Augmented Reality Ad Targeting Through Cumulative Ambience Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) advertising methods are limited by relying on simple triggers like object detection or location, leading to irrelevant ads and reduced conversion rates due to imprecision in targeting and repetitive exposure.
Innovation Solution
Ad targeting based on complex ambience specifications comprising multiple view specifications over time, using sensors to collect data on user experiences and determining a best fit ambience specification through match quality and rarity values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If ads are targeted based on simple triggers like object detection or location, then the system complexity is reduced, but ad relevance and conversion rates deteriorate
Solution Approach 1:
The ambience specification is segmented into multiple view specifications, each capturing a specific temporal slice of the user's experience. This allows the system to analyze cumulative patterns across time without requiring a monolithic complex system, resolving the contradiction between simplicity and relevance.
Solution Approach 2:
The system performs preliminary data collection and analysis of ambience attributes over time, building up a profile of user experiences before triggering ads. This preliminary action enables more relevant targeting without requiring complex real-time processing during the ad delivery moment.
2Speed
If ads are presented based on single-time triggers, then the response time is reduced, but ad relevance deteriorates due to lack of cumulative context
Solution Approach 1:
The system continuously collects and analyzes ambience data in advance, building a temporal profile of user experiences. When an ad trigger occurs, the system can quickly reference pre-computed patterns rather than analyzing everything in real-time, maintaining fast response while ensuring relevance through cumulative context.
Solution Approach 2:
The system adds the temporal dimension to ad triggering by analyzing ambience specifications across multiple time points. This dimensional expansion from single-time to multi-time analysis enables relevance improvement without proportionally increasing response time, as the temporal analysis is performed in advance.
3Reliability
If ads are targeted using cumulative experience data, then ad relevance is improved, but data collection and processing complexity increases
Solution Approach 1:
The complex task of analyzing cumulative user experience is segmented into discrete ambience attributes (lighting, sound, spatial characteristics) and discrete view specifications. This segmentation makes the data collection and processing more manageable and less complex while still capturing cumulative patterns.
Solution Approach 2:
The ambience specification framework serves multiple functions: it captures temporal patterns, identifies user states, determines ad relevance, and triggers appropriate ads. This multi-functionality reduces the need for separate complex systems for each function, overall reducing system complexity while improving relevance.
4Ease of operation
If simple object detection triggers are used, then the ease of operation is improved, but conversion rates deteriorate due to imprecision in targeting
Solution Approach 1:
The system performs preliminary analysis of ambience attributes and user experience patterns before ad delivery. This preliminary action filters and pre-segments the audience based on cumulative experience, so that when ads are delivered, the targeting is precise and conversion rates improve without adding complexity at the moment of ad delivery.
Solution Approach 2:
The system changes the parameters used for targeting from simple binary triggers (object present/absent) to multi-dimensional ambience specifications that capture temporal and contextual variations. This parameter expansion enables precise targeting while maintaining ease of operation through automated analysis of the expanded parameters.
Data Source
AI summary
Some embodiments of the present disclosure relate to methods and systems for providing an advertisement to a user based on a collective experience of the user. One method includes accessing a plurality of ambience specifications having corresponding advertisements. Each ambience specification may comprise a first view specification and a second view specification, and each view specification may comprise a list of ambience attributes. The method may include capturing first data at a first time and determining, for each of the first view specifications, a first match quality value. The method may include capturing second data at a second time and determining, for each of the second view specifications, a second match quality value. The method may include determining a best fit ambience specification based on the first match quality values and the second match quality values, and presenting to the user, the advertisement corresponding to the best fit ambience specification.