Automated Social Media Conversation Aggregation for CRM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current social customer relations management (CRM) systems are highly human-intensive and error-prone, lacking tools to effectively track and measure engagement conversations and their effectiveness across social media platforms like Twitter, which are decentralized and asynchronous, making it difficult for CRM teams to manage and analyze customer interactions.
Innovation Solution
A system that crawls social media messages in real-time, aggregates conversations using linguistic frameworks for dialog acts and conversation analysis, and computes metrics like conversion rate, resolution rate, and happy customer rate, enabling real-time online monitoring and analysis of customer interactions with CRM teams.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If social media monitoring is performed manually by human teams, then flexibility and adaptability are maintained, but the process becomes highly human-intensive and error-prone with limited scalability
Solution Approach 1:
The patent introduces an intermediary system comprising automated crawling tools, natural language processing algorithms, and linguistic frameworks that mediate between social media platforms and CRM teams. This intermediary automatically extracts, structures, and analyzes conversation data, reducing manual effort while maintaining reliability through systematic processing and consistent application of linguistic analysis rules.
Solution Approach 2:
The patent replaces the mechanical manual process of browsing and storing social posts with automated computational systems. Crawlers automatically scrape data from decentralized platforms, NLP algorithms automatically analyze message content and intent, and automated systems compute engagement metrics, substituting human mechanical operations with automated digital processes that eliminate human error and scale efficiently.
2Quantity of substance
If all social media messages are monitored and stored individually, then complete data availability is achieved, but the system becomes overwhelmed by the volume and complexity of decentralized asynchronous data
Solution Approach 1:
The patent merges individual asynchronous messages from decentralized social media platforms into unified conversation threads. By identifying related messages through linguistic analysis, participant identification, and temporal proximity, the system combines scattered data points into coherent conversation structures, reducing data complexity while preserving complete conversation context for analysis.
Solution Approach 2:
The patent segments the overwhelming volume of social media data into manageable conversation units. By applying linguistic frameworks to identify dialogue acts, topics, and conversation boundaries, the system divides the continuous stream of messages into discrete, analyzable conversation segments that can be processed and measured systematically without being overwhelmed by the total data volume.
3Measurement precision
If traditional call center metrics are applied to social media conversations, then familiar measurement frameworks are used, but the asynchronous and decentralized nature of social media makes direct application ineffective
Solution Approach 1:
The patent changes the parameters of measurement to suit social media's asynchronous and decentralized nature. Instead of measuring real-time call outcomes, the system measures engagement metrics based on message timing, conversation progression, and linguistic indicators of resolution. The system adapts metrics like resolution rate and customer satisfaction to account for delayed responses and multiple interaction points characteristic of social media conversations.
Solution Approach 2:
The patent creates a universal measurement framework that adapts to multiple decentralized social media platforms simultaneously. The linguistic framework and metric computation system are designed to work across different platforms (Twitter, Facebook, etc.) with their varying characteristics, providing consistent engagement measurements that are versatile enough to handle the diversity of social media environments while maintaining measurement precision.
Data Source
AI summary
The present disclosure provides a system that allows for the real-time and online monitoring of the exchanges between customers and a CRM team over social media. While crawling all messages exchanged over the social media by customers and CRM team, the system aggregates related messages exchanged between a given customer and the CRM team into a conversation. The system includes a linguistic framework for the analysis of conversations (based on the two linguistic theories of dialog acts and conversation analysis) to label the nature of the messages in a conversation or thread.