Marcus Woo

Growing up， Rachel Martywould spend hours shooting hoopson her driveway with her dad.

從小到大，瑞秋·馬蒂會(huì)跟父親一起在家門口的路上練習(xí)幾個(gè)小時(shí)的投籃。

Sometimes， a talking computerjoined them. In the early years，Marty's dad connected a laptop to acamera， placed them on a cart， androlled it out onto the street's edgewhere he surrounded it with trafficcones. From about 25 feet away， thecamera could capture the arc of theball as Marty shot. And with eachshot， the computer would announcethe angle of the ball's trajectory.

有時(shí)，一臺(tái)會(huì)說(shuō)話的電腦會(huì)加入他們。早年間，馬蒂的爸爸會(huì)把筆記本電腦與攝像機(jī)連接在一起，將這個(gè)設(shè)備裝在手推車上，推到街上由交通錐組成的場(chǎng)地上。在7.62米外，攝像機(jī)能夠捕捉馬蒂投籃時(shí)籃球的弧度。每次投籃后，電腦會(huì)報(bào)出皮球行進(jìn)路線的角度。

43.47.42.

43.47.42。

The optimal entry angle，Marty says， is 45 degrees， and thekey is consistency. With this hightechtrainer， she honed her shotover the years as a shooting guardin high school and in college at theUniversity of California， San Diego.

馬蒂說(shuō)，最理想的進(jìn)球角度是45度，關(guān)鍵在于持續(xù)性。有了這個(gè)高科技訓(xùn)練師，她不斷磨練自己的投籃，分別在高中和加州大學(xué)圣迭戈分校擔(dān)任得分后衛(wèi)。

"We were known in the neighborhoodas being the weirdos whohad this talking machine，" she said.

“鄰居都說(shuō)我們是跟機(jī)器說(shuō)話的怪人?！彼f(shuō)。

But things have changed.In the last few years， high-techcameras have proliferated acrossthe highest levels of basketball. In2010， the year Marty graduatedfrom high school， a sports companycalled Stats， LLC， installed the firstSportVU camera systems in NBAarenas. These cameras， perchedup with the rafters， track not onlythe basketball， but also playermovement. By 2013， these cameraswere in every NBA arena.

但情況已經(jīng)發(fā)生了改變。過(guò)去幾年，高科技攝像機(jī)已經(jīng)廣泛應(yīng)用于高水平的籃球賽。2010年，也就是馬蒂?gòu)母咧挟厴I(yè)那年，一家名為Stats的公司將首個(gè)SportVU攝像系統(tǒng)裝進(jìn)了NBA球館。這些裝在屋頂上的攝像機(jī)不僅追蹤籃球，同樣追蹤球員的移動(dòng)。到2013年，這些攝像機(jī)入駐了全部NBA球館。

The use of machine learningand AI in basketball representsonly the latest chapter in theanalytics revolution that has beentransforming basketball overthe last 15 or so years. "It's just acontinuation of the spectrum，" saidBrian Kopp， a sports technologyexecutive who helped Stats， LLCroll out SportVU to the NBAduring the early part of the decade.

使用機(jī)器學(xué)習(xí)及人工智能只是過(guò)去15年內(nèi)徹底改變籃球這項(xiàng)運(yùn)動(dòng)數(shù)據(jù)分析革命的最新篇章?！斑@只是這一領(lǐng)域的延續(xù)?！辈既R恩·庫(kù)普表示，作為體育科技工作人員，他協(xié)助St at s公司在早期將SportVU系統(tǒng)推廣到了NBA。

Of course， teams had longbeen recording basic statistics suchas points， rebounds， and assists. Butwith analytics， as this statisticalapproach is called， the stat geeksestablished the power of math.

