Mobile Device Sentiment Analysis for Customer Interaction Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems lack the ability to track and analyze interactions between customers and sales associates in a venue, failing to provide insights into successful interactions that lead to purchases and automatically initiate interactions between specific sales associates and customers.
Innovation Solution
A computer-implemented method and system that detects the presence of mobile devices within a venue, monitors their locations, records interaction events, determines customer service parameters, and generates alerts based on sentiment analysis to optimize associate-customer interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If customer movement tracking is implemented using mobile devices, then customer location information is obtained, but interaction analysis capability is lacking
Solution Approach 1:
The existing mobile device tracking system is extended to perform multiple functions: not only tracking customer location but also detecting interaction events between customers and associates, capturing sentiment data, and generating actionable insights. This multi-functional approach eliminates the need for separate interaction tracking devices.
Solution Approach 2:
The system leverages the mobile devices that customers already carry and use for other purposes. These self-owned devices serve the additional function of interaction tracking and sentiment capture without requiring customers to wear or carry dedicated tracking equipment.
2Loss of information
If interaction tracking is added to existing tracking systems, then interaction insights are provided, but computing overhead increases
Solution Approach 1:
The system focuses on detecting specific interaction events rather than continuously monitoring all customer movements. By triggering analysis only when interaction patterns are detected (such as停留 time thresholds or location-based events), the computing overhead is significantly reduced while still capturing essential interaction insights.
Solution Approach 2:
The system pre-establishes interaction detection rules and sentiment analysis models before actual interactions occur. This preliminary setup allows the system to process interactions in real-time using pre-configured parameters, reducing the computational burden during live operation.
3Loss of information
If sentiment analysis is performed on interaction data, then customer service parameters are determined, but automated interaction initiation capability is lacking
Solution Approach 1:
The system creates a closed-loop feedback mechanism where sentiment analysis results directly influence automated actions. When negative sentiment is detected or when specific interaction patterns are identified, the system automatically generates alerts and initiates follow-up interactions, transforming analytical insights into actionable automated responses.
Solution Approach 2:
The system introduces an intermediary alerting mechanism that bridges sentiment analysis and automated interaction initiation. The alerting system serves as a mediator that translates complex sentiment data into simple, actionable triggers that can automatically initiate appropriate customer service interactions.
Data Source
AI summary
Systems and methods for customer touchpoint pattern and sentiment analysis are disclosed. In embodiments, a computer-implemented method comprises: detecting, by a computer device, the presence of a mobile device of a participant within a venue during a first event; monitoring, by the computing device, the location of the mobile device of the participant within the venue during the first event; detecting, by the computing device, at least one interaction event between the participant and a venue associate; recording, by the computing device, first event data including interaction event data; detecting, by the computing device, the presence of the mobile device of the participant within the venue during a second event; determining, by the computing device, one or more customer service parameters based on the first event data; and generating, by the computing device, an alert based on the one or more customer service parameters.