# How AI Learns New Tasks Using Old Data Labels > A method for helping AI models understand new topics by grouping similar labels from different datasets into a shared, broader category. - **Patent:** US 11062228 - **Original title:** Transfer learning techniques for disparate label sets - **Owner:** Microsoft Technology Licensing LLC - **Granted:** 2021 - **Status:** Active - **Times cited:** 4 - **Field:** ai_ml, software, telecommunications ## What it does This patent describes a way to teach an AI model about a new subject by using knowledge from a subject it already knows. It works by turning labels (like 'weather' or 'flight status') into mathematical vectors, which are lists of numbers that represent their meaning. The system then uses clustering algorithms to find common ground between these different labels, creating a 'coarse label' that acts as a bridge. For example, if the AI knows 'book flight' and 'reserve seat,' it can use this shared 'coarse' category to better understand a new, related task like 'check-in for flight' even if it has very little training data for that specific task. ## What it does NOT cover - Does not cover systems that rely solely on manually defined rules rather than vector-based clustering. - Does not cover models that perform transfer learning without first creating a coarse label set as an abstraction layer. - Does not cover the specific hardware architecture, only the software-based method of label mapping. ## The clever bit Instead of trying to map labels directly from one domain to another, it creates an intermediate 'coarse' layer. This abstraction acts as a translator, allowing the model to see the semantic relationship between labels that might look completely different on the surface. ## Real-world examples 1. Virtual assistants like Microsoft Cortana or Alexa 2. Customer service chatbots 3. Natural language understanding modules in search engines ## Why it matters Training AI models from scratch is expensive and requires massive amounts of data. This technique allows companies to build smarter virtual assistants and chatbots by recycling knowledge across different domains, making AI more efficient and capable of handling new user requests without needing millions of new examples. ## Frequently asked questions ### What does How AI Learns New Tasks Using Old Data Labels cover? A method for helping AI models understand new topics by grouping similar labels from different datasets into a shared, broader category. ### Who owns patent US 11062228? Microsoft Technology Licensing LLC owns this patent, granted in 2021. ### When does this patent expire? This patent is expected to expire on July 13, 2041, when the invention enters the public domain. ### What is patent US 11062228 cited by? This patent has been cited by 4 later patents that build on its ideas. ### What problem does this patent solve? Training AI models from scratch is expensive and requires massive amounts of data. This technique allows companies to build smarter virtual assistants and chatbots by recycling knowledge across different domains, making AI more efficient and capable of handling new user requests without needing millions of new examples. ### What does this patent NOT cover? Does not cover systems that rely solely on manually defined rules rather than vector-based clustering. **Full plain-English explainer:** https://patentbrief.org/patent/us/11062228/gpt-3-few-shot-learning **Original patent:** https://patents.google.com/patent/US11062228 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How Computers Find Hidden Connections Between Different Fields of Knowledge](https://patentbrief.org/patent/us/6523026/google-search-query-processing) — 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. - [Automated AI for Adapting to New Data Without Retraining](https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement) — This patent describes an automated system that builds artificial intelligence models capable of adapting to new, different data without needing full retraining, by learning to ignore irrelevant changes. - [Teaching Computers to Understand Document Similarity Using AI](https://patentbrief.org/patent/us/10909459/federated-learning) — This patent describes a way to train a computer program (a neural network) to understand how similar documents are to each other, by showing it examples and teaching it to group similar ones together and separate dissimilar ones. - [Training AI Models Together with Unlabeled Data Using a Teacher](https://patentbrief.org/patent/us/20220012637/federated-teacher-student-machine-learning) — This patent describes a way for multiple AI systems to learn together from data that hasn't been manually labeled, using a 'teacher' AI to create temporary labels for a 'student' AI. - [How to Shrink Large AI Models Using Knowledge Distillation](https://patentbrief.org/patent/us/10289962/deep-q-networks-dqn) — A method for teaching small, efficient AI models to mimic the complex decision-making patterns of much larger, more powerful neural networks.