Unlock instant, AI-driven research and patent intelligence for your innovation.

Fishing condition prediction method and system based on cellular grid integration mechanism and space-time Transformer

A forecasting method and fishing situation technology, applied in forecasting, neural learning methods, computer components, etc., can solve the problems of little guiding significance, time and space are not fine-grained, etc., to enrich the sample size, reduce the feature dimension, Effects that improve accuracy and robustness

Active Publication Date: 2022-02-01
JIANGSU DAWN INFORMATION TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these data are not fine-grained in time and space, and have little guiding significance for practical applications.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fishing condition prediction method and system based on cellular grid integration mechanism and space-time Transformer
  • Fishing condition prediction method and system based on cellular grid integration mechanism and space-time Transformer
  • Fishing condition prediction method and system based on cellular grid integration mechanism and space-time Transformer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In the following description, a large amount of specific details are given to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, there is no description thereof in the art.

[0043] Applicants believe that due to over-fishing phenomena, the offshore fishery resource environment has been severely damaged, which makes the marine fishery resources in jeopardy, in order to maintain the sustainable development and utilization of fishery resources, through reasonable predictions of future fishery resources, provide decision-making basis for moderate fishing . However, prior art is performing fishing predictions, due to relatively small number of sensors in the ocean, fishing data is not easy to obtain, predict data in time and space is not fine-grained, r...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a fishing condition prediction method and system based on a cellular grid integration mechanism and a space-time Transformer, and provides a local-to-local prediction framework based on cellular grid region division and an integration mechanism aiming at the defect that grid division does not have isotropy in the prior art, so that the sample size is remarkably enriched, and the feature dimension is reduced; meanwhile, in order to better capture the spatio-temporal characteristics, the invention further provides a spatio-temporal Transform framework, and the framework provides a valuable insight for spatio-temporal data mining. According to the invention, in the data prediction process, dependency analysis is performed on the basis of marine environment data by combining data features in time and space dimensions, the defect of time dependency in the prior art is overcome, and the model prediction accuracy is improved.

Description

Technical field [0001] The present invention relates to a fishery prediction method and system based on a honeycomb grid integration mechanism and a space-time transformer, in particular to a field involving data integrated mining and analysis. Background technique [0002] Marine fishery resources plays an irreplaceable role in human survival and development, is part of the main economic activities of modern society. However, with the expansion of the fishing area and the high-intensity fishing of the fishery resource regeneration, the offshore fishery resource environment is seriously damaged, and the marine fishery resources are in jeopardy. In order to maintain the sustainable development and utilization of fishery resources, the rational configuration of fishery resources is achieved, and the basis for the moderate fishing is provided to moderate fishing. [0003] Prior Art In realizing future fishery resource prediction, due to the predicted future fish group, it needs the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/02G06N3/08G06K9/62
CPCG06Q10/04G06Q50/02G06N3/08G06F18/23G06F18/25
Inventor 刘玉海孙允超苏海涛张建一宋怀明
Owner JIANGSU DAWN INFORMATION TECH CO LTD