Voice Content Attribution via Session Identifiers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current natural language processing systems lack an effective mechanism for attributing user selections of content recommended by third-party skills to the originating skill developer, especially when the content is consumed on a different platform, leading to difficulties in tracking recommendations and providing appropriate attribution.

Innovation Solution

A content attribution platform is introduced that allows skill developers to register their skills and specify content items for attribution, generating an affiliate ID for each skill. This ID is used to associate voice-based content recommendations with the skill developer, enabling accurate attribution when users select recommended content, using a unique session identifier to validate and credit the developer's account.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a content attribution platform is introduced to track recommendations, then attribution accuracy is improved, but system complexity increases

Engineering Contradiction:
Improveattribution accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

A content attribution platform is introduced as an intermediary system between the speech processing system and content delivery platforms. This mediator receives content recommendations from skills, generates session identifiers, and tracks user selections to attribute them back to the appropriate skill developers, thereby enabling accurate attribution without requiring direct integration between all components.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The attribution system is segmented into distinct functional components: skill registration module, session identifier generation module, content recommendation module, user selection tracking module, and attribution crediting module. This segmentation allows each component to perform its specific function independently, managing overall system complexity while maintaining attribution accuracy.

Inventive Principle:
Principle #1Segmentation

2Reliability

If session identifiers are used to track content selections, then attribution reliability is improved, but information processing overhead increases

Engineering Contradiction:
Improveattribution reliabilityVSAvoidinformation processing overhead
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

Session identifiers are generated and associated with skill developer identifiers before content is recommended to the user. This preliminary action ensures that when a user selects content, the attribution can be reliably determined without requiring complex real-time analysis, thereby reducing information processing overhead during the selection event.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The session identifier acts as a simplified copy or representation of the complex attribution relationship between skill, user, and content. Instead of tracking all detailed interactions, the system uses this identifier copy to reliably attribute selections, reducing the information processing burden while maintaining attribution reliability.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS12198690B1Voice-based content attribution for speech processing applications
Publication Date: 2025.01.14 AMAZON TECH INC
  • US12198690B1 patent drawing
  • US12198690B1 patent drawing
  • US12198690B1 patent drawing

AI summary

Devices and techniques are generally described for voice-based content attribution for speech processing applications. In some examples, a request for voice-based content may be received from a first speech processing skill. First identifier data associated with the first speech processing skill may be received. A determination may be made that first content that is associated with the request. Voice-based output data describing the first content may be generated. A selection of the first content may be received. Attribution data may be determined based at least in part on the selection of the first content and the first identifier data. The attribution data may be sent to a remote computing device.