# How Wearable Devices Use Location and Biometrics to Know Who You Are > This patent describes how a computer system can figure out who is using a wearable device by combining its location data with biometric information like a face scan or voice recording. - **Patent:** US 20220189458 - **Original title:** Speech based user recognition - **Owner:** Amazon Technologies - **Status:** Active - **Times cited:** 1 - **Field:** consumer_electronics, software, telecommunications, ai_ml ## What it does The patent describes a computer-implemented method (Claim 21) for identifying a user of a wearable device. It works by receiving two types of data: first, location data for the wearable device (Claim 21), and second, biometric data such as image data of a face or audio data of a voice (Claim 21). The system then processes both the location data and the biometric data together to determine the user's identity (Claim 21). For example, if a smartwatch (wearable device) is detected in a specific room in a house (location data) and then records a voice command (audio data), the system can use both pieces of information to confirm if the voice belongs to the known owner of that smartwatch, especially if that owner is typically in that room. The system can also use a known user's profile to compare the biometric data (Claim 22, 23) and consider the type of wearable device (Claim 29) to improve accuracy. ## What it does NOT cover - Does not cover user identification solely based on biometric data (e.g., just a fingerprint scan) without also using location data or device type. - Does not cover systems that identify users without involving a "wearable device" as defined by the claims. - Does not cover identification methods that rely only on a user's password or PIN without any biometric or location input. - Does not cover systems that determine identity without combining at least two distinct data types: location data and biometric data (image or audio). ## The clever bit The novelty lies in combining location data (like being inside a specific room or a geographic coordinate) with biometric data (face or voice) to determine a user's identity, especially in the context of a wearable device. This multi-factor approach makes identification more robust than relying on biometrics or location alone. ## Real-world examples 1. Smartwatches unlocking features when worn by the owner in a specific location. 2. Smart glasses authenticating the wearer based on their face and GPS data. 3. Fitness trackers confirming user identity for secure health data access. 4. Voice assistants on earbuds recognizing the user only when in a trusted location. ## Why it matters This technology is important for making wearable devices more secure and personalized. By combining location and biometric data, devices can offer more reliable user authentication, which is crucial for accessing sensitive information or making payments. This approach helps prevent unauthorized use and enables seamless, context-aware experiences. ## Frequently asked questions ### What does How Wearable Devices Use Location and Biometrics to Know Who You Are cover? This patent describes how a computer system can figure out who is using a wearable device by combining its location data with biometric information like a face scan or voice recording. ### Who owns patent US 20220189458? This patent is owned by Amazon Technologies. ### When does this patent expire? This patent is expected to expire on January 26, 2042, when the invention enters the public domain. ### What is patent US 20220189458 cited by? This patent has been cited by 1 later patents that build on its ideas. ### What problem does this patent solve? This technology is important for making wearable devices more secure and personalized. By combining location and biometric data, devices can offer more reliable user authentication, which is crucial for accessing sensitive information or making payments. This approach helps prevent unauthorized use and enables seamless, context-aware experiences. ### What does this patent NOT cover? Does not cover user identification solely based on biometric data (e.g., just a fingerprint scan) without also using location data or device type. **Full plain-English explainer:** https://patentbrief.org/patent/us/20220189458/speech-based-user-recognition **Original patent:** https://patents.google.com/patent/US20220189458 --- _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 Voice Assistants Recognize Who is Talking](https://patentbrief.org/patent/us/11514901/anchored-speech-detection-and-speech-recognition) — This patent describes a system that uses a recorded voice sample to identify if new speech comes from the same person, allowing voice assistants to only respond to specific users. - [How Voice Assistants Change Their Speech Based on How You Talk](https://patentbrief.org/patent/us/10276149/dynamic-text-to-speech-output) — This patent describes a system where a voice-controlled device adjusts its text-to-speech output characteristics, like speed or tone, based on the user's speaking habits or current situation, making responses feel more natural and personalized. - [How Wearable Devices Act as Secure Bridges for Transactions](https://patentbrief.org/patent/us/9699159/microsoft-teams) — A system where a wearable device acts as a secure middleman between your phone and a payment terminal or electronic lock to verify your identity and complete transactions. - [How Sonos Speakers Use Personalized Wake Words to Recognize Different Users](https://patentbrief.org/patent/us/9965247/icloud-drive) — A system that lets multiple people control a shared speaker by using unique voice-trigger words to link their specific music accounts and preferences. - [Making Computer Voices Sound More Expressive from Your Speech](https://patentbrief.org/patent/us/11062694/text-to-speech-processing-with-emphasized-output-audio) — This patent describes how a computer listens to your spoken words, figures out which parts you emphasized, and then makes its own computer-generated voice emphasize those same parts when it speaks back.