Using OpenAI’s CLIP to Search for Design Patents

 By Medium - 2021-03-01

Description

This article shows how to use natural language to search and find over sixty thousand industrial designs that have entered the public domain since 2002.

Summary

  • Using natural language to search and find over sixty thousand industrial designs that have entered the public domain since 2002 Everybody knows about using patents as a way to protect new inventions.
  • Design Patents As I mentioned above, design patents protect the appearance, not the functional aspects of inventions.
  • But the image embeddings will capture some key aspects of the design, like the “curved water faucet” example above.
  • Check out the appendix below to see some sample search results.

 

Topics

  1. NLP (0.28)
  2. UX (0.24)
  3. Coding (0.03)

Similar Articles

DALL·E: Creating Images from Text

By OpenAI - 2021-01-05

We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.

Implementing Neumorphism in user interfaces

By Medium - 2020-11-27

Became viral a few months ago, Neumorphism has emerged as a must-have interface design for all designers. The term Neumorphism refers to an approach that uses a combination of highlights and shadows…

A Beginner’s Guide to the CLIP Model

By KDnuggets - 2021-03-11

CLIP is a bridge between computer vision and natural language processing. I'm here to break CLIP down for you in an accessible and fun read! In this post, I'll cover what CLIP is, how CLIP works, and ...