US 5,758,257 · Granted 1998-05-26

The 1998 Patent That Invented Personalized TV Before Netflix

Imagine a cable TV system that learns what kinds of shows you like, then automatically creates custom channels just for you—showing movies and programs ranked by how much it thinks you'll enjoy them. This patent from 1998 describes exactly that idea: using your preferences to predict what you'd want to watch and serving it up before you even ask.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The claim covers a system that builds a customer profile based on what you care about (genre, actors, length, rating), then compares your preferences to the actual characteristics of available programs to score how much you'd like each one. It protects the method of generating 'virtual channels'—personalized program lineups created dynamically from an agreement matrix—plus the feedback loops that let the system learn and improve over time as it watches what you actually choose.

Why it matters

Filed in 1994 and granted in 1998, this patent describes the core mechanics of what became on-demand and algorithmic recommendation systems. It predates Netflix's streaming model and algorithm-driven recommendations by years, capturing the fundamental idea of matching viewer profiles to content profiles to predict satisfaction—a concept that became worth billions in the streaming era.

Real-world use

Every time a streaming service shows you a 'Recommended for You' section or a personalized homepage tailored to your watch history, you're looking at technology descended from the logic this patent locked down.

Original USPTO abstract

A system and method for scheduling the receipt of desired movies and other forms of data from a network which simultaneously distributes many sources of such data to many customers, as in a cable television system. Customer profiles are developed for the recipient describing how important certain characteristics of the broadcast video program, movie or other data are to each customer. From these profiles, an "agreement matrix" is calculated by comparing the recipient's profiles to the actual profiles of the characteristics of the available video programs, movies, or other data. The agreement matrix thus characterizes the attractiveness of each video program, movie, or other data to each prospective customer. "Virtual" channels are generated from the agreement matrix to produce a series of video or data programming which will provide the greatest satisfaction to each customer. Feedback paths are also provided so that the customer's profiles and/or the profiles of the video programs or other data may be modified to reflect actual usage. Kiosks are also developed which assist customers in the selection of videos, music, books, and the like in accordance with the customer's objective profiles.

Patent details

Publication number: US 5,758,257
Filing date: 1994-11-29
Grant date: 1998-05-26
Assignee: Herz; Frederick / Ungar; Lyle / Zhang; Jian / Wachob; David / Salganicoff; Marcos
Inventor(s): HERZ; FREDERICK, UNGAR; LYLE, ZHANG; JIAN, WACHOB; DAVID, SALGANICOFF; MARCOS
CPC class: H04N21/44222

View original record on Google Patents →

Want to file your own patent?

If you're building an app that recommends products or content based on user behavior, search our database to see how older patents in this space might affect your launch plans.

Free patentability scan