[外絮] NBA全新數據--Gravity

看板NBA (美國籃球)作者EZ78 (EZ78)時間2小時前 (2025/12/26 14:57)推噓0(0推 0噓 0→)

留言0則, 0人參與討論串1/1

https://www.nba.com/inside-the-game/player/gravity https://www.nba.com/news/intro-to-gravity-stat-nba-2025 Gravity is a new way to quantify how much a player pulls defenders out of their normal assignments, essentially measuring how much attention they draw compared to what the spacing on the floor predicts. In simple terms, Gravity tells us who forces defenses to react, even before they touch the ball. Gravity是一種全新的方式，用來量化一名球員在場上把防守者拉離其原本防守位置的程度，本質上是在衡量球員實際吸引的防守注意力，與場上空間配置所預期的注意力之間的差異。簡單來說，Gravity告訴我們，哪些球員即使還沒碰到球，就已經迫使防守方做出反應。 Historically, the “eye test” has been the predominant way for spotting how certain players impact a defensive scheme, whether or not they have the ball. Coaches and fans have instinctively known which players demanded extra attention, but now, with the power of AWS AI and Machine Learning, the eye test just got smarter with the introduction of a new official NBA stat: Gravity. 過去，判斷某些球員在有球或無球狀態下，如何影響防守體系，主要仰賴eye test。教練與球迷本能地知道哪些球員需要被額外關注;而現在，透過AWS AI與機器學習的力量，這種eye test變得更聰明了，因為NBA推出了全新的官方數據指標:Gravity。 Gravity is the NBA’s first stat designed to quantify how much defensive pressure an offensive player draws both on and off the ball. Leveraging positional tracking data and powered by advanced Machine Learning models, Gravity scores show how much a player distorts a defense – opening driving or passing lanes, shifting rotations, and creating opportunities for teammates. Gravity是NBA首個用來量化進攻球員在有球與無球狀態下，究竟吸引了多少防守壓力的數據。它結合了球員位置追蹤資料，並由先進的機器學習模型驅動，能夠呈現一名球員如何扭曲防守結構--包括打開切入或傳球路線、迫使防守輪轉，以及為隊友創造機會。 The NBA’s optical tracking system uses 3D pose detection to track 29 points on every player’s body, 60 times per second. Those detailed body-position coordinates fuel the Machine Learning model, allowing it to capture every movement and spatial relationship on the floor. NBA的光學追蹤系統利用3D姿態偵測技術，每秒60次追蹤球員身體上的29個關鍵點。這些精細的身體位置座標成為機器學習模型的輸入資料，使其能捕捉場上每一個動作與空間關係。 The Gravity model compares the defensive pressure a player would receive on average based on the location of the ball and their position on the floor (Expected Defensive Pressure Score) to the pressure they actually draw (Defensive Pressure Score). The model learns how defenders typically behave in each scenario, and measures deviations that signal defensive adjustments. The result is a Gravity differential that measures how much attention a player pulls from the defense beyond expectation. Gravity模型會比較兩個數值一個是根據球的位置與球員在場上的站位，預期該球員平均應該承受的防守壓力，另一個是該球員實際吸引到的防守壓力。模型會學習防守者在各種情境下的典型行為，並衡量其中的偏離程度，藉此判斷防守是否因該球員而做出調整。最終產生的Gravity差值，代表球員超出預期所吸引的防守注意力。 The Gravity score measures frame-by-frame impact, expressed as a normalized value on a -100 to 100 scale, with 0 reflecting the league average. Above 0? You’ve got pull. Above 80 off-ball? Defenses are terrified of you before you even catch the ball. Above 90? You’re bending the floor and you’re a scorer the defense simply cannot blink on. Basically, that player should be guarded from the parking lot. Gravity 分數是以逐禎的方式計算，並以-100到100的標準化區間呈現，0代表聯盟平均水準。高於0？代表你有吸引力。無球狀態下高於80？代表防守在你接到球之前就已經害怕你了。高於90？代表你正在扭曲整個球場空間，是防守完全不敢眨眼的得分威脅。基本上，這種球員應該從停車場就開始被盯防。 Why does it matter? Gravity captures a player’s ability to impact the game before the play even begins. It highlights players who generate high-value spacing, draw mismatches, and make their teammates’ job easier – often without taking a shot. With Gravity, this invisible impact becomes visible, and the off-ball impact becomes measurable. Gravity is part of the next generation of stats and insights that we’re bringing to fans in real-time with the power of AWS AI. 那為什麼這很重要？Gravity能捕捉一名球員在戰術真正展開之前，就已經對比賽產生的影響。它凸顯了那些能創造高價值空間、迫使防守錯位、讓隊友打得更輕鬆的球員--即使他們沒有出手。透過Gravity，這種過去看不見的影響力變得可被量化，無球影響也終於有了明確指標。 Gravity是NBA運用AWS AI，為球迷即時帶來的下一世代數據與洞察的一部分。心得: 第一名當然是 https://i.meee.com.tw/B2EIquS.png