當(dāng)然，球隊(duì)多年來(lái)一直在記錄諸如得分，籃板和助攻這樣的基礎(chǔ)數(shù)據(jù)。但有了數(shù)據(jù)分析后，當(dāng)人們開始從數(shù)據(jù)角度看待一切，數(shù)據(jù)極客們確立了數(shù)學(xué)的威力。

That statistical sophisticationwas widespread in the NBA by thetime teams first adopted trackingcameras. But the new deluge of datademanded updated techniques andsoftware. "Along came SportVU，and the data we captured could notbe contained in Microsoft Excel，"said Kopp.

當(dāng)球隊(duì)第一次采用追蹤攝像機(jī)時(shí)，NBA早已開始使用復(fù)雜的數(shù)據(jù)統(tǒng)計(jì)方法。但新型數(shù)據(jù)的出現(xiàn)，要求技術(shù)和軟件也要做出更新?！斑@就出現(xiàn)了SportVU，而且我們采集的數(shù)據(jù)只靠Excel是沒法承受的。”庫(kù)普說(shuō)道。

Meanwhile， increasinglypowerful computers were enablingnew advances in machine learning，so NBA teams and companies likeStats took advantage. The task wasto translate the tracking data intosomething searchable and digestible，and one major goal， in particular，was to identify specific actions likepasses and common plays such asthe pick-and-roll. Machine learningand， more broadly， AI were perfectfor the task because， they're aboutpattern recognition at their hearts.And pattern recognition is preciselywhat's required to distinguish， say，the many variants of a pick-and-roll.

與此同時(shí)，功能越來(lái)越強(qiáng)大的計(jì)算機(jī)讓機(jī)器學(xué)習(xí)出現(xiàn)了新的突破，NBA球隊(duì)及Stats這樣的公司抓住了這個(gè)機(jī)會(huì)。他們的任務(wù)是將追蹤數(shù)據(jù)翻譯成可供研究，容易理解的信息;其中一個(gè)主要目標(biāo)，就是明確如傳球這樣的特定動(dòng)作，以及擋拆這樣的常見戰(zhàn)術(shù)。機(jī)器學(xué)習(xí)，或者更寬泛地說(shuō)，人工智能，極為適合執(zhí)行這個(gè)任務(wù)，因?yàn)闅w根結(jié)底，計(jì)算機(jī)的核心就是模式識(shí)別。舉個(gè)例子，模式識(shí)別正是區(qū)分多種擋拆類型所需的技能。

To be clear， these algorithmsaren't doing anything humanscan't. Humans are really good atrecognizing patterns， and teamshave long hired staff to reviewvideo and identify notable clips forgame planning. But it's impracticalto sift through hundreds of hours offootage to identify every single pass，shot， rebound， cut， screen and roll.

需要明確的是，算法能做的事，人類都能做。人類其實(shí)很善于識(shí)別模式，多年來(lái)球隊(duì)也有專門工作人員審查錄像，確定值得注意的戰(zhàn)術(shù)，從數(shù)百小時(shí)的錄像中篩選一個(gè)傳球，投籃，籃板，空切和擋拆。

Marty's talking computer --and steadily improved versions of it-- would follow her through highschool and college， helping to trainher teammates and even during herrecovery from injury. "The systemwas growing up with me，" she said.

馬蒂會(huì)說(shuō)話的電腦——以不斷改善的版本——伴隨她度過(guò)了高中和大學(xué)，幫助她訓(xùn)練隊(duì)友，甚至協(xié)助她從傷病中恢復(fù)。她說(shuō)：“這套系統(tǒng)和我一起長(zhǎng)大。”

In 2001， her father， Alan， hadturned his invention into a companycalled Noah Basketball， named sobecause in the Bible， Noah had theperfect “ark.” The newest version，which includes tools to analyze yourdata and is dubbed Noahlytics， isnow used by half of NBA teams，dozens of top college programs，and hundreds of individuals aroundthe country， said John Carter， thecompany's current CEO. Their systemconsists of cameras attached 10feet above the backboard that don'tjust track the ball's arc， but also itsdepth and left-right position as itapproaches the rim. The system collectsdata on every shot， adding to adatabase of more than 150 millionshots already recorded during practicesessions around the country.

