Agentic Generative AI for Media Content Discovery at the National Football League

2025-10-08

ISACE

AI Summary

To address low retrieval efficiency and rigid interaction paradigms in querying historical NFL game content, this paper proposes a generative AI–based, semantics-driven retrieval agent framework. The framework integrates natural language understanding, semantic parsing, and database query translation, and introduces a novel semantic caching mechanism to enable end-to-end mapping from complex natural language queries to precise video segments. Unlike conventional filter-based interfaces, the system supports direct, unstructured natural language queries (e.g., “show slow-motion replays of quarterback touchdown passes in Super Bowl 2022”), significantly improving both accuracy and latency: query accuracy reaches 95.3%, while average response time decreases from 10 minutes to 30 seconds. This work establishes a scalable, AI-native content discovery paradigm for sports media applications.

Technology Category

• Natural Language Processing: Question Answering
• Search and Optimization: Learning to Search
• Computer Vision: Image and Video Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and latency are further improved through carefully designed semantic caching. The solution achieves over 95 percent accuracy and reduces the average time to find relevant videos from 10 minutes to 30 seconds, significantly increasing the NFL's operational efficiency and allowing users to focus on producing creative content and engaging storylines.

Problem

• Enables natural language queries for historical NFL plays
• Replaces traditional filter interfaces with agentic AI workflow
• Improves content discovery accuracy and reduces search latency

Innovation

• Uses natural language queries for historical play discovery
• Implements agentic workflow to translate user queries
• Employs semantic caching to improve accuracy and latency