语音输入金融筛选请求，自动生成可执行的结构化查询。
StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
- 用语音识别+检索增强提取约束条件，再生成带校验的SQL。
- 在150条语音指令上，准确率和可执行性显著优于基线模型。
- 适合需要透明、可调试金融分析过程的研究者与投资者。
StocksTalk 是一个语音驱动的对话系统，能将口头金融筛选请求转化为针对真实市场数据的可执行、可验证的结构化查询。该系统整合了流式语音识别、检索增强的约束提取、基于模式的LLM-SQL生成、规则校验及人工介入验证，并通过交互式仪表板实现全流程可视化。与传统模板驱动的金融助手不同，StocksTalk 展示中间推理过程，包括提取的约束、标准化的财务指标、操作符对齐和生成的查询，支持用户逐阶段检查与修正。为评估系统，我们构建了一个包含150个口语化金融指令的基准测试集，涵盖多种投资策略和输入噪声场景。实验表明，检索增强、约束生成与交互验证显著提升了约束提取准确率、SQL可执行性、逻辑一致性及多轮对话稳定性，优于基线LLM方法。该工作展示了透明语音界面如何连接自然语言交互与结构化金融分析，为对话式股票筛选与决策支持提供有效框架。
原文摘要 · Abstract (English)
StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured queries over real-world market data. The system combines streaming speech recognition, retrieval-augmented constraint extraction, schema-grounded LLM-based SQL generation, rule-based validation, and human-in-the-loop verification within an interactive dashboard. Unlike traditional template-driven financial assistants, StocksTalk exposes intermediate reasoning artifacts, including extracted constraints, normalized financial metrics, operator grounding, and generated queries, allowing users to inspect and refine each stage before execution. To evaluate the system, we curate a benchmark of 150 spoken financial prompts spanning multiple investment strategies and input noise conditions. Experimental results show that retrieval grounding, constrained query generation, and interactive verification substantially improve constraint extraction accuracy, SQL executability, logical consistency, and multi-turn stability compared to baseline LLM-based approaches. StocksTalk demonstrates how transparent, voice-driven interfaces can bridge natural language interaction and structured financial analysis, providing an effective framework for conversational stock screening and decision support.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。