Storyblocks Adds AI to Improve Content Search and Recommendations

Storyblocks, a subscription-based stock media platform with video creation and workflow functionality, has unveiled search enhancements powered by artificial intelligence.

Recent improvements include the following:

• Prioritization of fresher content in its search results through a proprietary algorithm that evaluates the performance of new content every four hours.
• An in-house machine learning model based on the BERT framework, allowing the platform to analyze how users engage with content and refine search result rankings in near-realtime.
• AI technology to identify the most pertinent thumbnail in video search results.
• OpenAI's large language model to enhance search capabilities, delivering comprehensive results that transcend users' initial queries.
• Metadata enhancements and computer vision technology that can aggregate pertinent search results, recommend alternative scenes, and surface additional clips featuring specific individuals.
• User behavior data to suggest complementary pairings between different types of creative assets, such as videos, images, and audio tracks; analyze music tracks by rendering songs as spectrograms to identify and recommend tracks that are significantly similar.

"At Storyblocks, we're harnessing the power of AI to revolutionize the way creators discover and use content," said Lucy Huang, senior vice president of product and engineering at Storyblocks, in a statement. "By delivering faster, more relevant and more representative search results, we're not just streamlining creative workflows, we're empowering our global community of artists and customers to create inclusive and impactful work. Our commitment to curating a diverse and top-quality library, combined with cutting-edge technology, sets us apart in the stock media industry."