Social Network Analysis Weighting for User Influence Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Telecommunication operators face challenges in efficiently processing vast amounts of data from Call Data Records to identify influential users within communication systems, as existing social network analysis algorithms are resource-intensive and require choosing the most appropriate methods for specific goals.
Innovation Solution
A method using machine learning to calculate weight parameters for social network analysis metrics, allowing for the combination and ranking of user influence across large communication systems, enabling efficient data handling and accurate identification of influential users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple SNA algorithms are used to analyze user interactions, then the accuracy of influence assessment is improved, but the processing time and resource consumption increase
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing SNA metrics for a first number of users before the actual assessment is needed. These pre-computed metrics are then reused when assessing influence for a second number of users, eliminating the need to recalculate metrics repeatedly and significantly reducing processing time while maintaining accuracy.
Solution Approach 2:
The patent segments the user base into two distinct groups: a first number of users whose SNA metrics are pre-calculated and stored, and a second number of users whose influence is assessed using the pre-computed metrics. This segmentation allows the system to handle different user groups with different processing requirements, optimizing both accuracy and efficiency.
2Reliability
If multiple SNA metrics are calculated for each user, then the reliability of user influence assessment is improved, but the computational resources required increase
Solution Approach 1:
The system performs preliminary calculation of multiple SNA metrics for users in advance and stores these results. When influence assessment is needed, the pre-computed metrics are retrieved and combined using weight parameters rather than recalculating everything, thereby maintaining reliable multi-metric assessment while significantly reducing computational resource consumption at query time.
Solution Approach 2:
The patent creates a copy of SNA metrics from the first number of users and applies these pre-computed metrics to assess influence for the second number of users. Instead of recalculating metrics for every user assessment, the system copies and reuses the computational results, reducing energy consumption while maintaining assessment reliability through the use of multiple metrics.
3Speed
If SNA metrics are pre-calculated and stored for later use, then the execution speed of influence assessment is improved, but the data storage requirements increase
Solution Approach 1:
The patent implements preliminary action by pre-calculating and storing SNA metrics for a subset of users (first number of users). These pre-computed metrics are stored in a database and later retrieved for assessing influence of other users (second number of users), enabling fast execution of influence assessments without recalculating metrics in real-time.
Solution Approach 2:
The system extracts only the essential SNA metrics that are needed for influence assessment and stores these specific data points. Rather than storing all possible user data, the patent extracts and stores only the relevant SNA metrics (such as degree centrality, betweenness centrality, eigenvector centrality) that are necessary for the assessment, optimizing storage efficiency while maintaining execution speed.
Data Source
AI summary
The invention relates to a method performed in a computer system for aiding the assessment of an influence of a user in or interacting with a communication system by applying social network analysis, SNA, functions. The method comprises: obtaining two or more SNA metrics for each user of a first number of users, each SNA metric being determined by a respective SNA function; calculating a weight parameter for each one of the SNA metrics using a machine learning method, the weight parameters indicating a combination of the SNA metrics for use in the assessment of the influence of the user; and applying the estimated weight parameters to SNA metrics of a second number of users to assess a ranking in accordance with influence of users in the second number of users. The invention also relates to a computer system, computer programs, and computer program products.