Digital Personal Assistant Response Scaling via Device Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Digital personal assistants in mobile devices often provide responses that are not device-specific, leading to inefficiencies, especially when devices lack touch screens or have different operation modes and hardware characteristics.

Innovation Solution

A method that involves detecting the operation mode and hardware characteristics of a computing device to select and provide appropriate response strings and presentation modes for digital personal assistant interactions, using reactive agents and a scaling service to tailor responses to the device's capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a digital personal assistant provides generic responses across all devices, then the system complexity is reduced and ease of manufacture is improved, but the adaptability to different device characteristics and operation modes deteriorates

Engineering Contradiction:
Improveadaptability to device characteristicsVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary detection of device characteristics and operation modes before generating responses. The digital personal assistant identifies the current device type, hardware capabilities, and operational context in advance, then selects pre-prepared response strings that are optimized for those specific conditions, avoiding the need for complex real-time adaptation logic

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the parameters of responses based on detected device characteristics. Different response strings with varying levels of detail, formatting, and interaction instructions are selected according to device parameters such as screen presence, processing power, and operation mode, allowing the same digital personal assistant to adapt its output without structural modifications

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If response strings are customized for each device type and operation mode, then the adaptability and user experience are improved, but the device complexity and processing requirements increase

Engineering Contradiction:
Improveuser experienceVSAvoidprocessing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The response generation system is segmented into distinct components: device characteristic detection, operation mode identification, and response string selection. Each component handles a specific aspect of the adaptation process independently, reducing the complexity of any single component while maintaining overall system effectiveness in providing device-specific responses

Inventive Principle:
Principle #1Segmentation

3Loss of information

If the digital personal assistant detects operation mode and hardware characteristics for each interaction, then the relevance of responses is improved, but the processing time and energy consumption increase

Engineering Contradiction:
Improverelevance of responsesVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

Device characteristic detection and response string selection are performed as preliminary actions before the actual user interaction proceeds. By identifying the device type, hardware capabilities, and operation mode in advance, the system prepares appropriate response strings that can be immediately deployed during user interaction, minimizing delays and ensuring relevant responses without significant processing time penalties

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9690542B2Scaling digital personal assistant agents across devices
Publication Date: 2017.06.27 MICROSOFT TECHNOLOGY LICENSING LLC
  • US9690542B2 patent drawing
  • US9690542B2 patent drawing
  • US9690542B2 patent drawing

AI summary

A method for providing digital personal assistant responses may include receiving, by a digital personal assistant associated with a plurality of reactive agents, a user input initiating a dialog with the digital personal assistant within the computing device. In response to receiving the input, an operation mode of the computing device may be detected from a plurality of available operation modes. One of the plurality of reactive agents can be selected based on the received input. A plurality of response strings associated with the selected reactive agent can be accessed. At least one of the plurality of response strings is selected based at least on the operation mode and at least one hardware characteristic of the computing device. The selected at least one of the plurality of response strings is providing during the dialog, as a response to the user input.