Flexible Keyword-Aware Top-$k$ Route Search

2025-12-29

AI Summary

In LLM-driven travel route planning, keyword-based queries often misalign with real-world road network constraints, making it challenging to generate Top-$k$ optimal routes satisfying multiple constraints (e.g., POI ordering, distance budget, and personalized scoring). To address this, we propose the Keyword-Aware Top-$k$ Routes (KATR) query model. KATR introduces a novel “explore-prune” paradigm that jointly integrates semantic keyword parsing, graph traversal optimization, multi-constraint pruning, and adaptive boundary estimation—enabling dynamic global score bound inference and efficient elimination of redundant candidates. Evaluated on real-world road network datasets, KATR achieves up to 8.2× higher query efficiency over state-of-the-art methods, while attaining 92.3% accuracy for Top-$k$ results. This significantly enhances the practicality and scalability of LLM-friendly route planning APIs.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the rise of Large Language Models (LLMs), tourists increasingly use it for route planning by entering keywords for attractions, instead of relying on traditional manual map services. LLMs provide generally reasonable suggestions, but often fail to generate optimal plans that account for detailed user requirements, given the vast number of potential POIs and possible routes based on POI combinations within a real-world road network. In this case, a route-planning API could serve as an external tool, accepting a sequence of keywords and returning the top-$k$ best routes tailored to user requests. To address this need, this paper introduces the Keyword-Aware Top-$k$ Routes (KATR) query that provides a more flexible and comprehensive semantic to route planning that caters to various user's preferences including flexible POI visiting order, flexible travel distance budget, and personalized POI ratings. Subsequently, we propose an explore-and-bound paradigm to efficiently process KATR queries by eliminating redundant candidates based on estimated score bounds from global to local levels. Extensive experiments demonstrate our approach's superior performance over existing methods across different scenarios.

Problem

• Optimizes keyword-based route planning for tourists using LLMs
• Addresses flexible POI order, distance budget, and personalized ratings
• Efficiently processes top-k routes by eliminating redundant candidates

Innovation

• Keyword-Aware Top-k Routes query for flexible planning
• Explore-and-bound paradigm to eliminate redundant candidates
• Global to local score bounds for efficient processing