In-Store Analytics for Augmented Reality Customer Service
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users find augmented reality applications in mobile devices cumbersome to use due to the need to hold the device to view live scenes and contextual information, leading to fleeting usage and reduced accessibility of relevant information.
Innovation Solution
A store analytics system that collects user information, device data, and estimated fields-of-view to identify commonalities among users, creating logical groups and providing targeted offers, notifications, and customer service assistance through signage, remote agents, or social networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If augmented reality applications are used to provide contextual information, then information accessibility is improved, but device operation complexity increases
Solution Approach 1:
The patent uses the mobile device camera as an intermediary to capture the live scene and presents augmented information through the display screen, mediating between the physical store environment and the user. This allows users to access contextual information without directly manipulating the device to view live scenes, as the system processes and presents information automatically
Solution Approach 2:
The system creates a digital copy of the user's field-of-view through the camera and overlays contextual information on this copy. Instead of requiring users to view the live scene directly through the camera, the system captures the scene, processes it, and presents augmented information based on the captured image, allowing users to access information without holding the device up to view the live scene
2Loss of information
If augmented reality applications provide comprehensive contextual information, then information completeness is improved, but user engagement duration decreases
Solution Approach 1:
The system provides augmented reality information selectively based on the detected scene and user context, rather than continuously displaying all possible information. The camera detects specific products or areas of interest, and contextual information is presented only when relevant, reducing the burden of continuous device holding while maintaining information completeness for detected items
3Adaptability or versatility
If store analytics system collects detailed user information, then customer service personalization is improved, but data processing complexity increases
Solution Approach 1:
The store analytics system merges multiple data sources including camera field-of-view data, user profile information, purchase history, and real-time location data into a unified user context model. This integrated approach allows personalized customer service recommendations to be generated from combined data rather than processing separate data streams independently
Solution Approach 2:
The system automatically processes and analyzes user data in real-time without requiring manual intervention. The analytics system self-adjusts by continuously monitoring user behavior patterns, field-of-view data, and contextual information to dynamically generate personalized service recommendations and offers
Data Source
AI summary
Concepts and technologies disclosed herein are directed to aspects of customer service based upon in-store field-of-view and analytics. According to one aspect disclosed herein, a store analytics system can collect user information associated with a plurality of users located within an environment. The store analytics system also can collect user device information associated with a plurality of user devices associated with the plurality of users. The store analytics system also can collect estimated fields-of-view associated with the plurality of users. The store analytics system can analyze the user information, the user device information, and the estimated fields-of-view to identify at least one commonality shared among at least two of the plurality of users. The store analytics system can create a logical group. The logical group can include the at least two users of the plurality of users that share the commonality.