2001年，她的父親阿倫用自己的發(fā)明創(chuàng)始了名為“諾亞籃球”的公司;之所以使用這個(gè)名字，是因?yàn)槭ソ?jīng)中諾亞擁有完美的“方舟”。據(jù)公司現(xiàn)任CEO約翰·卡特表示，被命名為“諾亞分析”的最新系統(tǒng)包括數(shù)據(jù)分析工具，如今已經(jīng)被半數(shù)NBA球隊(duì)，眾多頂尖大學(xué)以及全美各地?cái)?shù)百名個(gè)人用戶使用。他們的系統(tǒng)由位于籃板上方3.05米的攝像機(jī)構(gòu)成，這些攝像機(jī)不但追蹤球的弧度，也會(huì)記錄球的深度以及接近籃板時(shí)的左右位置。系統(tǒng)會(huì)收集每一次出手?jǐn)?shù)據(jù)，補(bǔ)充到數(shù)據(jù)庫(kù)中，這個(gè)數(shù)據(jù)庫(kù)已經(jīng)記錄了全美各地超過(guò)1.5億次的投籃數(shù)據(jù)。

This data is crucial for themachine learning algorithms thatare being incoroporated into thenewer systems. The next version，which has already been installedfor a few NBA teams， incorporatesfacial recognition， and can trackshots from multiple shooterssimultaneously. That allows thesystem to collect and analyze datafrom team practices， for example.According to Carter， in the springthe company will introduceanother new feature to capture thetype of shot a player takes. Usingdeep learning， a type of machinelearning that mimics how a brainlearns， the system can identify theparticular type of shot taken --moves that have varying degrees ofdifficulty that affect the likelihoodthat the ball goes in.

對(duì)于配備在新系統(tǒng)中的機(jī)器學(xué)習(xí)算法，這個(gè)數(shù)據(jù)至關(guān)重要。一些NBA球隊(duì)已經(jīng)開始使用有面部識(shí)別系統(tǒng)的新版了，它可以同時(shí)記錄多名射手的投籃。舉個(gè)例子，這個(gè)改變可以讓系統(tǒng)收集球隊(duì)訓(xùn)練中的數(shù)據(jù)并做出分析。據(jù)卡特表示，公司春天還會(huì)引入另一個(gè)新功能，捕捉球員的出手方式。使用深度學(xué)習(xí)（一種模仿人腦學(xué)習(xí)過(guò)程的機(jī)器學(xué)習(xí)），系統(tǒng)可以確定特定類型的出手方式——不同難度的出手，會(huì)影響進(jìn)球概率。

But whether a shot is madeultimately depends on the ball'strajectory. Rachel Marty， whorecently earned a doctorate inbioinformatics， analyzed datafrom 22 million shots collectedby Noah's system to find a moreefficient way to evaluate a shooter'sskill. Typically， coaches and scoutsevaluate shooting ability based onhow many shots a player makesduring a workout. The more shotsa player takes， the better you canassess her true abilities.

可能否進(jìn)球，最終取決于球的行進(jìn)軌跡。最近剛獲得生物訊息學(xué)博士學(xué)位的瑞秋·馬蒂分析了諾亞系統(tǒng)收集的2200萬(wàn)次投籃，希望能找到更有效評(píng)估投手能力的方法。一般來(lái)說(shuō)，教練和球探基于球員訓(xùn)練時(shí)的命中數(shù)量評(píng)估投籃能力。出手?jǐn)?shù)量越多，就越能評(píng)估她的真實(shí)能力。

Since not every player has theopportunity to take thousands ofshots， Marty trained an algorithmto recognize the characteristics ofa made shot and predict a player'sskill based on only a few attempts.Instead of having players takethousands of shots， coaches andscouts can have them shoot， say，25. By analyzing the recordeddata， Marty's program can providean accurate estimate of their ability.This capability is also somethingthat will be eventually incorporatedinto their commercial product，Carter said.

