Cloud Server Event Sequence Construction for Digital Channel Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for allocating resources to digital channels in subscription-based services, such as live TV streaming, are inefficient as they rely on experiential knowledge and broad assumptions, failing to capture real-time market dynamics and the sequence of events influencing user conversion.
Innovation Solution
A system and method that automatically allocate resources to digital channels based on each channel's contribution to user conversion, using a cloud server to receive events from multiple channels, construct sequences of events for users, and apply machine learning to generate values for channels, thereby optimizing resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional experiential knowledge and broad assumptions are used for resource allocation, then decision-making is simple and quick, but accuracy in attributing user conversions to correct channels is low
Solution Approach 1:
The patent introduces an event sequence construction module as an intermediary between raw user interaction data and the machine learning model. This module sequences events chronologically and creates structured representations of user journeys across channels, enabling accurate attribution without requiring complex direct analysis of raw data. The intermediary structure makes the complex data relationships manageable and interpretable.
Solution Approach 2:
The patent replaces traditional manual, experience-based resource allocation methods with an automated machine learning system. The ML model processes event sequences and automatically determines channel contributions to conversions, substituting human judgment with data-driven algorithms. This substitution dramatically improves measurement precision while the automation handles the complexity, making the system both accurate and efficient.
2Adaptability or versatility
If historical effectiveness is used to allocate resources to channels, then allocation is stable and predictable, but adaptability to real-time market dynamics is poor
Solution Approach 1:
The patent implements dynamic resource allocation by continuously processing new event data through the machine learning model. As users interact with channels and conversions occur, new event sequences are generated and fed into the model, which updates channel contribution assessments in real-time. This dynamic approach allows the system to adapt to changing market conditions, seasonal trends, and emerging user behaviors without being constrained by historical allocations.
Solution Approach 2:
The system maintains continuous operation by constantly receiving event data, processing it through the ML model, and updating resource allocation recommendations. Rather than periodic batch processing, the system operates continuously to capture real-time market dynamics. The cloud infrastructure ensures uninterrupted data flow and model inference, enabling the organization to respond immediately to changing conditions while minimizing processing delays.
3Measurement precision
If individual user event sequences are analyzed for each channel, then attribution accuracy is high, but computational complexity and processing time increase
Solution Approach 1:
The patent segments the analysis by constructing individual event sequences for each user, tracking their journey across multiple channels chronologically. This segmentation allows the machine learning model to analyze each user's unique path to conversion separately, capturing the specific contribution of each channel touched. By processing users in discrete sequences rather than aggregated data, the system maintains high attribution accuracy while enabling efficient parallel processing across many users simultaneously.
Solution Approach 2:
The system performs preliminary action by pre-processing and sequencing events as they occur, organizing them into structured user journey sequences before ML analysis. This preliminary structuring of data into chronological event sequences with channel identifiers prepares the data for efficient model processing. By organizing data in advance into the required format, the system reduces computational complexity during the actual ML inference phase, improving overall processing speed while maintaining detailed individual user analysis.
Data Source
AI summary
A method of automatically allocating resources to digital channels includes receiving, at a cloud server running on a multi-node cloud system, one or more events associated with each of a plurality of users from at least one of a plurality of digital channels; constructing, by the cloud server, a sequence of events for each of the plurality of users; generating, using a machine learning model, a value for each of the plurality of digital channels for each of the plurality of users based on the respective sequences of events of the plurality of users. The method further includes calculating a second value for each of the plurality of digital channels based on the first value of each of the plurality of users and an attribute of each of the plurality of users; and automatically allocating resources to each of the plurality of digital channels based on the respective second value.