ML-Based Communication Routing by Collaboration Circle
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication platforms struggle to intelligently distribute diverse communication methods such as email, instant messaging, and video calls across disparate communication tools, and fail to consider collaboration circle membership and availability status when routing communication requests.
Innovation Solution
A system and method that uses machine learning to process communication requests based on collaboration circle membership data, determining the best recipient and facilitator by analyzing availability status and notification preferences, and generating notifications accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If software-based telephony systems are used to forward and distribute telephone communications, then some degree of automation is provided, but intelligent distribution of disparate communication methods such as email, instant messaging, text messaging, push notifications, video calls, audio notes, meeting invitations, or calendar entries is not provided
Solution Approach 1:
The communication facilitator system is designed to handle multiple types of communication requests including telephone calls, emails, instant messages, text messages, push notifications, video calls, audio notes, meeting invitations, and calendar entries through a single unified platform. The system uses machine learning models to intelligently route any of these communication types to appropriate recipients based on their availability and preferences, making the system universally applicable across diverse communication methods rather than requiring separate systems for each communication type.
Solution Approach 2:
The patent replaces traditional rule-based or manual communication routing systems with machine learning-based intelligent routing. The machine learning models analyze communication patterns, recipient availability, and preferences to dynamically determine the best recipient for each communication request, substituting the mechanical or static routing mechanisms with adaptive, data-driven decision-making that can handle the complexity of multiple communication types.
2Ease of operation
If traditional communication distribution systems are used, then communication requests can be forwarded, but the structure or organization of collaborating individuals within a company is not included in the design of intelligent communication platforms
Solution Approach 1:
The system performs preliminary actions by pre-processing communication requests to identify the request initiator and request recipient before routing decisions are made. The machine learning models analyze the communication request in advance, determine the appropriate recipient based on collaboration circle membership and availability, and prepare the routing decision before the actual communication is delivered. This preliminary analysis ensures that collaboration structure information is incorporated into the routing decision-making process.
Solution Approach 2:
The system incorporates feedback mechanisms where the machine learning models continuously learn from communication patterns and routing outcomes. The system analyzes whether communications were successfully delivered and how recipients interact with them, using this feedback to improve future routing decisions. This feedback loop ensures that the system adapts to the actual collaboration structures and communication patterns within the organization, making the routing increasingly accurate over time.
3Productivity
If communication requests are distributed without considering availability status, then distribution can proceed quickly, but communication preferences of the individual receiving a communication are not respected
Solution Approach 1:
The system dynamically adjusts communication routing decisions based on real-time availability status and individual communication preferences. Rather than using static routing rules, the machine learning models continuously evaluate the current state of potential recipients (their availability, current workload, communication history) and adapt the routing decision accordingly. This dynamic approach allows the system to respect individual preferences while maintaining efficient communication flow by selecting the most appropriate available recipient for each request.
Data Source
AI summary
Various aspects of the subject technology related to systems, methods, and a machine readable storage medium for distributing communication requests based on collaboration circle membership data using machine learning. A system may be configured to receive a plurality of communication requests. Each communication request may include a request initiator and a request recipient. The system may process the plurality of communication requests to using one or more predictive models derived from a machine learning process to generate a communication request resolution for each of the plurality of communication requests. The system may forward a communication request notification to a request facilitator to implement the generated communication request resolution.