ML Model for Facility Asset Tracking via Natural Language and ToF Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional automated warehouse mapping and management tools lack granularity in real-time information on moving assets such as forklifts, personnel, and goods, and rely on multiple separate systems for effective warehouse management.

Innovation Solution

The system uses a Machine Learning (ML) model to receive natural language input for tasks, determine instructions for dynamic assets, and update these instructions based on real-time location feedback from Time-of-Flight (ToF) sensors, enabling precise management and control of assets within a facility.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple separate systems are used for warehouse management, then each system can be specialized and optimized for its specific function, but the overall system complexity increases and integration becomes difficult

Engineering Contradiction:

Improvespecialization of management functionsVSAvoidnumber of separate systems

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent combines multiple separate warehouse management functions (asset tracking, inventory management, personnel coordination, autonomous vehicle control) into a single integrated system that uses unified sensors, centralized processing, and a common communication protocol. This consolidation reduces the number of separate systems while maintaining the specialized capabilities of each function through modular software architecture.

Inventive Principle:

Principle #5Merging (Combining)

2Measurement precision

If conventional mapping tools are used, then the system is simpler to implement, but the granularity of real-time information on moving assets is insufficient

Engineering Contradiction:

Improvegranularity of real-time location informationVSAvoidcomplexity of mapping system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the facility into multiple zones with distributed sensors and tracking points, allowing high-granularity real-time location tracking of individual assets while maintaining overall system manageability. Each sensor node independently tracks local movements and communicates with the centralized system, enabling precise tracking without requiring a monolithic complex system.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediate tracking points and relay nodes throughout the facility that aggregate location data from individual asset sensors before transmitting to the central system. These intermediaries reduce the communication burden on the central system while maintaining high measurement precision through localized data processing and filtering.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Manufacturing precision

If real-time location tracking with high granularity is implemented, then control precision over dynamic assets improves, but the cost and complexity of the tracking infrastructure increases

Engineering Contradiction:

Improveprecision of asset location controlVSAvoidtracking infrastructure complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent employs universal sensor nodes and tracking infrastructure that serve multiple functions: location tracking, asset identification, communication relay, and data aggregation. These multi-functional components reduce the total number of specialized devices needed while maintaining high precision tracking through software-based differentiation of functions.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach provides real-time, granular control over assets, improving the efficiency and accuracy of warehouse operations by integrating multiple management functions into a single, intelligent system.

Implementation Method 1

a Time-of-Flight (ToF) of a signal communicated between the tag and each of the two or more stationary assets

Methodology Applied

Scientific EffectTime-of-Flight: Time of Flight

Data Source

PatentUS20250156691A1System for training and deploying generative language model for formulating instructions for facility asset and updating different map types of facility

Publication Date: 2025.05.15 HAO ALSTON

AI summary

The arrangements of the present disclosure are directed to systems, methods, and non-transitory computer-readable media for receive natural language input corresponding to a task to be performed by a dynamic asset within a facility, determine, using a Machine Learning (ML) model, first instructions for the dynamic asset to perform the task by applying the natural language input as a first input to the ML model. The first instructions includes a first location to which the dynamic asset is to move. The ML model receives feedback information comprising a metric determined using a current location of the dynamic asset. The ML model is updated using the current location of the dynamic asset. The ML model determines second instructions for the dynamic asset to perform the task, wherein the second instructions comprises a second location to which the dynamic asset is to move.