Cross-Environment Entity Similarity via Join Panel Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to seamlessly attribute information about entities across disparate operating environments, such as internet and mobile devices, preventing effective content serving decisions based on existing user data.
Innovation Solution
A method and system that determine similarity between entities in different identifier spaces by using a join panel of entities operating in both spaces, building models based on their histories, and applying these models to predict similarity between an archetypical population and a target entity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If information is captured for entities in one operating environment, then content consumption habits can be analyzed, but the information cannot be seamlessly attributed to the same entity in a different operating environment
Solution Approach 1:
The patent introduces an intermediary mapping mechanism that connects different identifier spaces through a common reference framework. This intermediary layer enables information from disparate operating environments (mobile devices, web browsers, gaming consoles) to be attributed to the same entity without requiring direct integration between each environment, thus resolving the information loss problem while managing system complexity.
Solution Approach 2:
The system creates a universal identifier mapping framework that serves multiple operating environments simultaneously. By establishing a common reference space where identifiers from different sources can be mapped and correlated, the system achieves multi-functional capability to handle entity identification across diverse platforms, enabling seamless information attribution without requiring environment-specific separate systems.
2Productivity
If models are built using join panel entities to determine similarity across identifier spaces, then content serving decisions can be made, but the process requires complex model building and application steps
Solution Approach 1:
The patent performs preliminary model building using join panel entities that exist in multiple identifier spaces. By pre-establishing similarity models based on entities with known cross-environment presence, the system prepares transformation rules and similarity metrics in advance. This preliminary action enables efficient content serving decisions to be made later without requiring complex real-time model computation, thus improving productivity while managing computational complexity.
Solution Approach 2:
The system transforms entity characteristics and identifier formats between different operating environments by applying parameter transformation rules. By changing the representation parameters of entities to a standardized format that can be universally compared, the system simplifies the model application process. This parameter transformation approach enables efficient similarity determination across identifier spaces without requiring complex environment-specific processing at decision time.
Data Source
AI summary
Models are built based on existing histories in one identifier space to infer features of entities in a different identifier space. A source model is built using features of an archetypical population in a given identifier space and the standard population. A join panel, i.e., a set of entities operating across both the given identifier space and a second disjoined identifier space, is scored using the source model. Based on the scores and features associated with the entities in the join panel within the second identifier space, a target model specific to the second identifier space is built. An audience of entities within the second identifier space can then be scored using the target model to identify entities that are similar to the archetypical population.