RTL荷兰文, 是欧洲最大广播集团的一部分, uses artificial intelligence (AI) to optimize the value and discoverability of video assets and automate the creation of video trailers and thumbnails. 在竞争激烈的媒体行业, having more compelling content that entices interaction is critical to increasing advertising revenue.
RTL chose 888贵宾会登录 to deliver the data-driven machine learning (ML) automation, 规模, and 再现性 the team needed to work with massive amounts of video and other media assets generated daily.
RTL荷兰文 broadcasts to millions of daily TV viewers, along with delivering streaming content that garners hundreds of millions of monthly 网上的观点. Its parent, RTL Group, is Europe’s largest broadcaster and part 贝塔斯曼是世界上最大的媒体集团之一.
One of the key growth metrics for RTL荷兰文 is viewership, but optimizing the value and discoverability of video assets is an extremely 劳动密集型的努力. 这使得自动化和团队的时机成熟了 applied machine learning to optimize key aspects of its video platform, like creating thumbnails and trailers, picking the right thumbnail for those 预告片，以及在视频流中插入广告内容. 右边的缩略图 might not seem crucial but it makes all the difference in the world to 无论某人是否点击或永远跳过视频.
“We want to use artificial intelligence to make sure we optimally apply our human intelligence, so our teams can be more creative and connected,” RTL荷兰公司的高级数据科学家文森特·库普斯说. “问题 is that it’s not easy to apply AI to managing unstructured content; these content operations are computationally complex, making video AI 从数据科学的角度来看具有挑战性.”
的 team solved this problem by breaking complicated tasks into simpler subtasks, eliminating larger task-specific models in favor of an assembly 可重用模块. 这种模块化的方法允许机器学习 the company to train the AI on various elements of the video stream across visual (frame extraction, shot segmentation, facial recognition), audio (tagging, speech identification, musical genre) and text (language 检测，关键短语)子任务.
888贵宾会登录 provides the data layer that allows machine learning teams to productionize and 扩展他们的机器学习生命周期. 凭借888贵宾会登录行业领先的数据版本管理， pipelines and lineage, teams gain data-driven automation, petabyte scalability and end-to-end 再现性. For RTL荷兰文, 888贵宾会登录 was the key to combining and orchestrating the 以统一的方式将各种子任务转化为视频规模化处理. 不仅如此，还有视频处理 资源密集型. 888贵宾会登录的 incrementality allowed the team to only process new videos as they arrive or change, rather than reprocessing everything from scratch. 这个交付 速度极快，节省时间和金钱.
RTL荷兰也需要跟踪元数据和 从视频流中提取的内容进行评估 并提高其人工智能模型的有效性. 888贵宾会登录的 immutable lineage ensured this endto-end 再现性. 更重要的是， 888贵宾会登录允许团队倒回到旧版本 的代码，数据或模型，所以如果一个新的缩略图或 Clip的表现不如以前的版本 they could roll back the change to the more highperformance versions.
最后，视频数据是拍字节级数据，这使得 厚皮动物的能力扩展到几拍字节 对于实现RTL荷兰的目标至关重要. 888贵宾会登录的 固有的并行处理和代码不可知论 让团队处理了大量的 视频无需代码更改，同时其数据可伸缩 版本控制优化了存储和计算成本.
With 888贵宾会登录, RTL荷兰文 can easily combine various AI models to solve much more complex video challenges, such as identifying the optimum point for ad insertion, or selecting 剪辑一个引人注目的缩略图.
决定广告的插入是很棘手的. 商业规则规定了广告频率，但只是播放 ad at predetermined intervals will disrupt dialogue or ruin a key scene, substantially degrading 观看体验. Ideally, the ad should appear between scene and dialogue transitions – something the team at RTL荷兰文 has trained its AI to recognize.
In this instance, videos are housed in the cloud on Azure, S3 or a similar service, and imported into a video repository in 888贵宾会登录, where pipelines extract the information necessary to detect an ideal ad insertion point, staying in line with business rules about ad frequency, content restrictions, 和更多的. 边界检测确定镜头过渡与高 probability based on frame-to-frame changes in color histograms. 最后, speech detection ensures a break in the dialogue so that speakers aren’t cut 一句话中间出现了一个出人意料的广告. 所有这些模型结合在一起 allow automated ad insertion without degrading 观看体验.
Koops notes that this approach – creating simple subtasks that are orchestrated through 888贵宾会登录 to solve complex challenges – can apply 跨领域. 它允许该公司使用或调整公开可用的人工智能 模型的独特需求. “这种编排适用于任何任务 can be distilled down into smaller components; it’s much more efficient and flexible than creating monolithic models, and with 888贵宾会登录 it’s easy to 重新组合组件以解决其他有趣的挑战.”
的 team continues to focus on the their key growth metrics of viewership, 优化视频的价值和可发现性 以及其他广播资产. Letting the computer and ML to do this reduces this 劳动密集型的努力.
With their new scalable platform they are creating new offerings that are broader in scope and add additional services that their 客户需要.