Journey Recommendation Apparatus Using Event Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing an entire history related to an entity to determine the correct channel of interaction for future procurement or task performance is technically challenging, especially in determining the optimal sequence of events, frequency, and time interval for maximum impact.
Innovation Solution
The apparatus and method partition and analyze historical data to provide sequence, frequency, and time interval-based journey recommendations, using machine learning to optimize marketing activities and interactions by clustering entities, determining success criteria, and simulating probabilities and frequencies to generate optimal recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire history of entity interactions is analyzed to determine the optimal sequence of events, frequency, and time interval, then the accuracy of journey recommendations is improved, but the computational complexity and time required for analysis increases
Solution Approach 1:
The patent segments the entire interaction history into discrete events with specific attributes (event type, timestamp, channel, etc.). This segmentation allows the complex historical data to be processed in structured units, making it feasible to analyze sequence, frequency, and time interval patterns without overwhelming computational burden.
Solution Approach 2:
The system performs preliminary actions by pre-processing and storing interaction history in a structured format with defined events and attributes. This preliminary structuring enables faster subsequent analysis of journey patterns, reducing the computational complexity when generating recommendations.
2Measurement precision
If the entire history of entity interactions is analyzed to determine the optimal sequence of events, frequency, and time interval, then the accuracy of journey recommendations is improved, but the time required for analysis increases
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing interaction history in a structured format with defined events and attributes. This preliminary structuring enables faster subsequent analysis of journey patterns, reducing the computational complexity when generating recommendations.
Solution Approach 2:
The system implements self-service through automated event extraction, sequence identification, and journey recommendation generation. The apparatus autonomously processes historical data and generates recommendations without manual intervention, significantly reducing the time required for analysis while maintaining accuracy.
3Productivity
If sequence, frequency, and time interval based analysis is implemented, then the effectiveness of marketing activities is improved, but the device complexity increases
Solution Approach 1:
The patent segments the entire interaction history into discrete events with specific attributes (event type, timestamp, channel, etc.). This segmentation allows the complex historical data to be processed in structured units, making it feasible to analyze sequence, frequency, and time interval patterns without overwhelming computational burden.
Solution Approach 2:
The system introduces an intermediary layer (the journey recommendation apparatus) that sits between the raw interaction history and the marketing activities. This intermediary processes and structures the data, identifying optimal sequences, frequencies, and time intervals, thereby simplifying the overall system while improving marketing effectiveness.
4Speed
If real-time predictions and dynamic recommendations are generated, then the responsiveness to entity needs is improved, but the computational resources required increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing interaction history in a structured format with defined events and attributes. This preliminary structuring enables faster subsequent analysis of journey patterns, reducing the computational complexity when generating recommendations.
Solution Approach 2:
The system implements dynamic journey recommendations that adapt to changing entity behavior and context. By using structured event data and automated analysis, the system can generate real-time predictions and adjust recommendations dynamically without requiring excessive computational resources.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
In some examples, sequence, frequency, and time interval based journey recommendation may include generating a plurality of clusters of entities, and generating a network that identifies a time interval to a next interaction that leads to success. An estimated time interval to a specified number of conversions may be determined. A success criterion that represents a positive outcome in the estimated time interval may be determined. A historical sequence of events may be partitioned into a plurality of sequences of events leading to success or failure. The plurality of sequence of events may be mapped based on analyzed probabilities, a determined waiting interval, and determined frequency contributions, and evaluated as to whether a mapped sequence of events duration is less than a planned duration. If so, a journey may be generated and include a determined sequence of events, a corresponding frequency, and a corresponding waiting interval.