{"id":2624,"date":"2022-07-27T07:05:06","date_gmt":"2022-07-27T07:05:06","guid":{"rendered":"https:\/\/www.welovecycling.com\/dk\/?p=2624"},"modified":"2022-07-27T07:31:37","modified_gmt":"2022-07-27T07:31:37","slug":"jumbo-visma-nutrition-under-touren-machine-learning","status":"publish","type":"post","link":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/","title":{"rendered":"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring"},"content":{"rendered":"<p><strong>Hvordan hj\u00e6lper maskinl\u00e6ring professionelle cykelryttere? Mange hold ved Tour de France tager ern\u00e6ringen for deres ryttere meget alvorligt. En af de ting, som g\u00f8r Team Jumbo-Visma anderledes, er den teknologi, de anvender til at blive bedre og justere deres rytteres indtag.<\/strong><\/p>\n<p><!--more--><\/p>\n<h2><strong>Der er mange ting, som medtages i beregningen<\/strong><\/h2>\n<p>Det er ikke nemt at beregne pr\u00e6cist, hvilken slags ingredienser og hvor mange kalorier hver rytter har brug for. F\u00f8r i tiden begyndte holdenes ern\u00e6ringseksperter at forberede deres kalorieestimater flere uger eller endda en m\u00e5ned f\u00f8r starten p\u00e5 Tour de France. De kiggede i f\u00f8rste omgang p\u00e5 etapernes profiler og p\u00e5 rytternes v\u00e6gt og kropsbygning. Men efter l\u00f8bets start kom der altid uforudsete faktorer til. Vejret, \u00e6ndringer i holdets taktik og mange andre ting kr\u00e6vede en hurtig tilpasning af indtagelsen.<\/p>\n<p>Asker Jeukendrup, som er ansvarlig for ern\u00e6ringen hos Team Jumbo-Visma, har sagt i interviews, at han var n\u00f8dt til at oprette diagrammer for hver rytter for at beregne deres optimale indtag og omdanne det til m\u00e5ltider.<\/p>\n<div class=\"embed-controller-wrapper\">\n<blockquote class=\"twitter-tweet\" data-width=\"500\" data-dnt=\"true\">\n<p lang=\"en\" dir=\"ltr\">\ud83c\uddeb\ud83c\uddf7 <a href=\"https:\/\/twitter.com\/hashtag\/TDF2022?src=hash&amp;ref_src=twsrc%5Etfw\">#TDF2022<\/a><\/p>\n<p>Pre-race chat \ud83d\udde3<br \/>What are <a href=\"https:\/\/twitter.com\/rogla?ref_src=twsrc%5Etfw\">@rogla<\/a> and <a href=\"https:\/\/twitter.com\/LAPORTEChristop?ref_src=twsrc%5Etfw\">@LAPORTEChristop<\/a> talking about? \ud83e\udd14 <a href=\"https:\/\/t.co\/EVS3DtzvWX\">pic.twitter.com\/EVS3DtzvWX<\/a><\/p>\n<p>&mdash; Team Visma | Lease a Bike (@vismaleaseabike) <a href=\"https:\/\/twitter.com\/vismaleaseabike\/status\/1546807730173841408?ref_src=twsrc%5Etfw\">July 12, 2022<\/a><\/p><\/blockquote>\n<p><script async data-src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/div>\n<p>\u201dDet var meget tidskr\u00e6vende, og jeg kunne kun udf\u00f8re beregningerne for to ryttere ad gangen. Langsomt begyndte vi at opskalere, men det blev f\u00f8rst skalerbart og hurtigere, da Jumbo Foodcoach-appen kunne udf\u00f8re beregningerne for os og oms\u00e6tte dem til m\u00e5ltider. Jumbo har v\u00e6ret en fantastisk partner p\u00e5 det omr\u00e5de, og vi forbedrer hele tiden appen.\u201d<\/p>\n<h2><strong>Indsamling af data<\/strong><\/h2>\n<p>Opskalering og udvikling af en app, som kunne hj\u00e6lpe med at automatisere processen, var et stort skridt fremad for holdet. For at det kan fungere effektivt har de v\u00e6ret n\u00f8dt til at sikre, at appen har alle de n\u00f8dvendige data til at kunne give pr\u00e6cise forudsigelser. Det omfattede f\u00f8lgende:<\/p>\n<ul>\n<li>En Garmin-enhed p\u00e5 hver rytters cykel, som viser de faktiske rutedata vedr\u00f8rende samlet distance, k\u00f8rt stigning i meter etc.<\/li>\n<li>Et powermeter i kranken, som leverer en pr\u00e6cis beregning af de forbr\u00e6ndte kalorier.<\/li>\n<li>Rytternes individuelle v\u00e6gt, h\u00f8jde og rolle (sprinter, bjergrytter, etc.).<\/li>\n<li>Vejrudsigten i kombination med GPS-lokationsdata for hver rytter for at hj\u00e6lpe med at beregne p\u00e5virkningen fra vejret (medvind eller modvind etc.).<\/li>\n<\/ul>\n<p>Indsamlingen og visualiseringen af disse data udf\u00f8res af Smartbase, som er en datah\u00e5ndterings- og -analyseplatform. Tr\u00e6nerne hos Team Jumbo-Visma anvender denne platform til indtastning af faktiske data.<\/p>\n<h2><strong>Kontrolleret l\u00e6ring<\/strong><\/h2>\n<p>Holdet skal ogs\u00e5 rense dataene ved at fjerne fejl. Hvis en rytter eksempelvis glemmer at slukke sin Garmin-enhed, n\u00e5r etapen er slut, skal han slette den del af dataene, som er registreret efter etapen. De g\u00f8r ogs\u00e5 visse variabler relative, som fx kraft, energi og stigning, s\u00e5 det bliver nemt at sammenligne etaper og l\u00f8b. Alle disse data bliver s\u00e5 anvendt til at forberede prognoser.