PREDICTING THE POPULARITY OF A SONG BASED ON HARMONIC SURPRISE

Patent №

US 11,048,747

Granted

2021-06-29

Filed 2020

Owner

GEORGETOWN UNIVERSITY

+1 more

Lab

AI components

3

ml · nlp · planning

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16786816

A system and method for estimating the popularity of song by calculating the (absolute and/or contrastive) harmonic surprise of each song in a corpus of music data, determining the popularity of each song in the corpus (e.g., based on a music chart, downloads, online streams), determining correlations between harmonic surprise and popularity, and estimating the popularity of an individual song based on the (absolute and/or contrastive) harmonic surprise of the individual song and the correlations between harmonic surprise and popularity.

Machine learningNatural languagePlanningG06F 16/65G06F 16/61G06F 16/683G10H 1/06G10H 1/383G10H 2210/031G10H 2210/091G10H 2210/576+1 more

AI classification

Natural language1.00
Machine learning0.98
Planning0.61
Knowledge representation0.18
Vision0.02
Speech0.01
AI hardware0.00
Evolutionary computation0.00

Ownership

GEORGETOWN UNIVERSITY

assignment · 548290168

SECRET CHORD LABORATORIES, INC.

assignment · 548300603

Assignors

GEORGETOWN UNIVERSITY

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC