# How a Digital Assistant Launches Apps Using Your Voice

> This patent describes how a digital assistant like Siri uses your spoken words and understanding of your conversation to figure out what you want and launch the right app.

- **Patent:** US 9548050
- **Original title:** Intelligent automated assistant
- **Owner:** Apple Inc
- **Granted:** 2017
- **Status:** Active
- **Times cited:** 211
- **Field:** consumer_electronics, software, telecommunications, ai_ml

## What it does

This patent details a method for a digital assistant to launch applications on a device using speech. The system provides a graphical interface with a speech-based conversational element, displaying part of the ongoing chat (Claim 1). It gathers "context information" from previous interactions, which could be earlier speech (Claim 2) or non-speech input (Claim 6). When a user speaks, the system processes this "speech input" to figure out their "user intent" (Claim 1). If the intent is to open an app, the system launches that app *external* to the assistant's own interface and then provides a response based on what the user said and the gathered context (Claim 1). For example, if you say "Open Maps to find coffee," the assistant would launch the Maps app and potentially show coffee shops, while also giving a spoken or on-screen confirmation.

## What it does NOT cover

- Does not cover launching applications without a speech input (e.g., tapping an icon).
- Does not cover systems that only process speech commands without maintaining or using "context information" to understand intent.
- Does not cover digital assistants that execute tasks *only* within their own interface without invoking external applications.
- Does not cover systems where the launched application runs *inside* the conversational interface, rather than "external" to it.
- Does not cover assistants that don't display "at least a portion of a conversational interaction."

## The clever bit

The novelty lies in combining a speech-based conversational interface with the ability to understand user intent, leverage conversational context, and then specifically invoke *external* software applications while still providing a relevant response. This allows the assistant to act as a smart intermediary, bridging user requests to the device's full app ecosystem.

## Real-world examples

1. Apple Siri
2. Google Assistant
3. Amazon Alexa (on devices with screens and app integration)
4. Samsung Bixby

## Why it matters

This patent is foundational to how modern voice assistants operate, particularly in their ability to integrate with the device's other applications. Assigned to Apple, it underpins core functionality seen in Siri, which revolutionized how users interact with smartphones. Its focus on understanding "user intent" and "context information" allows for more natural and effective voice commands, moving beyond simple keyword recognition.

## Frequently asked questions

### What does How a Digital Assistant Launches Apps Using Your Voice cover?

This patent describes how a digital assistant like Siri uses your spoken words and understanding of your conversation to figure out what you want and launch the right app.

### Who owns patent US 9548050?

Apple Inc owns this patent, granted in 2017.

### When does this patent expire?

This patent is expected to expire on January 17, 2037, when the invention enters the public domain.

### What is patent US 9548050 cited by?

This patent has been cited by 211 later patents that build on its ideas.

### What problem does this patent solve?

This patent is foundational to how modern voice assistants operate, particularly in their ability to integrate with the device's other applications. Assigned to Apple, it underpins core functionality seen in Siri, which revolutionized how users interact with smartphones. Its focus on understanding "user intent" and "context information" allows for more natural and effective voice commands, moving beyond simple keyword recognition.

### What does this patent NOT cover?

Does not cover launching applications without a speech input (e.g., tapping an icon).

**Full plain-English explainer:** https://patentbrief.org/patent/us/9548050/continuity-handoff

**Original patent:** https://patents.google.com/patent/US9548050

---

_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 Digital Assistants Control Apps and Ask for More Information](https://patentbrief.org/patent/us/11204787/github-copilot-code-generation-ai) — This patent describes how a digital assistant on a device can understand what a user wants from a natural language command, find the right app, get a step-by-step guide from another device, and then ask the user for more details on the screen to complete the task with that app.
- [How Smart Speakers Know You're Talking to Them After a Command](https://patentbrief.org/patent/us/11361763/detecting-system-directed-speech) — This patent describes how a smart speaker system can tell if follow-up speech is meant for it, even without a "wake word," by analyzing voice activity and partial speech recognition results using an AI model.
- [How Assistant Systems Combine Information About One Thing from Many Places](https://patentbrief.org/patent/us/11704899/resolving-entities-from-multiple-data-sources-for-assistant-systems) — This patent describes a system that gathers all known information about a single person, place, or thing from various sources and combines it into one complete profile for an assistant system.
- [How AI Predicts Who Will Speak Next in a Conversation](https://patentbrief.org/patent/us/11645473/palm-pathways-language-model) — IBM's patent describes a system that uses neural networks to analyze speech patterns and intentions to predict which person will talk next in a conversation.
- [How Software Detects What You Want Based on Your Social Media Posts](https://patentbrief.org/patent/us/8521818/facebook-share-button) — A system that reads your social media posts to figure out your intent, then automatically serves ads or updates your profile based on how likely you are to actually buy or do something.
