Influence Rank Generation for Enterprise Social Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprise communities face challenges in utilizing vast amounts of user interaction data to customize user experiences effectively, as existing systems lack the capability to process and leverage this data to identify high-impact users and enhance engagement.
Innovation Solution
An influence rank generation system that utilizes a social graph and machine learning techniques, including sentiment analysis and page rank algorithms, to rank users based on their interactions, allowing for targeted communications and customized user interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If enterprise communities collect and store vast amounts of user interaction data, then the quantity of available information increases, but the ability to process and leverage this data effectively deteriorates
Solution Approach 1:
The patent extracts only the most relevant features and interactions from the vast user data using machine learning algorithms. Instead of processing all raw interaction data, the system identifies and extracts key patterns, user behaviors, and influence metrics that are most valuable for customization, thereby making the data processing manageable and effective
Solution Approach 2:
The patent introduces an intermediary layer of machine learning models and influence ranking algorithms that mediate between the raw user interaction data and the customization application. This intermediary processing layer transforms the vast amount of raw data into meaningful influence scores and user profiles that can be effectively utilized for personalization
2Loss of information
If enterprise communities implement comprehensive data collection across all user interactions, then the completeness of user information improves, but the complexity of the system increases
Solution Approach 1:
The patent segments the complex data collection and processing system into distinct modular components: data collection modules for different interaction types, machine learning processing modules, influence ranking algorithms, and application modules for customization. This segmentation allows the system to maintain comprehensive data collection while managing complexity through modular architecture
Solution Approach 2:
The patent creates a universal machine learning framework that handles multiple types of user interactions (purchases, reviews, social actions, browsing) through a single integrated system. This multi-functional approach maintains complete user information across all interaction types while avoiding the complexity of separate processing systems for each interaction type
3Loss of information
If enterprise communities send communications to all users, then the coverage of information delivery improves, but the efficiency of communication decreases
Solution Approach 1:
The patent applies local quality by customizing communications based on individual user influence ranks and preferences rather than using a uniform approach for all users. High-influence users receive different communication priorities and content than low-influence users, optimizing communication efficiency for each user segment while maintaining overall coverage
Solution Approach 2:
The patent implements partial action by selectively communicating with users based on their influence ranks and predicted interests. Instead of sending communications to all users equally, the system identifies and targets the most relevant users for specific communications, thereby improving efficiency while maintaining adequate coverage through strategic selection
Data Source
AI summary
Disclosed herein are system, method, and computer program product embodiments for generating an influence rank for users within an enterprise community based on a social graph and utilizing the influence rank to customize the user experience in the enterprise community. An influence rank for a user of the enterprise community may be determined based on building a social graph representing the user's interactions within the enterprise community and analyzing the social graph. Communications may be then redirected within the enterprise community based on the determined influence rank.