Intelligent Assistant Task Modification via Speech Input

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing intelligent automated assistants require multiple commands to modify or undo tasks after initiation, making it inefficient for users to change or reverse previously performed tasks.

Innovation Solution

The system allows for the determination and execution of a second task based on a user's speech input that modifies at least a portion of the first task, enabling efficient task modification or reversal without requiring multiple inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the digital assistant requires multiple commands to modify or undo a task, then the task modification capability is reliable, but the user interaction efficiency deteriorates

Engineering Contradiction:
Improveuser interaction efficiencyVSAvoidnumber of inputs required
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system performs preliminary action by maintaining context information about the first task in memory after task initiation. When a second speech input is received, the system can immediately determine whether it refers to modifying the first task without requiring the user to re-specify task details, thus reducing the number of inputs needed while maintaining reliable task modification capability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by analyzing the second user speech input to determine if it contains a modification to the first task. This feedback mechanism allows the system to understand user intent and perform appropriate task modifications or undos based on contextual understanding, improving interaction efficiency without sacrificing reliability

Inventive Principle:
Principle #23Feedback

2Reliability

If the system processes multiple commands to modify tasks, then the task modification accuracy is improved, but the time consumption increases

Engineering Contradiction:
Improvetask modification accuracyVSAvoidtime to modify task
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by preserving context information about the first task parameters, operations, and state in memory immediately after task initiation. This preliminary storage of task context eliminates the need for users to re-specify task details when requesting modifications, thereby reducing time consumption while maintaining accurate task modification through contextual understanding

Inventive Principle:
Principle #10Preliminary action

3Ease of operation

If the digital assistant requires several different commands to undo a task, then the command processing reliability is improved, but the user experience deteriorates

Engineering Contradiction:
Improveuser experienceVSAvoidcommand processing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system applies universality by designing a unified speech input processing mechanism that can handle multiple types of user intents (new tasks, modifications to first task, undos) through a single interface. The same speech processing pipeline and task management system serve multiple functions, simplifying the user experience while maintaining reliable command processing through consistent handling of diverse requests

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11908473B2Task modification after task initiation
Publication Date: 2024.02.20 APPLE INC
  • US11908473B2 patent drawing
  • US11908473B2 patent drawing
  • US11908473B2 patent drawing

AI summary

Systems and processes for operating an intelligent automated assistant are provided. An example process includes, at an electronic device having one or more processors and memory: performing a first task specified in a first user speech input; receiving a second user speech input; and in accordance with a determination that the second user speech input includes a modification to the first task, performing a second task, wherein performance of the second task modifies at least a portion of the performance of the first task.