Sequence data prediction system of novel multi-scale attention mechanism

Abstract

The invention discloses a sequence data prediction system of a novel multi-scale attention mechanism. The sequence data prediction system comprises a sequence data coding module combined with time feature coding, a multi-scale time feature extraction module and a long sequence rapid prediction module; the sequence data coding module combined with time characteristic coding codes sequence data andtime characteristics of an input sequence to obtain a new input vector; the multi-scale time feature extraction module is used for segmenting the new input vector, inputting the segmented new input vector into a corresponding feature extraction structure, and combining the extracted sequence features of different time scales to obtain stable and effective time sequence representation; and the long-sequence rapid prediction module constructs an initial input sequence, performs data encoding and then performs fusion to obtain a prediction output result.

Description

technical field [0001] The invention relates to a sequence data prediction system, in particular to a sequence data prediction system with a novel multi-scale attention mechanism. Background technique [0002] Sequence data refers to a collection of observations collected in a certain order. Taking time series as an example, it is a set of data arranged in time order. Sequence data widely exists in all aspects of social life and industrial production, such as medical diagnosis, meteorological research, power system, intelligent transportation, etc. The prediction of sequence data is a typical data science task, and accurate and effective prediction results are of great significance to the decision-making of data application scenarios. [0003] Sequence data often contains time dependence, that is, the generation of data in the sequence is closely related to change and time. Time series has the characteristics of seasonality, cycle, trend and randomness, etc. Accurate predi...

AI Technical Summary

Problems solved by technology

However, various RNN-based models, which are the basic methods of sequence prediction in deep learning, have the disadvantages of high time cost and low accuracy when predicting long sequences.

Images