Auto-tracking with Just-in-time AI Agents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tracking systems rely on proprietary applications and provide limited value to users, as data is often consumed through inflexible interfaces and real-time representations, lacking in-depth analysis and flexibility.
Innovation Solution
A system for auto-tracking using just-in-time training and goal-seeking AI agents, comprising asset trackers, communications hubs, a base station, and a server computing device that processes raw data from asset trackers to answer user queries efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If proprietary applications with inflexible interfaces are used to access tracking data, then data can be accessed through standardized channels, but user flexibility and adaptability are limited
Solution Approach 1:
The system replaces proprietary applications with a universal API interface that can serve multiple functions and user needs. The API allows different clients (mobile devices, web browsers, custom applications) to access tracking data through a single standardized interface, eliminating the need for multiple proprietary applications while maintaining ease of access.
Solution Approach 2:
Instead of providing fixed interfaces that users must adapt to, the system inverts the approach by providing raw data access that allows users to create their own customized interfaces and representations. The server returns raw sensor data that clients can process and display in whatever format best suits their specific needs.
2Productivity
If tracking data is processed and presented through pre-defined graphical interfaces and smart notifications, then data can be consumed in standardized formats, but in-depth analysis and custom insights are limited
Solution Approach 1:
The system extracts and separates the data processing function from the presentation function. Instead of embedding analysis logic within proprietary applications, the system extracts raw data and makes it available through the API, allowing users to apply their own analysis methods and tools according to their specific needs.
Solution Approach 2:
The system enables users to perform their own custom analysis by providing direct access to raw tracking data through the API. Users can implement their own algorithms, analysis methods, and insight generation processes without being constrained by pre-defined processing pipelines in proprietary applications.
3Device complexity
If device ML models perform analytical computation on asset trackers, then data can be processed locally, but raw data transmission increases network bandwidth consumption
Solution Approach 1:
The system implements a dynamic data transmission strategy where the level of local processing on asset trackers can be adjusted based on network conditions, device capabilities, and user needs. Some devices may transmit raw data while others perform local aggregation, allowing the system to optimize the balance between local processing and network usage in real-time.
Solution Approach 2:
The system allows changing the parameter of data processing location from fixed (either all local or all remote) to variable. Users and system administrators can adjust the degree of local processing versus remote processing based on specific requirements, enabling optimization of both device complexity and network bandwidth consumption for different scenarios.
Data Source
AI summary
In one aspect, a system for auto-tracking with just-in-time training and goal seeking AI agents comprising: a plurality of asset trackers, wherein each asset tracker tracks one or more IoT assets and obtains a set of IoT data; one or more communications hubs; a base station; one or more communication networks; wherein each asset tracker is configured to be in communication with a base station and one or more of the communications hubs; wherein in the one or more communications hubs are configured to be in communication with one or more of the mobile units, and the one or more network; wherein the base station is configured to be in communication with the plurality of asset trackers; a server computing device configured to be in communication with the one or more networks, wherein the server computing device is further configured to implement the following logic: wherein one or more asset trackers transmit raw data directly to the server computing device, instead of device ML model-derived inference or device computed data, storing the raw data of the one or more asset trackers in the server computing device without analytical computation; receiving a user query; initiating a just-in-time process to find an answer to the user query; communicating the question to an AI agent in the server computing device; with the AI agent: seeking a goal of answering the question, by breaking the question down into multiple steps, and executing the multiple steps until the goal is reached.