Stock K-line image recognition method and device, intelligent terminal and storage medium

Abstract

The invention discloses a stock K-line image recognition method and device, an intelligent terminal and a storage medium. The method comprises the steps of obtaining a to-be-recognized stock K-line image; using the trained stock K-line image recognition model to recognize the to-be-recognized stock K-line image, and obtaining a classification recognition result corresponding to the to-be-recognized stock K-line image; wherein the stock K-line image recognition model is a residual convolutional network model. According to the method, the convolutional neural network technology in deep learningis utilized to perform intelligent identification on the stock data, the visual features of the stock K-line graph are extracted, the future trend of the stock is predicted by utilizing the visual features, and the stock prediction accuracy is improved. And a reasonable and correct transaction prompt is provided for the user. The problem that the prediction result is inaccurate when the stock trend is predicted by using the stock K-line graph in the prior art is solved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a stock K-line image recognition method, a storage medium and an intelligent terminal. Background technique [0002] In stock trading, stockholders usually need to study and judge the trend of the stocks they buy before trading. In addition to considering the fundamentals of the stocks they want to buy and sell, they often also need to study and judge the recent trends of the stock market and individual stocks. The reference is the stock K-line chart . K-line charts are also called Japanese candlestick charts. According to time, they can be divided into time-sharing charts such as daily, weekly, monthly, seasonal, annual, hourly, and minute lines. The K-line consists of the opening price, closing price, highest price, and lowest price of the day. [0003] When stockholders study and judge the K-line chart, most of them trade on the so-called right side, that is, when ...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a stock K-line chart identification method, device, intelligent terminal and storage medium for the above-mentioned defects of the prior art, aiming to solve the problem of doping Too many human factors and inaccurate analysis results

Images