{"id":35196,"date":"2022-08-24T13:19:03","date_gmt":"2022-08-24T13:19:03","guid":{"rendered":"https:\/\/beacontower.io\/?p=35196"},"modified":"2022-11-09T08:07:15","modified_gmt":"2022-11-09T08:07:15","slug":"datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata","status":"publish","type":"post","link":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/","title":{"rendered":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata"},"content":{"rendered":"

[et_pb_section fb_built=”1″ _builder_version=”4.14.2″ _module_preset=”default” custom_margin=”0px||0px||true|false” custom_padding=”0px||0px||true|false” global_colors_info=”{}”][et_pb_row _builder_version=”4.14.2″ _module_preset=”default” custom_padding=”||0px||false|false” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

N\u00e5r man arbejder med data fra industrielle aktiver, hvad enten det er fra automationssystemer eller direkte fra micro-controllerne, s\u00e5 er det afg\u00f8rende at kunne lave strukturer i sin back-end, der giver mulighed for at kunne beskrive data ud fra en forretningskontekst, og ikke blot en 1:1 gengivelse af \u201dtemp_sensor_123\u201d fra \u201dmachine1234abc\u201d. Man vil med andre ord gerne have mulighed for fleksibelt at kunne definere strukturer som passer den enkelte medarbejder, kunde eller samarbejdspartner. Udover at de individuelle akt\u00f8rer i et IoT-scenarie kan komme fra forskellige organisationer, s\u00e5 er det ogs\u00e5 ofte, at de involverede organisationer har forskellige interne roller som skal anvende data. Derfor er det vigtigt, at en IoT-platform giver fleksibilitet ift. at kunne strukturere data p\u00e5 mange forskellige m\u00e5der og at den underliggende datamodel er let at integrere til. <\/p>\n

Lad os g\u00e5 et spadestik dybere:\u00a0<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.14.2″ _module_preset=”default” custom_margin=”19px||0px||false|false” custom_padding=”0px||0px||false|false” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Data er data er data<\/h2>\n

N\u00e5r vi dykker lidt dybere ned i kravene for at arbejde effektivt med tidsserie- og maskindata, s\u00e5 er tingene ikke s\u00e5 simple, som det umiddelbart kan lyde n\u00e5r man l\u00e6ser diverse produkt- og firmapr\u00e6sentationer. F.eks. er der mange IoT-platforme der sl\u00e5r sig op p\u00e5 at give deres kunder en \u00e5ben adgang til deres data. Det er der s\u00e5dan set heller ikke noget galt i. Faktisk b\u00f8r det v\u00e6re det mindste man kan forlange.<\/p>\n

[\/et_pb_text][et_pb_testimonial _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

“F.eks. er der mange IoT-platforme der sl\u00e5r sig op p\u00e5 at give deres kunder en \u00e5ben adgang til deres data. Det er der s\u00e5dan set heller ikke noget galt i. Faktisk b\u00f8r det v\u00e6re det mindste man kan forlange.”<\/em><\/p>\n

[\/et_pb_testimonial][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Et vigtigere kriterie er, om den datamodel som indkapsler r\u00e5data og giver forretningskontekst, er \u00e5ben, fleksibel og let tilg\u00e6ngelig. Et yderligere krav til datamodellen, b\u00f8r ogs\u00e5 v\u00e6re, at denne har en fleksibilitet der g\u00f8r at r\u00e5data kan fortolkes og sammens\u00e6ttes i nye sammenh\u00e6nge, alt efter behov, samt at r\u00e5data ikke replikeres hver gang man laver en ny datamodel. Et andet overordnet krav man b\u00f8r stille, er at det skal v\u00e6re ligetil at integrere til b\u00e5de datamodeller, livedata og IoT-platformens services. Det kr\u00e6ver en \u00e5ben arkitektur som kan skalere b\u00e5de ift. datam\u00e6ngder men lige s\u00e5 vigtigt er det at platformens datah\u00e5ndtering kan skalere effektivt n\u00e5r der kommer flere typer brugere og organisationer p\u00e5. Et sidste overordnet krav b\u00f8r v\u00e6re, at man kan garantere at data og ikke mindst datamodellen (og dermed nok hele platformen) er i virksomhedens kontrol. Det vil i praksis betyde, at man som ejer af et IoT-produkt eller som dataejer i en Industry 4.0 proces, formentlig skal have mulighed for at flytte hele l\u00f8sningen over i sin egen IT-infrastruktur, som kan v\u00e6re cloud eller on-premise.<\/p>\n

