Contact Resolution for Voice-Activated Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing communication systems face challenges in accurately identifying and disambiguating contacts with similar names when users provide voice commands, leading to confusion and incorrect contact selection.

Innovation Solution

A method and system that utilize speech-processing and natural language understanding to analyze voice commands, generate text data, and query contact lists using device identifiers, applying disambiguation rules to narrow down contact options and confirm the intended contact through user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If speech-processing and natural language understanding are used to analyze voice commands and query contact lists, then contact identification accuracy is improved, but system complexity increases

Engineering Contradiction:
Improvecontact identification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The contact resolution process is divided into distinct stages: voice command reception, speech-to-text conversion, natural language understanding, contact list querying, disambiguation rule application, and user confirmation. Each stage handles a specific aspect of the problem, making the overall complex system manageable and maintainable while achieving high accuracy in contact identification.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary components such as the speech-processing system that converts voice to text, and the natural language understanding system that bridges voice commands and contact database queries. These intermediaries translate between different data formats and representations, enabling accurate contact identification while managing system complexity through modular architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If disambiguation rules are applied to narrow down contact options, then contact selection accuracy is improved, but processing time increases

Engineering Contradiction:
Improvecontact selection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies disambiguation rules preliminarily to filter and rank contact options before presenting them to the user. By pre-processing the contact list using various disambiguation criteria (such as recent communications, contact frequency, and contextual relevance), the system reduces the number of contacts requiring user review, thus improving accuracy while minimizing additional processing time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements a tiered disambiguation approach where the most critical disambiguation rules are applied first to quickly narrow down the contact list. If the top result has sufficient confidence, the system may skip additional disambiguation steps, thereby achieving high accuracy without always incurring maximum processing time. This partial application of disambiguation rules optimizes the balance between precision and speed.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If user confirmation is required to verify intended contact, then communication accuracy is improved, but user interaction time increases

Engineering Contradiction:
Improvecommunication accuracyVSAvoiduser interaction time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system implements conditional confirmation where user verification is only required when the top disambiguated contact result does not meet a confidence threshold. When the system is highly confident in its contact identification, it proceeds directly to initiate communication without requiring user confirmation, thus maintaining high reliability while minimizing user interaction time. This selective confirmation approach balances accuracy with efficiency.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent incorporates feedback mechanisms where the system presents the top contact match to the user for verification when uncertainty exists. Based on user confirmation or correction, the system learns and adapts, improving future contact identification accuracy. This feedback loop ensures high communication reliability while reducing confirmation requirements over time as the system becomes more accurate.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11495224B2Contact resolution for communications systems
Publication Date: 2022.11.08 AMAZON TECH INC
  • US11495224B2 patent drawing
  • US11495224B2 patent drawing
  • US11495224B2 patent drawing

AI summary

Methods and systems for performing contact resolution are described herein. When initiating a communications session using a voice activated electronic device, a contact name may be resolved to determine an appropriate contact with which the communications session may be directed to. Contacts from an individual's contact list may be queried to determine a listing of probable contacts associated with the contact name, and contact identifiers associated with the contact may be determined. Using one or more rules for disambiguating between similar contact names, a single contact may be identified, and a communications session with that contact may be initiated.