Contextual Extensible Skills Framework for Intent-Based Add-In Discovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face difficulties in discovering and accessing relevant computing service skills and add-ins associated with those skills, as they often need to manually search for and install add-ins, which interrupts their workflow and requires prior knowledge of available add-ins.

Innovation Solution

A method and system that utilize natural language processing to identify task intents in user inputs, match them with relevant computing service skills and add-ins, and automatically surface and install the necessary skills, leveraging a service manifest and scoring engines to rank and execute the most relevant skills.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users manually search for and install add-ins, then they can access relevant computing service skills, but it interrupts workflow and requires prior knowledge of available add-ins

Engineering Contradiction:
ImproveEase of accessing add-insVSAvoidTime lost to manual search and installation
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-indexing and cataloging all available add-ins and computing service skills in a centralized database before users need them. When a user expresses an intent, the system has already prepared the matching add-ins and can immediately present them for installation or execution, eliminating the need for manual searching during the workflow interruption point.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

An intermediary intent service is introduced between the user and the add-in installation process. This service receives user intents, translates them into queries against the add-in catalog, scores and ranks relevant add-ins, and presents them for selection. This intermediary layer automates the matching process and eliminates the need for users to manually search through available add-ins.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If users need to know add-ins exist to download and install them, then they can access relevant skills, but it creates a barrier to discovering and utilizing available functionality

Engineering Contradiction:
ImproveDiscoverability of add-insVSAvoidEase of discovering add-ins
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system implements feedback mechanisms by monitoring user intents and automatically presenting relevant add-ins as suggestions or recommendations. When users express needs through natural language or interaction patterns, the system provides immediate feedback with tailored add-in recommendations, making the available functionality visible and accessible without requiring users to proactively search or know what exists.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The add-in discovery and installation process becomes self-service oriented. The system automatically detects user needs, queries the add-in catalog, scores relevance based on contextual factors, and presents appropriate add-ins without requiring user initiation of the search process. Users simply express their needs, and the system handles the rest automatically.

Inventive Principle:
Principle #25Self-service

3Productivity

If add-ins are automatically installed based on intent matching, then workflow interruption is reduced, but the system complexity increases

Engineering Contradiction:
ImproveWorkflow efficiencyVSAvoidSystem complexity for intent matching and add-in management
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The complex system is segmented into distinct functional modules: an intent service for processing user inputs, a scoring service for evaluating add-in relevance, an installation service for handling add-in deployment, and a centralized add-in catalog for storage. Each module performs a specific function and can be independently developed, tested, and maintained, reducing overall system complexity despite the automation capabilities.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4046013B1Contextual extensible skills framework across surfaces
Publication Date: 2024.07.24 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4046013B1 patent drawingFigure 1
  • EP4046013B1 patent drawingFigure 2
  • EP4046013B1 patent drawingFigure 3

AI summary

In non-limiting examples of the present disclosure, systems, methods and devices for exposing computing service skills are presented. A task intent associated with a natural language input may be identified. A plurality of add-in matching language models may be applied to the natural language input, wherein each add-in matching language model corresponds to a computing service skill. A score for each of the computing service skills may be generated. Each of the computing service skills may be ranked. A selectable option to execute an add-in associated with a top ranked computing service skill may be caused to be displayed. An indication that a selection of the option has been made may be received. The add-in associated with the top ranked computing service skill may be executed.