Dynamic Ad Generation via Sentiment-Keyword Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional advertising methods using printed media and scheduled broadcast television are inefficient as they fail to react to recent trends and news, making them less effective in influencing ideal customer sentiments.

Innovation Solution

A system and method for generating advertisements by transcribing media files, extracting sentiments, associating keywords, analyzing trending topics, and publishing ads based on matches between sentiments and keywords to create sentiment-keyword matched media that can be dynamically updated to reflect current events and consumer interests.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional scheduled broadcast television advertisements are used, then advertising coverage is achieved, but the advertisements cannot react to recent trends and news developments

Engineering Contradiction:

Improveability to react to trends and newsVSAvoidtime delay in advertising publication

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements dynamic advertising by continuously monitoring trending topics and sentiments in real-time, then automatically generating and publishing ads that match current consumer interests. The system transitions from static pre-scheduled ads to dynamic real-time ad generation, allowing advertisements to adapt their content and timing based on current events and consumer sentiment analysis.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs self-service by automatically transcribing media files, extracting sentiments, identifying trending topics, generating relevant ads, and publishing them without human intervention. The automated workflow includes sentiment analysis of transcribed content, keyword extraction, ad generation based on matched sentiments and trends, and real-time publication to social media platforms.

Inventive Principle:

Principle #25Self-service

2Productivity

If static pre-scheduled advertisements are published, then advertising content is controlled, but the advertisements fail to leverage current events and consumer sentiments

Engineering Contradiction:

Improveadvertising effectivenessVSAvoidresponsiveness to current events

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system implements feedback loops by continuously monitoring social media platforms for trending topics and consumer sentiments, then using this feedback to generate and publish relevant advertisements. The process includes extracting sentiments from transcribed media content, comparing against real-time trending topics, and automatically publishing ads that resonate with current consumer interests and discussions.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary actions by pre-transcribing and analyzing media files to extract sentiments and keywords before trending topics emerge. This allows the system to quickly generate and publish relevant advertisements as soon as related trends appear on social media, capturing advertising opportunities before competitors.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If real-time sentiment analysis and automated ad generation are implemented, then advertising relevance to current trends is improved, but system complexity increases

Engineering Contradiction:

Improvereal-time ad customizationVSAvoidsystem architecture complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the advertising system into distinct functional modules: media file transcription service, sentiment extraction service, trending topic monitoring service, ad generation service, and automated publishing service. Each module performs a specific function and can be independently managed, maintained, and scaled, reducing overall system complexity while enabling real-time sentiment-based advertising.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10552877B2Engine and system for the transcription and assessment of media files

Publication Date: 2020.02.04 VERITONE INC

AI summary

A system and method for publishing endorsed media is disclosed herein. The system receives a media file and then transcribes a portion of the media file to produce a transcribed script for the media portion. The system then extracts one or more sentiments based on the transcribed script and media data of the media file. Next, the system associates the one or more extracted sentiments to one or more keywords in the transcribed script. Trending topic around the Internet is then determined. In one aspect, the system then publishes the media portion over the network based on a match between the trending topic and the one or more keywords associated with the one or more extracted sentiments.