数字化教练智能：基于VLM和RAG的整体运动员画像智能体框架
Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG
AI总结：
提出基于LLM的混合智能体框架，结合计算机视觉与视觉语言模型，通过3×3智能网格分块策略降低计算开销，并引入LLM-as-a-Judge自校正循环和双持久化RAG管道，实现符合印度体育局标准的自动化整体运动员评估。
摘要：
运动员评估是跟踪身体进展和识别精英人才的关键过程。然而，在大规模招聘活动中，传统方法依赖于人工观察，这本质上是主观且不可扩展的，或者依赖于仅限于定量重复计数的基本计算机视觉（CV）系统。这些标准方法缺乏评估定性生理指标（如形态退化、脊柱关节和疲劳）所需的“教练智能”。本文提出了一种新颖的、基于LLM的混合智能体框架，用于自动化的整体运动员画像，严格遵循印度体育局（SAI）评估协议。通过LangGraph编排，我们的双管道架构将CV（MediaPipe）的几何精度用于运动学跟踪，与视觉语言模型（Llama-4-scout）的语义推理相结合。为了克服多模态视频处理相关的延迟和令牌限制，我们引入了一种3×3“智能网格”时间分块策略，将计算开销降低超过88%，同时保留关键的时间连续性。为确保数据完整性并减少幻觉，该框架开创了一种自主的“LLM-as-a-Judge”自校正循环，在持久化之前交叉引用定量和定性指标。最后，我们实现了一个利用向量搜索引擎（ChromaDB）的双持久化检索增强生成（RAG）管道。这使得教练能够绕过僵化的SQL数据库，使用自然语言执行复杂的语义查询（例如，“识别出耐力高但核心刚性差的运动员”）。实验结果表明，这种多智能体方法显著弥合了原始生物特征跟踪与可操作教练见解之间的差距，为全国性人才识别提供了可扩展、客观的解决方案。
英文摘要：
Athlete assessment is a critical process for tracking physical progress and identifying elite talent. However, during mass recruitment drives, traditional methods rely on manual observation, which is inherently subjective and unscalable, or basic computer vision (CV) systems limited to quantitative repetition counting. These standard approaches lack the "coaching intelligence" required to evaluate qualitative physiological markers such as form degradation, spinal articulation, and fatigue. This paper presents a novel, LLM-based hybrid agentic framework for automated, holistic athlete profiling that strictly aligns with the Sports Authority of India (SAI) assessment protocols. Orchestrated via LangGraph, our dual-pipeline architecture synthesizes the geometric precision of CV (MediaPipe) for kinematic tracking with the semantic reasoning of Vision-Language Models (Llama-4-scout). To overcome the latency and token constraints associated with multimodal video processing, we introduce a 3 X 3 "Smart Grid" temporal chunking strategy, reducing computational overhead by over 88% while preserving critical temporal continuity. To ensure data integrity and mitigate hallucination, the framework pioneers an autonomous "LLM-as-a-Judge" self-correction loop that cross-references quantitative and qualitative metrics before persistence. Finally, we implement a dual-persistence Retrieval-Augmented Generation (RAG) pipeline utilizing a vector search engine (ChromaDB). This enables coaches to bypass rigid SQL databases and perform complex semantic queries (e.g., "Identify athletes with high endurance but poor core rigidity") using natural language. Experimental results demonstrate that this multi-agent approach significantly bridges the gap between raw biometric tracking and actionable coaching insights, offering a scalable, objective solution for national talent identification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
