InnoVAE: Generative AI for Understanding Patents and Innovation

50 Pages Posted: 13 Apr 2022

See all articles by Zhaoqi Cheng

Zhaoqi Cheng

Boston University - Questrom School of Business

Dokyun Lee

Boston University - Questrom School of Business

Prasanna Tambe

Wharton School, U. Pennsylvania

Date Written: March 2022

Abstract

A lack of interpretability limits the use of common unsupervised learning techniques (e.g., PCA, t-SNE) in contexts where they are meant to augment managerial decision-making. We develop a generative deep learning model based on a Variational AutoEncoder (“InnoVAE”) that converts unstructured patent text into an interpretable, spatial representation of innovation (“Innovation Space”). After validating the internal consistency of the model, we apply it to three decades of computing system patents to show that our approach can be used to construct economically interpretable measures—at scale—that characterize a firm’s IP portfolio from the text of its patents, such as whether a patent is a breakthrough innovation, the volume of intellectual property enclosed by a portfolio of patents, or the density of patents at a point in Innovation Space. We show that for explaining innovation outcomes, these interpretable, engineered features have explanatory power that augments and often surpasses the structured patent variables that have informed the very large and influential literature on patents and innovation. Our findings illustrate the potential of using generative methods on unstructured data to guide managerial decision-making.

Keywords: Patents, Creativity, Generative AI, Artificial Intelligence, Variational Autoencoder, Innovation Space, Disentangled Representation Learning, Invention of a Method of Invention, Interpretability

Suggested Citation

Cheng, Zhaoqi and Lee, Dokyun and Tambe, Prasanna, InnoVAE: Generative AI for Understanding Patents and Innovation (March 2022). Available at SSRN: https://ssrn.com/abstract=3868599 or http://dx.doi.org/10.2139/ssrn.3868599

Zhaoqi Cheng

Boston University - Questrom School of Business ( email )

595 Commonwealth Avenue
Boston, MA MA 02215
United States

Dokyun Lee (Contact Author)

Boston University - Questrom School of Business ( email )

595 Commonwealth Avenue
Boston, MA MA 02215
United States

Prasanna Tambe

Wharton School, U. Pennsylvania ( email )

Philadelphia, PA 19104
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
873
Abstract Views
2,882
Rank
44,301
PlumX Metrics