Customized content stream utilizing dwelltime-based machine learning

This invention describes a system for personalizing the content you see online. It works by measuring how long you spend looking at each piece of content, known as "dwelltime." This exact dwelltime is then used to teach a computer system what kinds of content you prefer, based on the content's characteristics. The system then uses this learned preference to select and present new content that it predicts you will spend more time viewing.

Why it matters: Filed in 2017, this invention predates the widespread availability of highly optimized, scalable machine learning platforms and advanced behavioral analytics tools that make real-time dwelltime-based training and content recommendation significantly more efficient and effective today. The specific method of using dwelltime directly as a training label has become more practical with modern ML architectures.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, machine learning, data engineering

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10