Machine learning method, system and device and application method

Abstract

The invention relates to a machine learning method, a system, a device and an application method, which relate to the artificial intelligence field. The system comprises an interface module, an enginemodule and a database module. The interface module provides an interface with external communication, receives external input rules, training data and input information. The engine module realizes the supervised learning and obtains knowledge according to the rules and training data received by the interface module. The database module stores all kinds of data involved in machine learning. When the interface module receives a group of input information, the engine module selects the optimal knowledge to get the corresponding decision information, and outputs it through the interface module. The invention integrates the machine learning function into an entity independent of the system requiring the machine learning function, and when applied in an existing system, does not affect the basic architecture of the current product or system.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a machine learning method, system, equipment and application method. Background technique [0002] The goal of machine learning is how to use the "knowledge" acquired by the system itself to improve the performance of the system itself through computational methods or means. In the field of machine learning, "knowledge" usually exists in the form of "data". Therefore, the value of machine learning can be understood as calculating specific data (knowledge) from ubiquitous data, so as to use this specific data to improve the function and function of the system. performance. [0003] The general application model of machine learning is to organically combine machine learning algorithms with the current system to obtain a new system with machine learning functions. In other words, machine learning as the fundamental property and organic composition of new systems. In...

AI Technical Summary

Problems solved by technology

[0005] (1) The transformation from the original system to the new system requires a large investment

[0006] (2) The original system may have been very stable and reliable, but the new system after transformation may introduce new problems and damage the original stability and reliability of the system

[0007] (3) Increased complexity of the new system

[0008] (4) The scalability of the machine learning function is poor, and the enhancement of the machine learning function may affect the entire system

[0009] (5) The performance of the new system may not meet expectations due to the impact of the required resources

[0010] (6) The machine learning function cannot be shared with other systems

However, there is an essential difference between the CPU used by the embedded system and the CPU used by the general server. The CPU used by the embedded system has some special functions, but the general computing or storage function is weaker than the CPU used by the server; at the same time, the embedded system The software system is also more closed. If the machine learning function is embedded in the software system, not only will there be a problem of whether the CPU is competent, but the six problems mentioned above are also more obvious due to the closed nature of the software system.

Images