Flexible Keyword-Aware Top-$k$ Route Search
By: Ziqiang Yu , Xiaohui Yu , Yueting Chen and more
Potential Business Impact:
Plans better trips by understanding your wishes.
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.
Similar Papers
Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agents
Artificial Intelligence
Finds best routes from your spoken requests.
Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethics
Machine Learning (CS)
Chooses the best AI for each job.
Revisiting Task-Oriented Dataset Search in the Era of Large Language Models: Challenges, Benchmark, and Solution
Databases
Finds the right data for science projects faster.