Idea
Query suggestion platform improving local service search relevance and speed to boost user engagement and reduce no-result queries.
Research Paper
Core Innovation
This paper introduces LocalSUG, which integrates geographic grounding into LLM-based query suggestion via city-aware candidate mining. It addresses exposure bias with a beam-search-driven GRPO training aligned with inference and reduces latency through quality-aware beam acceleration and vocabulary pruning, outperforming traditional methods in real-world deployment.
Why It Matters
Local-life service platforms face challenges in providing relevant query suggestions due to geographic diversity and long-tail demand. Improving query suggestions reduces user effort and search time, enhancing user satisfaction and platform engagement. This solution scales across cities, addressing local preferences and business goals to optimize search outcomes.
Market Size (TAM)
$10–20B TAM for local and e-commerce search query suggestion platforms; $2–5B SAM from local-life service and e-commerce companies. Driven by increasing mobile search usage and demand for personalized local content.
Potential Customers & Pain Points
- Local-life service platforms – Need relevant fast query suggestions
- E-commerce platforms – Need to reduce search abandonment
- Search engine providers – Need to improve local query accuracy
- Mobile app developers – Need to enhance user search experience.
Business Model
SaaS or API subscription model targeting local-life service platforms and e-commerce companies, with tiered pricing based on query volume and customization level.
Competitive Landscape
- Google Autocomplete
- Bing Autosuggest
- Alibaba Query Suggestion
- Baidu Search Suggestion
Implementation Challenges
- Integration complexity with existing search infrastructure
- Balancing latency reduction with suggestion quality
- Maintaining geographic data accuracy and freshness
Validation Strategy
- Conduct large-scale A/B testing on partner local-life platforms
- Measure CTR improvement and reduction in no-result queries
- Collect user feedback on suggestion relevance and latency
- Iterate model and system optimizations based on real-world data
Research Paper Overview
LocalSUG: Geography-Aware LLM for Query Suggestion in Local-Life Services
Summary
LocalSUG is an LLM-based query suggestion framework designed for local-life service platforms to improve user search experience by generating geographically grounded candidate queries, reducing exposure bias, and minimizing online latency. It enhances click-through rates and reduces no-result queries through city-aware candidate mining, a beam-search-driven training algorithm, and efficient inference techniques.