# How Computers Find Hidden Connections Between Different Fields of Knowledge

> A method for finding related ideas in completely different subjects by using math to map how words appear together, even when the subjects use different vocabulary.

- **Patent:** US 6523026
- **Original title:** Method for retrieving semantically distant analogies
- **Owner:** Huntsman International LLC
- **Granted:** 2003
- **Status:** Public domain (expired)
- **Times cited:** 456
- **Field:** ai_ml, software, telecommunications

## What it does

This patent describes a way to find 'analogies' between two unrelated fields, such as finding a biological solution to a mechanical engineering problem. It works by first analyzing a source domain (like a library of biology papers) to create a high-dimensional map of how words appear together. It then uses this map—represented as vectors in a multi-dimensional space—to search a second, completely different domain (like a library of engineering patents) where the same words might not even appear. By comparing the 'meaning' of the words based on their context in the first domain, the system can pull up relevant documents from the second domain that share a functional relationship despite having no overlapping keywords.

## What it does NOT cover

- Does not cover simple keyword-based search engines that rely on matching exact words or synonyms.
- Does not cover systems that require the target domain to contain the same vocabulary as the source domain.
- Does not cover manual categorization or human-led tagging of documents.
- Does not cover basic vector search that does not specifically map relationships across semantically distant domains.

## The clever bit

The system ignores the actual words in the target domain and instead maps them into the 'semantic space' of the source domain, allowing it to find functional equivalents without needing a direct translation or shared dictionary.

## Real-world examples

1. Cross-disciplinary research tools
2. Automated patent landscape analysis
3. AI-driven scientific discovery platforms

## Why it matters

This technology is a precursor to modern cross-domain knowledge discovery and semantic search. It addresses the 'vocabulary mismatch' problem, which is a major hurdle in AI and data science where different industries use different jargon to describe the same underlying physical or logical processes.

## Frequently asked questions

### What does How Computers Find Hidden Connections Between Different Fields of Knowledge cover?

A method for finding related ideas in completely different subjects by using math to map how words appear together, even when the subjects use different vocabulary.

### Who owns patent US 6523026?

Huntsman International LLC owns this patent, granted in 2003.

### When does this patent expire?

This patent has expired and is now in the public domain — anyone can use the invention freely.

### What is patent US 6523026 cited by?

This patent has been cited by 456 later patents that build on its ideas.

### What problem does this patent solve?

This technology is a precursor to modern cross-domain knowledge discovery and semantic search. It addresses the 'vocabulary mismatch' problem, which is a major hurdle in AI and data science where different industries use different jargon to describe the same underlying physical or logical processes.

### What does this patent NOT cover?

Does not cover simple keyword-based search engines that rely on matching exact words or synonyms.

**Full plain-English explainer:** https://patentbrief.org/patent/us/6523026/google-search-query-processing

**Original patent:** https://patents.google.com/patent/US6523026

---

_Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._