
  • Received : June 5, 2026
  • Accepted : June 20, 2026
  • Published : June 30, 2026

Jeong Yon Shim 1

1강남대학교

Accredited

ABSTRACT

Goal-oriented planning and recommendation systems are essential in personalized decision support across diverse domains. This paper presents a novel similarity-based framework that leverages a rule-based planner for automatic generation of Goal-Aware Sequential Recommendation. The framework mathematically formalizes goal, action, and context representations as vectors, enabling effective similarity computations to guide planning decisions. We focus on the student personal education domain to demonstrate how the system adapts learning plans to individual profiles and goals. Comprehensive simulation results highlight the effectiveness and flexibility of the approach, showcasing improved plan relevance and learner satisfaction.

Citation status

* References for papers published after 2024 are currently being built.