One-to-many automatic content generation

US11868790B2 · kind B2 · utility

Assignee

• Salesforce, Inc. · US

Inventors

• Michael Sollami · Cambridge, US
• Sönke Rohde · San Francisco, US
• Alan Martin Ross · San Francisco, US
• David James Woodward · Bozeman, US
• Jessica Lundin · Seattle, US
• Owen Winne Schoppe · Orinda, US
• Brian J. Lonsdorf · Belmont, US
• Aashish Jain · Bengaluru, IN

Key dates

• Filing date: Jan 26, 2022
• Grant date: Jan 9, 2024
• Expiry date: Feb 5, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V30/19173
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.