US 6,460,036 · Granted 2002-10-01

The 2002 Patent That Invented Your Personalized News Feed

Imagine a smart newspaper that learns what topics you care about—sports, music, science—and automatically sorts through thousands of articles to show you only the ones you'd actually want to read. This patent describes exactly that: a system that builds a profile of your interests and uses it to rank articles by relevance, plus a privacy tool that keeps your reading habits secret from advertisers.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The claim covers a system that analyzes articles by measuring how often words appear in them (relative to how common those words are across all articles), then compares those article profiles against a user's interest profile to generate a ranked list of recommended articles. It also protects the underlying method of building these profiles automatically and the cryptographic system that lets users hide their interest data from third parties while still getting personalized recommendations.

Why it matters

This patent is foundational to how modern news aggregation and content recommendation systems work. Filed in 1997 and granted in 2002, it captures the core mechanics of algorithmic content ranking—the same logic that later powered platforms like Google News, news apps, and social media feeds. The privacy proxy component was notably early thinking about user control over personal data, a concern that became central to tech regulation decades later.

Real-world use

When you open Apple News or flip through a personalized news app and see articles sorted by topic relevance, you're experiencing technology directly descended from this patent's core idea of matching user interests to article content automatically.

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 6,460,036
Filing date: 1997-12-05
Grant date: 2002-10-01
Assignee: Pinpoint Incorporated
Inventor(s): HERZ FREDERICK S. M.
CPC class: G06Q30/02

View original record on Google Patents →

Want to file your own patent?

If you're building an app that recommends content to users, search our database to see how similar recommendation patents might intersect with your design before you launch.

Free patentability scan