考慮到不是所有球員都有機(jī)會(huì)出手幾千次，25歲的馬蒂表示，她嘗試了一種算法，可以識(shí)別命中投籃的特點(diǎn)，且只需要幾次出手就能預(yù)測(cè)球員的能力，教練和球探不再需要球員出手幾千次。通過(guò)分析記錄的數(shù)據(jù)，馬蒂的系統(tǒng)可以準(zhǔn)確估算球員的能力?？ㄌ卣f(shuō)，這個(gè)功能最終也會(huì)被融入他們的商用產(chǎn)品。

The impact of machinelearning and AI goes beyondX's and O's. Much of SecondSpectrum's efforts are to providea personalized game-watchingexperience with evermore detailedstatistics for the geekiest fans.For example， their CourtVisionaugmented video technologylike the probability a player wouldmake a basket， which is based onhis past data. You can watch thenumbers change above his head ashe runs around. The company's goalis for this technology to be widelyavailable on all broadcasts.

機(jī)器學(xué)習(xí)及人工智能的影響并不局限于賽場(chǎng)。Sec ondSpectrum公司的主要工作，就是為癡迷于數(shù)據(jù)的極客球迷，針對(duì)他們提供定制化的觀賽體驗(yàn)。比如他們的CourtVision增強(qiáng)視頻技術(shù)可以在球隊(duì)過(guò)往數(shù)據(jù)的基礎(chǔ)上，將球員的進(jìn)球可能性等數(shù)據(jù)或圖像疊加在視頻中。球員跑動(dòng)時(shí)，觀眾可以看到他頭頂?shù)臄?shù)字變化。公司的目標(biāo)是讓這個(gè)技術(shù)廣泛用于所有比賽直播。

隨著體育接納人工智能，機(jī)器最終會(huì)統(tǒng)治一切嗎？不管怎么說(shuō)，目前世界上最好的國(guó)際象棋，圍棋選手都是電腦。未來(lái)NBA的比賽會(huì)降格到算法之間的競(jìng)爭(zhēng)嗎？在戰(zhàn)略及戰(zhàn)術(shù)層面，你無(wú)法像解決圍棋比賽那樣解決籃球比賽。復(fù)雜的棋牌運(yùn)動(dòng)需要遵守嚴(yán)格的規(guī)則，而籃球是流動(dòng)的，球隊(duì)需要不斷做出調(diào)整與反調(diào)整。

An emerging market for thesereal-time probabilities is sportsgambling， which is now legal inmost states thanks to a SupremeCourt ruling in May that struckdown a ban on commercial sportsbetting. Much of sports gamblinginvolves wagering on specific eventsduring a game， such as whether acertain player will score 20 pointsin a quarter. To set the odds， gamblinghouses will need real-timeprobabilities. It might take a fewyears for this to develop， Kopp said，but the opportunity is there.

這種實(shí)時(shí)可能性的新興應(yīng)用市場(chǎng)，就是體育博彩，五月，美國(guó)最高法院撤銷了對(duì)體育商業(yè)博彩的禁令，美國(guó)大多數(shù)州已允許體育博彩。很多體育博彩涉及在一場(chǎng)比賽的特定時(shí)間投注，比如某個(gè)球員能否在一節(jié)比賽里得到20分。為了確定賠率，博彩公司需要實(shí)時(shí)可能性。庫(kù)普表示，這種技術(shù)可能需要數(shù)年時(shí)間才能發(fā)展完善，但機(jī)會(huì)就在眼前。

As sports continue to embraceAI， though， will machines soonreign supreme？ After all， the bestchess and go players in the worldare now computers. Would afuture NBA game be reduced to acompetition of algorithms？

隨著體育接納人工智能，機(jī)器會(huì)統(tǒng)治一切嗎？不管怎么說(shuō)，目前世界上最好的國(guó)際象棋，圍棋選手都是電腦。未來(lái)NBA的比賽會(huì)降格到算法之間的競(jìng)爭(zhēng)嗎？

Unlikely， said Dean Oliver，vice president of data science atTruMedia， and considered one ofthe pioneers of basketball analytics.When it comes to strategy andtactics， you can't solve basketball theway you can solve a game like go.Even complex board games followrigid rules， while basketball is fluid，with teams constantly adjusting andreadjusting to each other. "There isno dominant strategy，" he said. "Thegame is far more robust.”