<\/p>\n<p>Ved hj\u00e6lp af eksempler fra tr\u00e6ningen har Team Jumbo-Visma indf\u00f8rt kontrolleret l\u00e6ring for at l\u00e6re deres algoritme, hvad resultatet af kalorieforudsigelserne skal v\u00e6re. Det var et regressionsproblem, og de valgte tilf\u00e6ldig prognose som den bedste maskinl\u00e6ring-algoritme til at l\u00f8se det.<\/p>\n<h2><strong>Maskinl\u00e6ring er langt mere pr\u00e6cis<\/strong><\/h2>\n<p>Det lyder jo godt alt sammen, men det kan ikke bruges til s\u00e5 meget, hvis ikke forudsigelserne som minimum er lige s\u00e5 pr\u00e6cise, som n\u00e5r menneskelige ern\u00e6ringseksperter laver dem manuelt. De anvendte R-squared til at evaluere b\u00e5de maskinl\u00e6ring-modellen og manuelle forudsigelser. R-squared m\u00e5ler styrken af forholdet mellem modellen og kalorierne p\u00e5 en skala fra 0-100 %. Denne maskinl\u00e6ring-model fik en score p\u00e5 82 %, mens de manuelle forudsigelser kun opn\u00e5ede 52 %. Det er helt utroligt! Algoritmen er ikke bare mere pr\u00e6cis, men ern\u00e6ringseksperterne f\u00e5r ogs\u00e5 resultaterne p\u00e5 et splitsekund, s\u00e5 de har mere tid til at reagere p\u00e5 de uforudsete faktorer, som opst\u00e5r under l\u00f8bet.<\/p>\n<h2><strong>Jumbo Foodcoach-appen oms\u00e6tter det til m\u00e5ltider<\/strong><\/h2>\n<p><a href=\"https:\/\/play.google.com\/store\/apps\/details?id=com.jumbo.foodcoach\">Jumbo Foodcoach-appen<\/a> samler tr\u00e5dene. N\u00e5r et holds ern\u00e6ringsekspert indtaster antallet af kalorier fra maskinl\u00e6ring-modellen i appen, s\u00e5 viser den eksempler p\u00e5 m\u00e5ltider med optimerede st\u00f8rrelser for hvert m\u00e5ltid. Nemmere bliver det ikke. Det er en af de afg\u00f8rende \u00e5rsager til, at holdet bliver ved med at vinde. Du kan <a href=\"https:\/\/apps.apple.com\/cz\/app\/jumbo-foodcoach\/id1486068608?l=cs\">tage et kig p\u00e5 deres app<\/a> i App Store eller p\u00e5 Google Play.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Hvordan hj\u00e6lper maskinl\u00e6ring professionelle cykelryttere? Mange hold ved Tour de France tager ern\u00e6ringen for deres ryttere meget alvorligt. En af [&hellip;]<\/p>\n","protected":false},"author":126,"featured_media":2628,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9,15],"tags":[],"global-categories":[],"class_list":["post-2624","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-professionel-cykling","category-tour-de-france"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.3 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring<\/title>\n<meta name=\"description\" content=\"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring\" \/>\n<meta property=\"og:description\" content=\"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"\u0160koda We Love Cycling - Danmark\" \/>\n<meta property=\"article:published_time\" content=\"2022-07-27T07:05:06+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-07-27T07:31:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"990\" \/>\n\t<meta property=\"og:image:height\" content=\"660\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"asbe\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Jiri Kaloc\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/\",\"url\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/\",\"name\":\"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring\",\"isPartOf\":{\"@id\":\"https:\/\/www.welovecycling.com\/dk\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg\",\"datePublished\":\"2022-07-27T07:05:06+00:00\",\"dateModified\":\"2022-07-27T07:31:37+00:00\",\"author\":{\"@id\":\"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/e9c2704405d1b37b5659f386cada996f\"},\"description\":\"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage\",\"url\":\"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg\",\"contentUrl\":\"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg\",\"width\":990,\"height\":660,\"caption\":\"Team Jumbo Visma\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.welovecycling.com\/dk\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/#website\",\"url\":\"https:\/\/www.welovecycling.com\/dk\/\",\"name\":\"\u0160koda We Love Cycling - Danmark\",\"description\":\"\u0160koda We Love Cycling - Danmark - Nyt online cykel magasin\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.welovecycling.com\/dk\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/e9c2704405d1b37b5659f386cada996f\",\"name\":\"asbe\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/27ef4966326ebca59ab8aad145325bbc7c03dae08e250562bfca8780fe30c9da?