Lad os se hvordan Beacon Tower adresserer disse krav:<\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Beacon Tower anvender en \u00e5ben arkitektur<\/h2>\n

Beacon Tower har en \u00e5ben arkitektur uden brug af \u201dblack-box\u201d funktionalitet. Samtidig er alle services udstillede via API\u2019er i et servicelag, og dermed kan r\u00e5data fra maskiner og sensorer frit tilg\u00e5s, men endnu vigtigere er det at man kan integrere ligetil med datamodellernes services og dermed genbruge datastrukturerne i andre systemer. Det er f.eks. utroligt nyttigt i en machine learning sammenh\u00e6ng, at data-analytikerne kan anvende datamodellerne og ikke skal bruge tid p\u00e5 at s\u00e6tte struktur p\u00e5 data. Det betyder f.eks. at en data-analytiker kan foresp\u00f8rge Beacon Tower om f\u00f8lgende:<\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” background_color=”#808080″ global_colors_info=”{}”]<\/p>\n

\n

\u201cGiv mig de maskiner af model X som har haft et atypisk vibrationsm\u00f8nster inden for de seneste 24 timer for vores kunder i Skandinavien<\/em>\u201d
<\/span><\/p>\n<\/blockquote>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.14.2″ _module_preset=”default” min_height=”802.1px” custom_margin=”-55px||-84px||false|false” custom_padding=”0px||||false|false” global_colors_info=”{}”][et_pb_row _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

P\u00e5 den m\u00e5de kan dataanalytikeren arbejde effektivt med f.eks. at forbedre algoritmen til at detektere anomalier i sit foretrukne udviklingsmilj\u00f8. Liges\u00e5 kan serviceteknikeren have et dashboard i f.eks. CRM eller i sin serviceapplikation der viser hvilke maskiner der udviser tegn p\u00e5 at skulle kr\u00e6ve vedligehold inden for vedkommendes ansvarsomr\u00e5de.<\/p>\n

Beacon Tower har en fleksibel datamodel<\/h3>\n

For at ovenst\u00e5ende dataanalyse scenarie overhovedet kan lade sig g\u00f8re, kr\u00e6ver det naturligvis at man kan definere sin data pr\u00e6cis som man gerne vil have det. I Beacon Tower kan man definere lige s\u00e5 mange datamodeller som man har lyst til og s\u00e6tte dem ind i et uendeligt antal hierarkier med forskellige adgangsrettigheder. Derfor bliver det let at strukturere data p\u00e5 f\u00f8lgende m\u00e5de hvor vi bruger en virksomhed som laver, s\u00e6lger og servicerer el-billadere (car chargers) som eksempel:<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/iot_cloud_dtld_models_azure_beacon_tower.png” alt=”IoT cloud DTDL models Azure Beacon Tower” title_text=”iot_cloud_dtld_models_azure_beacon_tower” _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.14.2″ _module_preset=”default” custom_padding=”0px||||false|false” global_colors_info=”{}”][et_pb_row _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.14.2″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Beacon Tower er replikerbart og dedikeret<\/h3>\n

Beacon Tower er designet til at forenkle og accelerere IoT-udvikling og -drift ved at hele platformen k\u00f8res i et valgfrit Azure-milj\u00f8 der er dedikeret til den enkelte kunde og dennes samarbejdspartnere. Hele platformen bliver l\u00f8bende opdateret og vedligeholdt. Dette fjerner meget af uvisheden og kompleksiteten med at bygge p\u00e5lidelige, skal\u00e9rbare og sikre IoT-applikationer, samtidig med at I p\u00e5 et hvilket som helst tidspunkt kan f\u00e5 et udviklings- og test-milj\u00f8 eller s\u00e5gar en dedikeret l\u00f8sning til \u00e9n specifik kunde. Det g\u00f8r ogs\u00e5 at I har 100% kontrol med platformen og kan garantere over for kunder og samarbejdspartnere at data ligger \u00e9t specifikt sted.<\/p>\n

L\u00e6s mere om hvordan Beacon Tower indg\u00e5r som en integreret dataplatform i et enterprise IT-milj\u00f8<\/a>.<\/p>\n

