US 5,835,087 · Granted 1998-11-10

The 1995 Patent That Invented Your News Feed

Before Netflix recommendations or TikTok's algorithm, this patent figured out how to automatically rank news articles and other content based on what YOU personally find interesting. The system builds a profile of your tastes and then uses it to filter through mountains of information and show you the stuff most likely to matter to you.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The claim covers a system that creates two kinds of profiles: one for each piece of content (like a news article) based on which words appear most often in it, and another for each user based on what types of content they've shown interest in. What's protected here is the automated matching process that compares these profiles to rank-order content for individual users, plus a privacy layer that lets users control who can see their interest profile without revealing their actual identity.

Why it matters

This patent arrived right as the internet was exploding with information. Before algorithmic ranking, finding relevant content in a sea of options was nearly impossible. The patent essentially blueprinted personalized content recommendation—the same concept that powers modern social feeds, streaming services, and search engines today. The privacy component was also ahead of its time, giving users a way to benefit from profiling while staying anonymous.

Real-world use

When Netflix suggests a show you might like, or when a news app highlights stories tailored to your reading history, you're watching this patent's core idea in action—automatically matching what you care about with what's available.

Original USPTO abstract

This invention relates to customized electronic identification of desirable objects, such as news articles, in an electronic media environment, and in particular to a system that automatically constructs both a "target profile" for each target object in the electronic media based, for example, on the frequency with which each word appears in an article relative to its overall frequency of use in all articles, as well as a "target profile interest summary" for each user, which target profile interest summary describes the user's interest level in various types of target objects. The system then evaluates the target profiles against the users' target profile interest summaries to generate a user-customized rank ordered listing of target objects most likely to be of interest to each user so that the user can select from among these potentially relevant target objects, which were automatically selected by this system from the plethora of target objects that are profiled on the electronic media. Users' target profile interest summaries can be used to efficiently organize the distribution of information in a large scale system consisting of many users interconnected by means of a communication network. Additionally, a cryptographically-based pseudonym proxy server is provided to ensure the privacy of a user's target profile interest summary, by giving the user control over the ability of third parties to access this summary and to identify or contact the user.

Patent details

Publication number: US 5,835,087
Filing date: 1995-10-31
Grant date: 1998-11-10
Assignee: Herz; Frederick S. M. / Eisner; Jason M. / Ungar; Lyle H.
Inventor(s): HERZ; FREDERICK S. M., EISNER; JASON M., UNGAR; LYLE H.
CPC class: H04N21/44222

View original record on Google Patents →

Want to file your own patent?

If you're building a consumer app that learns from user behavior, search our database to see how algorithmic personalization patents have evolved since 1998.

Free patentability scan