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/27ef4966326ebca59ab8aad145325bbc7c03dae08e250562bfca8780fe30c9da?s=96&d=mm&r=g\",\"caption\":\"asbe\"},\"url\":\"https:\/\/www.welovecycling.com\/dk\/author\/asbe\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring","description":"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/","og_locale":"da_DK","og_type":"article","og_title":"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring","og_description":"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.","og_url":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/","og_site_name":"\u0160koda We Love Cycling - Danmark","article_published_time":"2022-07-27T07:05:06+00:00","article_modified_time":"2022-07-27T07:31:37+00:00","og_image":[{"width":990,"height":660,"url":"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg","type":"image\/jpeg"}],"author":"asbe","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Jiri Kaloc","Est. reading time":"5"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/","url":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/","name":"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring","isPartOf":{"@id":"https:\/\/www.welovecycling.com\/dk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage"},"image":{"@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage"},"thumbnailUrl":"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg","datePublished":"2022-07-27T07:05:06+00:00","dateModified":"2022-07-27T07:31:37+00:00","author":{"@id":"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/e9c2704405d1b37b5659f386cada996f"},"description":"Machine learning hj\u00e6lper det professionelle cykelhold Jumbo-Visma til at blive bedre og justere deres rytteres indtag.","breadcrumb":{"@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#primaryimage","url":"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg","contentUrl":"https:\/\/d2p6e6u75xmxt8.cloudfront.net\/7\/2022\/07\/Jumbo-Visma-profimedia-0557100980-1024x694-CVR.jpg","width":990,"height":660,"caption":"Team Jumbo Visma"},{"@type":"BreadcrumbList","@id":"https:\/\/www.welovecycling.com\/dk\/professionel-cykling\/jumbo-visma-nutrition-under-touren-machine-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.welovecycling.com\/dk\/"},{"@type":"ListItem","position":2,"name":"S\u00e5dan anvender Jumbo-Visma maskinl\u00e6ring ved ern\u00e6ring"}]},{"@type":"WebSite","@id":"https:\/\/www.welovecycling.com\/dk\/#website","url":"https:\/\/www.welovecycling.com\/dk\/","name":"\u0160koda We Love Cycling - Danmark","description":"\u0160koda We Love Cycling - Danmark - Nyt online cykel magasin","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.welovecycling.com\/dk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Person","@id":"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/e9c2704405d1b37b5659f386cada996f","name":"asbe","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/www.welovecycling.com\/dk\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/27ef4966326ebca59ab8aad145325bbc7c03dae08e250562bfca8780fe30c9da?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/27ef4966326ebca59ab8aad145325bbc7c03dae08e250562bfca8780fe30c9da?s=96&d=mm&r=g","caption":"asbe"},"url":"https:\/\/www.welovecycling.com\/dk\/author\/asbe\/"}]}},"_links":{"self":[{"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/posts\/2624","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/users\/126"}],"replies":[{"embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/comments?post=2624"}],"version-history":[{"count":2,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/posts\/2624\/revisions"}],"predecessor-version":[{"id":2643,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/posts\/2624\/revisions\/2643"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/media\/2628"}],"wp:attachment":[{"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/media?parent=2624"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/categories?post=2624"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/tags?post=2624"},{"taxonomy":"global-categories","embeddable":true,"href":"https:\/\/www.welovecycling.com\/dk\/wp-json\/wp\/v2\/global-categories?post=2624"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}