不過(guò)TruMedia的數(shù)據(jù)科學(xué)副總裁迪恩·奧利弗認(rèn)為這種情況不可能發(fā)生，他被看作是籃球分析界的先鋒。在戰(zhàn)略及戰(zhàn)術(shù)層面，你無(wú)法像解決圍棋比賽那樣解決籃球比賽。復(fù)雜的棋牌運(yùn)動(dòng)需要遵守嚴(yán)格的規(guī)則，而籃球是流動(dòng)的，球隊(duì)需要不斷做出調(diào)整與反調(diào)整。“不存在統(tǒng)治性的戰(zhàn)略?！彼f(shuō)，“籃球比賽更有活力?！?/p>

Indeed， a coach's job is farmore than drawing up plays. "Theelement of coaching that doesn't getplayed up as much as it should is theability of the coaches to work withplayers， to motivate them， to getthem to play together，" Oliver said.

事實(shí)上，教練的工作遠(yuǎn)不止指定戰(zhàn)術(shù)這么簡(jiǎn)單。“教練一項(xiàng)很少被提起的工作，就是與球員合作的能力，如何激勵(lì)他們，讓他們團(tuán)結(jié)在一起?！眾W利弗說(shuō)。

Although the teams quickestto adopt machine learning do gainan edge， machine learning hasn'trevolutionized the game just yet， headded. "What's changed the gameof basketball from what it was 10years ago until now is not the AIand machine learning part of it，" hesaid. "It wouldn't be tremendouslysimplifying to say that StephCurry changed basketball." Currysdevastating ability to shoot fromsuch range has forced teams toabandon strategies that were onceconventional wisdom.

盡管最早接受機(jī)器學(xué)習(xí)的球隊(duì)確實(shí)獲得了競(jìng)爭(zhēng)優(yōu)勢(shì)，但他補(bǔ)充，機(jī)器學(xué)習(xí)尚未給比賽帶來(lái)革命性變化?！艾F(xiàn)在的籃球與10年前的變化不在于人工智能和機(jī)器學(xué)習(xí)參與到了其中?！彼f(shuō)，“極度簡(jiǎn)化的說(shuō)法就是，史蒂芬·庫(kù)里改變了籃球。”庫(kù)里的遠(yuǎn)程出手能力迫使球隊(duì)放棄了傳統(tǒng)策略。

As a data scientist， Martydoesn't play basketball as muchanymore. But when she visits herparents' home， she tries to takethe time to roll out the old shottrackingsystem， just like thoseevenings she used to spend shootingwith her dad. "That was our specialfather-daughter thing，" she said.

作為數(shù)據(jù)科學(xué)家，馬蒂不再像過(guò)去那樣經(jīng)常打籃球。但拜訪父母時(shí)，她總會(huì)搬出舊的投籃追蹤系統(tǒng)，就像當(dāng)年她和父親一起投籃的那些夜晚?！澳鞘呛芴貏e的父女之間的聯(lián)系?！彼f(shuō)。

Trying to hit that 45-degreeangle gets addictive， she said. But it'sfun， and sometimes it's always goodto go back to the basics -- even ifthat means a talking computer.

她說(shuō)，以45度角命中投籃會(huì)讓人上癮。但這很有趣，而且回歸基本是好事——盡管這意味著你需要一臺(tái)會(huì)說(shuō)話的電腦。