Docket #: S26-223
A Cross-Division Talent Discovery System for Intercollegiate Athletics Using Composite Scoring, Productivity Exchange Rates, and Natural-Language Semantic Retrieval
Stanford researchers developed a system that makes athletic performance comparable across competitive divisions that otherwise share no common scale. A method translates production from every division onto one scale, and a natural-language retrieval layer lets the resulting index be queried in plain descriptive language, returning ranked, source-traceable results.
Stage of Development:
Prototype
Applications
- Cross-division talent evaluation and recruiting
- Professional scouting and roster construction
- Natural-language retrieval over other siloed, structured datasets
Advantages
- Produces a quantitative translation between competitive tiers, not just a within-tier rating
- Unifies records from many disconnected sources into one queryable index
- Plain-language search in place of structured filters
Related Links
Similar Technologies
-
Mesh-based Performance Capture from Multi-view Video S08-122Mesh-based Performance Capture from Multi-view Video
-
WiDeo: A Motion Tracing Camera using WiFi Signals S14-059WiDeo: A Motion Tracing Camera using WiFi Signals
-
End-to-end Semantic Segmentation of 3D Point Clouds by Convolutional Neural Networks, Trilinear interpolation, and Conditional Random Fields S17-380End-to-end Semantic Segmentation of 3D Point Clouds by Convolutional Neural Networks, Trilinear interpolation, and Conditional Random Fields