Directional artificial intelligence training method and device and storage medium

Abstract

The invention discloses a training method of agricultural directional artificial intelligence. Graphic data of agricultural land and corresponding agricultural data are continuously collected, and pretreatment is performed, a training set and a test set are performed, a simulation platform is built, a corresponding artificial intelligence algorithm is selected according to the performance of thecomputing terminal, training is performed through a parallel virtual system; calculation power distribution is performed according to performance requirements in various artificial intelligence algorithms, an evaluation network is constructed, each decision is evaluated, the decision training efficiency is improved, the decision made by each grid is planned as a whole, the cost of the made corresponding decision is selected according to the grid distance, and the obtained optimal decision is deployed. According to the method, training is carried out in a single operation node through multipleartificial intelligence training methods, more parallel operations of a CPU and a GPU are mobilized under the condition that the computing power is limited, an evaluation function is introduced to reduce the training expenditure, and the operation cost of agricultural execution is greatly reduced.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a training method, device and storage medium for directional artificial intelligence. Background technique [0002] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. Machine learning is the learning of computational methods that automate the acquisition of knowledge. The purpose is to make the computer acquire new knowledge or...

AI Technical Summary

Problems solved by technology

[0004] For agricultural data, the difficulty of data collection now is that due to the particularity of agriculture, the data is too fragmented, and the nature of the land between 50 mu and 50 mu in 100 mu is different. If there is not enough algorithmic AI, it will not be able to handle it at all. With such data, even if the same algorithm is used for decision-making, the results obtained are not the best

Images