Question Answering using trained generative adversarial network based modeling of text

This invention describes a system that answers questions by using a special AI called a GAN generator. This generator creates a 'bag of words and phrases' (BoN) that represents what a correct answer should contain. The system then compares potential answers to this BoN to find the best match and selects it. The claims narrow this to the generator specifically creating a BoN representing ngrams in a correct answer.

Why it matters: Filed before large language models (LLMs) could directly generate and evaluate answers. The specific GAN-BoN approach for n-gram comparison is now a less competitive method.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, neural networks, NLP

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10