Geospatial AI Cube Inference With Task-to-Model Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spatiotemporal big data computing platforms face challenges in performing accurate and efficient artificial intelligence inference in multi-spatiotemporal or large-scale scenarios due to high computational complexity and dependency on specific temporal and spatial conditions, leading to low inference accuracy and slow inference speed.
Innovation Solution
An AI Cube-based online inference method that integrates spatiotemporal data and GeoAI models using a unified organizational model, employing explicit and implicit matching mechanisms, and a distributed inference framework for parallel processing of tile data across multiple computing nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single AI model is used for inference in multi-spatiotemporal scenarios, then the system complexity is low, but the inference accuracy deteriorates due to dependency on specific temporal and spatial conditions
Solution Approach 1:
The patent implements a multi-model inference system where multiple AI models with different spatial and temporal generalization capabilities are integrated into a unified framework. The system selectively applies different models based on the specific spatiotemporal characteristics of the input data, allowing the system to handle diverse inference scenarios universally while maintaining high accuracy for each specific case.
2Productivity
If massive remote sensing imagery is processed using traditional methods, then the data processing capability is sufficient for small-scale data, but the inference speed deteriorates due to high computational complexity and large data volumes
Solution Approach 1:
The patent divides massive remote sensing imagery into smaller tile units that can be processed independently and in parallel. This segmentation approach reduces the computational burden on each processing unit while enabling distributed computation across multiple resources, thereby significantly improving overall inference speed for large-scale datasets.
Solution Approach 2:
The patent introduces a distributed computing dimension by deploying AI models across multiple computing nodes. Instead of processing all data sequentially on a single system, the inference workload is distributed across multiple dimensions of computational resources, enabling parallel processing and dramatically reducing total inference time for massive datasets.
3Productivity
If cloud-based online computing platforms are used for spatiotemporal big data processing, then the data processing capability is improved, but the inference accuracy deteriorates in multi-spatiotemporal scenarios due to model performance dependency on specific conditions
Solution Approach 1:
The patent changes the parameter of model selection by dynamically choosing different AI models based on the spatiotemporal parameters of the input data. Instead of using a fixed model, the system adjusts which model is applied by evaluating the spatial and temporal characteristics of the data, thereby maintaining high inference accuracy across different conditions while leveraging cloud-based processing capabilities.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
The disclosure pertains to the field of data analysis and services, specifically to an online inference method, service system, and device based on an artificial intelligence geospatial data cube. The method involves constructing a cube organizational model based on a spatiotemporal grid, where the cube organizes and manages geospatial data and GeoAI models in a unified manner. It performs task-oriented model matching through a combination of explicit and implicit matching, where explicit matching converts user inference requests into multidimensional query conditions to retrieve candidate models, and implicit matching determines the optimal model by computing the feature similarity between inference data tiles and candidate models. Based on a distributed inference framework, an efficient inference workflow is executed in parallel across multiple computing nodes. The disclosure aims to address the limitations of existing technologies in multi-scenarios or large-scale spatial scenarios, such as low inference accuracy and slow inference speed.