Mobile Machine Status GUI With AI Gap Filling Over Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile machine operation tracking systems rely heavily on manual recording and lack consideration for complex interactions between terrain, ground conditions, soil type, and weather, leading to incomplete and inaccurate datasets, which increase operational costs and reduce productivity.
Innovation Solution
Implement a machine learning or deep learning-based model to track mobile machine operational statuses at intervals of time, generating graphical user interfaces (GUIs) that provide a chronological view of operations, incorporating environmental factors and machine locations, using satellite and sensor data to enhance data completeness and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual recording methods are used to track mobile machine operations, then operators can maintain control of machines, but recording completeness and accuracy deteriorate due to human error and multitasking demands
Solution Approach 1:
The system enables self-service tracking where the mobile machine automatically records its own operational data through integrated sensors and processors, eliminating the need for manual recording by operators while maintaining continuous and accurate data collection throughout operations
Solution Approach 2:
The patent replaces manual mechanical recording methods with automated electronic sensing and processing systems that continuously capture operational parameters, location data, and environmental conditions without requiring operator intervention
2Loss of information
If automated tracking systems are implemented, then data collection improves, but system complexity and cost increase
Solution Approach 1:
The system employs multi-functional sensors and processors that simultaneously capture operational data, location information, and environmental conditions, reducing overall system complexity by consolidating multiple tracking functions into integrated components
Solution Approach 2:
The patent utilizes changes in physical parameters detected by sensors (such as position, speed, temperature, humidity) to automatically infer operational status and fill data gaps, reducing the need for complex manual tracking mechanisms
3Productivity
If simple computational methods are used to fill data gaps, then processing speed is maintained, but accuracy deteriorates due to inability to consider complex environmental interactions
Solution Approach 1:
The system implements feedback mechanisms where collected operational data and environmental parameters are continuously analyzed to identify and fill data gaps, with results fed back into the tracking system to improve subsequent data accuracy while maintaining processing efficiency
Solution Approach 2:
The patent combines multiple data sources and sensor inputs into a composite operational profile, integrating diverse information streams (machine sensors, environmental sensors, historical data) to create accurate operational records that account for complex environmental interactions
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Technologies for generating GUIs for tracked mobile machine operational statuses. In some embodiments, a method includes receiving, by a computing system (102, 200), machine operational status information (111a, 111b) of a mobile machine (110) that has moved through an area of land during a time period (step 302). The received machine status information (111a, 111b) including respective operational statuses of the machine (110) at each interval of intervals of time within the time period. The method also including generating, by the computing system (102, 200), a GUI (102d) according to the status information (111a, 111b) (step 304). The GUI (102d) including a calendar view (900) of the statuses. In some cases, the operational status information (111a) includes respective operational statuses of the machine at only some intervals within the time period. And, the statuses of the machine that are missing can be generated by a model (108) that is trained by the available statuses received by the system.