OTT Ad Recommendation Using Personality and Needs Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing OTT media communication systems lack the ability to effectively target advertisements beyond basic demographic segmentation, failing to deliver the right advertisement to the right person at the right time, which limits their conversion potential.
Innovation Solution
A method and system that analyze user personality and needs by receiving and processing data from various sources, using machine learning models and neural networks to identify user attributes and needs, and recommend targeted advertisements based on these classifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If basic demographic segmentation is used for advertisement targeting, then the advertising system is simple to implement, but the advertisement delivery precision is insufficient
Solution Approach 1:
The patent segments the advertising system into multiple independent modules: data collection module, personality analysis module (using machine learning models), need identification module (using neural networks), and advertisement recommendation module. This segmentation allows the system to achieve precise targeting through personality traits and needs analysis while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The patent changes the targeting parameters from basic demographics to psychological dimensions including personality traits (analyzed via machine learning) and user needs (identified via neural networks). This parameter transformation enables much more precise advertisement matching by capturing deeper user characteristics beyond age, gender, and location.
2Productivity
If personalized advertisement delivery based on personality and needs is implemented, then the conversion rate increases, but the data processing complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-analyzing user personality traits and needs before advertisement delivery. Machine learning models pre-process user data to establish personality profiles, and neural networks pre-identify user needs based on viewing behavior. This preliminary processing enables rapid, accurate advertisement matching without adding complexity to the real-time delivery process.
Solution Approach 2:
The patent introduces intermediary components: machine learning models act as intermediaries between raw user data and personality traits, while neural networks serve as intermediaries between viewing behavior and user needs. These intermediaries simplify the overall system by breaking down complex data processing into manageable transformation steps, each handled by a specialized component.
3Measurement precision
If multiple data sources are collected and analyzed, then the user profile accuracy improves, but the data processing time increases
Solution Approach 1:
The patent performs preliminary data processing by collecting and pre-analyzing data from multiple sources (viewing history, interaction patterns, demographic information) before the advertisement delivery moment. Machine learning models pre-compute personality traits, and neural networks pre-identify needs based on accumulated viewing behavior. This upfront processing ensures high user profile accuracy while keeping real-time processing minimal.
Solution Approach 2:
The patent implements continuous data collection and analysis across multiple viewing sessions, continuously refining user profiles through ongoing interaction with the system. This continuous process distributes data processing over time rather than concentrating it, maintaining accurate user profiles without creating processing bottlenecks at any single moment.
Data Source
AI summary
This disclosure relates generally to a system and method to recommend a targeted advertisement to a user. The system is configured to receive and pre-processes a plurality of data from various sources based on a set of predefined business rules. A set of training data is extracted from the pre-processed plurality of data to develop a machine learning model to identify a set of attributes of personality of the user. A neural network is trained to identify at least one classifier to define one or more needs of the user. It would be appreciated that the one or more needs of the user are mapped with the set of attributes of the personality. Finally, the recommendation module of the system recommends at least one advertisement to a media service provider to share the same over OTT to the user.