How Computers Use Memory Networks to Answer Questions

A method for AI to search through large amounts of stored information by repeatedly 'hopping' through memory to find the most relevant facts for answering a question.

What it covers

This patent describes a way for an AI model to process information by treating a database of knowledge like a long-term memory. When the system receives a question, it converts both the question and the stored facts into mathematical vectors. It then performs a 'hop' operation, where it calculates which facts are most relevant to the question using a probability score. By repeating this process across multiple hops, the system refines its focus, effectively 'reading' through the memory to build a better answer. For example, if you provided a story about a character moving between rooms, the system would use these hops to track the character's location before answering 'Where is the character now?'

What it doesn't cover

• —Does not cover traditional database lookups that rely on exact keyword matching.
• —Does not cover systems that use hard-coded rules or logic trees to find answers.
• —Does not cover non-vectorized storage methods for knowledge entries.
• —Does not cover architectures that do not utilize a multi-hop iterative refinement process.

The clever bit

The system uses a 'continuous weighting function' (like softmax) during the hop process, which allows the model to be trained end-to-end using back-propagation. This means the AI learns how to search its own memory without needing human-labeled instructions on which specific facts are important.

Why it matters

This technology was a significant step in the evolution of Natural Language Processing (NLP) at Meta (formerly Facebook). It helped move AI beyond simple pattern matching toward models that can reason over long-term context, which is a foundational requirement for modern large language models.

Real-world examples

• 1.Question-answering chatbots
• 2.Automated document summarization tools
• 3.Context-aware AI assistants