Pseudo-User Estimation for Unique Viewer Counting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the number of unique viewers of content items are inaccurate due to multiple users sharing the same device identifier and individuals viewing content on multiple devices, leading to overcounting of unique viewers.
Innovation Solution
A method that assigns received identifiers to pseudo-users based on a non-linear distribution, using a product logarithmic function to create pseudo-users for each user category, allowing for accurate estimation of unique viewers by summing the estimated number of unique viewers across categories without counting identifiers multiple times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If device identifiers are used to count unique viewers, then the counting process is simple, but the accuracy of unique viewer estimation deteriorates due to multiple users sharing devices and individuals using multiple devices
Solution Approach 1:
The patent introduces pseudo-users as an intermediary layer between device identifiers and unique viewer counting. Each pseudo-user represents a probabilistic model of a real user's viewing behavior across multiple devices. The system assigns device identifiers to pseudo-users based on non-linear distribution functions, allowing accurate estimation of unique viewers without directly tracking individual users or their devices.
2Productivity
If real-time unique viewer estimation is implemented, then the speed of providing content performance data is improved, but the complexity of data processing increases
Solution Approach 1:
The patent pre-establishes user categories with associated non-linear distribution functions that model identifier distribution patterns for each category. These distribution models are prepared in advance based on historical data and user characteristics. When identifiers are received in real-time, the system simply assigns them to appropriate pseudo-users using the pre-defined distribution functions, enabling fast real-time estimation without complex on-the-fly calculations.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a number of unique viewers of a content item. In one aspect, a method includes receiving an identifier specifying characteristics of a user associated with a device that was used to present a given content item. A user category is identified for the received identifier based on the characteristics. Each user category of a set of user categories include a respective number of pseudo-users. The received identifier is assigned to a given pseudo-user in the identified user category based on a non-linear distribution of identifiers per actual user in the identified user category. A number of unique users, including the given pseudo-user, that have viewed the given content item is determined based on a total number of pseudo-users that have been assigned an identifier corresponding to presentation of the given content item.