Time series data risk prediction method and system based on knowledge guidance, and application thereof

Abstract

The invention discloses a time series data risk prediction method and system based on knowledge guidance, and application thereof. The method comprises the following steps: collecting sample time series data, converting each piece of sample time series data into an input sequence matrix, and acquiring the feature information of risk events and an event relation from a knowledge graph; inputting adistance weight matrix, and the feature information of the risk events and the event relation into a preset network model to obtain two context vectors, and performing full connection on the two context vectors to realize risk prediction; training a preset network model according to each sample time series data sequence and the two context vectors, performing supervised training, and carrying outtraining to a preset convergence condition when risk occurrence probability is obtained so as to obtain a trained risk prediction model; and performing risk prediction via the obtained risk predictionmodel. The method is more reasonable and effective in time series data representation, and can improve the accuracy of time series data risk prediction.

Description

technical field [0001] The invention belongs to the technical field of data mining of time series data, and in particular relates to a method, system and application of time series data risk prediction based on knowledge guidance. Background technique [0002] In recent years, various data-based forecasting methods have been produced, and risk forecasting based on time series data is one of the important applications in data mining and machine learning. It can be widely used in many application areas such as medical treatment, data retrieval, and cohort analysis. In the past decade, this field has attracted extensive research interest and made great progress, but the temporality, heterogeneity, high dimensionality and irregularity of time series data pose great challenges to the research in this field. [0003] Since the limited amount of data cannot meet the large number of samples required by the latest methods, especially for deep learning models, the insufficient amount...

AI Technical Summary

Problems solved by technology

[0003] Since the limited amount of data cannot meet the large number of samples required by the latest methods, especially for deep learning models, the insufficient amount of data makes the accuracy of the model unable to achieve the desired ideal

In addition, during the data collection process, some missing data records may contain important data information, which may have an important guiding effect on the experimental results. If such data information is ignored, it will lead to prediction bias

Time-series data is sparse, high-dimensional, unequal-dimensional, sequential and irregular. Most of the existing risk prediction models are purely data-driven and cannot incorporate the defects of relevant auxiliary knowledge. Taking into account the relationship, the function of not being able to extract more information from insufficient data input affects the reliability and accuracy of the prediction results

Deep learning-based methods cannot determine the contribution of each event to the final result, which prevents such models from being widely accepted in practical applications

Images