US 6,029,195 · Granted 2000-02-22

The 2000 Patent That Invented Your Personalized News Feed

This patent describes an automated system that learns what kinds of news articles you like, then ranks new articles by how closely they match your interests. It's like having a personal librarian who reads everything and hands you only the stuff you actually care about—plus a secret proxy server that keeps your reading taste private from advertisers and other third parties.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The patent covers a method for automatically analyzing news articles (or other 'desirable objects') by measuring how often specific words appear in each article relative to their overall usage across all articles, then comparing those profiles against individual user interest profiles to rank-order content. What's protected here is both the technique for building these 'target profiles' and the system for matching them against user preferences to deliver customized ranked lists. It also covers the use of a cryptographic proxy server to shield user interest data from third-party access.

Why it matters

This patent represents an early foundational approach to personalized content recommendation—a core mechanic now embedded in social media feeds, streaming platforms, and news aggregators. Filed in 1997 and granted in 2000, it arrived at the birth of mass-market internet publishing, when the ability to automatically filter signal from noise across thousands of articles was a novel and valuable problem. The inclusion of privacy-protecting cryptography also reflects early recognition that tracking user preferences raises privacy concerns.

Real-world use

Every time you open a news app or social media feed and see articles ranked by relevance to your interests rather than strict publication time, you're seeing the core idea this patent protects in action.

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 6,029,195
Filing date: 1997-12-05
Grant date: 2000-02-22
Assignee: Herz; Frederick S. M.
Inventor(s): HERZ; FREDERICK S. M.
CPC class: H04N21/44224

View original record on Google Patents →

Want to file your own patent?

If you're building a content recommendation or discovery tool, use our free patentability scanner to check whether your approach overlaps with existing claims in this space.

Free patentability scan