For mere information:<\/strong><\/h3>\n

Partner, Mikael R\u00f6nde, mikael.ronde@glaze.dk<\/a><\/p>\n

L\u00e6s mere om de forskellige Beacon Tower leveringsmuligheder<\/a>.<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

N\u00e5r man arbejder med data fra industrielle aktiver, hvad enten det er fra automationssystemer eller direkte fra micro-controllerne, s\u00e5 er det afg\u00f8rende at kunne lave strukturer i sin back-end, der giver mulighed for at kunne beskrive data ud fra en forretningskontekst, og ikke blot en 1:1 gengivelse af \u201dtemp_sensor_123\u201d fra \u201dmachine1234abc\u201d. Man vil med andre […]<\/p>\n","protected":false},"author":5,"featured_media":35216,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[19],"tags":[],"class_list":["post-35196","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized-da"],"yoast_head":"\nDatastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower\" \/>\n<meta property=\"og:description\" content=\"N\u00e5r man arbejder med data fra industrielle aktiver, hvad enten det er fra automationssystemer eller direkte fra micro-controllerne, s\u00e5 er det afg\u00f8rende at kunne lave strukturer i sin back-end, der giver mulighed for at kunne beskrive data ud fra en forretningskontekst, og ikke blot en 1:1 gengivelse af \u201dtemp_sensor_123\u201d fra \u201dmachine1234abc\u201d. Man vil med andre […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/\" \/>\n<meta property=\"og:site_name\" content=\"Beacon Tower\" \/>\n<meta property=\"article:published_time\" content=\"2022-08-24T13:19:03+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-11-09T08:07:15+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1500\" \/>\n\t<meta property=\"og:image:height\" content=\"1002\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Jakob Appel\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Skrevet af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Jakob Appel\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/\"},\"author\":{\"name\":\"Jakob Appel\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#\\\/schema\\\/person\\\/c241382a256ec0f2de3cc46babd7ab1d\"},\"headline\":\"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata\",\"datePublished\":\"2022-08-24T13:19:03+00:00\",\"dateModified\":\"2022-11-09T08:07:15+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/\"},\"wordCount\":1322,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/struktur_data_datamodeller_beacon_tower_Azure.jpg\",\"articleSection\":[\"Uncategorized @da\"],\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/\",\"url\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/\",\"name\":\"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/struktur_data_datamodeller_beacon_tower_Azure.jpg\",\"datePublished\":\"2022-08-24T13:19:03+00:00\",\"dateModified\":\"2022-11-09T08:07:15+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#primaryimage\",\"url\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/struktur_data_datamodeller_beacon_tower_Azure.jpg\",\"contentUrl\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/struktur_data_datamodeller_beacon_tower_Azure.jpg\",\"width\":1500,\"height\":1002,\"caption\":\"struktur_data_datamodeller_beacon_tower_Azure\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/beacontower.io\\\/da\\\/azure-iot-cloud-and-edge-platform\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#website\",\"url\":\"https:\\\/\\\/beacontower.io\\\/da\\\/\",\"name\":\"Beacon Tower\",\"description\":\"Azure IoT Cloud and Edge Platform\",\"publisher\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/beacontower.io\\\/da\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#organization\",\"name\":\"Beacon Tower\",\"url\":\"https:\\\/\\\/beacontower.io\\\/da\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/BT-logo-web.png\",\"contentUrl\":\"https:\\\/\\\/beacontower.io\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/BT-logo-web.png\",\"width\":400,\"height\":175,\"caption\":\"Beacon Tower\"},\"image\":{\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/company\\\/glaze-about\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/beacontower.io\\\/da\\\/#\\\/schema\\\/person\\\/c241382a256ec0f2de3cc46babd7ab1d\",\"name\":\"Jakob Appel\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g\",\"caption\":\"Jakob Appel\"},\"url\":\"https:\\\/\\\/beacontower.io\\\/da\\\/author\\\/appel\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower","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:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/","og_locale":"da_DK","og_type":"article","og_title":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower","og_description":"N\u00e5r man arbejder med data fra industrielle aktiver, hvad enten det er fra automationssystemer eller direkte fra micro-controllerne, s\u00e5 er det afg\u00f8rende at kunne lave strukturer i sin back-end, der giver mulighed for at kunne beskrive data ud fra en forretningskontekst, og ikke blot en 1:1 gengivelse af \u201dtemp_sensor_123\u201d fra \u201dmachine1234abc\u201d. Man vil med andre […]","og_url":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/","og_site_name":"Beacon Tower","article_published_time":"2022-08-24T13:19:03+00:00","article_modified_time":"2022-11-09T08:07:15+00:00","og_image":[{"width":1500,"height":1002,"url":"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg","type":"image\/jpeg"}],"author":"Jakob Appel","twitter_card":"summary_large_image","twitter_misc":{"Skrevet af":"Jakob Appel","Estimeret l\u00e6setid":"5 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#article","isPartOf":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/"},"author":{"name":"Jakob Appel","@id":"https:\/\/beacontower.io\/da\/#\/schema\/person\/c241382a256ec0f2de3cc46babd7ab1d"},"headline":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata","datePublished":"2022-08-24T13:19:03+00:00","dateModified":"2022-11-09T08:07:15+00:00","mainEntityOfPage":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/"},"wordCount":1322,"commentCount":0,"publisher":{"@id":"https:\/\/beacontower.io\/da\/#organization"},"image":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#primaryimage"},"thumbnailUrl":"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg","articleSection":["Uncategorized @da"],"inLanguage":"da-DK","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/","url":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/","name":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata - Beacon Tower","isPartOf":{"@id":"https:\/\/beacontower.io\/da\/#website"},"primaryImageOfPage":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#primaryimage"},"image":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#primaryimage"},"thumbnailUrl":"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg","datePublished":"2022-08-24T13:19:03+00:00","dateModified":"2022-11-09T08:07:15+00:00","breadcrumb":{"@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#primaryimage","url":"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg","contentUrl":"https:\/\/beacontower.io\/wp-content\/uploads\/2022\/08\/struktur_data_datamodeller_beacon_tower_Azure.jpg","width":1500,"height":1002,"caption":"struktur_data_datamodeller_beacon_tower_Azure"},{"@type":"BreadcrumbList","@id":"https:\/\/beacontower.io\/da\/datastruktur-og-aabne-datamodeller-goer-det-muligt-at-lave-effektiv-ai-med-tidsserie-og-maskindata\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/beacontower.io\/da\/azure-iot-cloud-and-edge-platform\/"},{"@type":"ListItem","position":2,"name":"Datastruktur og \u00e5bne datamodeller g\u00f8r det muligt at lave effektiv AI med tidsserie- og maskindata"}]},{"@type":"WebSite","@id":"https:\/\/beacontower.io\/da\/#website","url":"https:\/\/beacontower.io\/da\/","name":"Beacon Tower","description":"Azure IoT Cloud and Edge Platform","publisher":{"@id":"https:\/\/beacontower.io\/da\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/beacontower.io\/da\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Organization","@id":"https:\/\/beacontower.io\/da\/#organization","name":"Beacon Tower","url":"https:\/\/beacontower.io\/da\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/beacontower.io\/da\/#\/schema\/logo\/image\/","url":"https:\/\/beacontower.io\/wp-content\/uploads\/2021\/04\/BT-logo-web.png","contentUrl":"https:\/\/beacontower.io\/wp-content\/uploads\/2021\/04\/BT-logo-web.png","width":400,"height":175,"caption":"Beacon Tower"},"image":{"@id":"https:\/\/beacontower.io\/da\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/company\/glaze-about"]},{"@type":"Person","@id":"https:\/\/beacontower.io\/da\/#\/schema\/person\/c241382a256ec0f2de3cc46babd7ab1d","name":"Jakob Appel","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/secure.gravatar.com\/avatar\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/154751ee44dd51fb1a3377a2a3c6b4415d5e614f3f0ce8187f0c875a9b728ce9?s=96&d=mm&r=g","caption":"Jakob Appel"},"url":"https:\/\/beacontower.io\/da\/author\/appel\/"}]}},"_links":{"self":[{"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/posts\/35196","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/comments?post=35196"}],"version-history":[{"count":20,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/posts\/35196\/revisions"}],"predecessor-version":[{"id":35446,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/posts\/35196\/revisions\/35446"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/media\/35216"}],"wp:attachment":[{"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/media?parent=35196"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/categories?post=35196"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/beacontower.io\/da\/wp-json\/wp\/v2\/tags?post=35196"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}