APP violation monitoring method based on OCR and transfer learning

The invention discloses an APP violation monitoring method based on OCR and transfer learning, and the method comprises the steps: periodically updating an APK, collecting data of a corresponding APPaccording to the updated APK by data capture and page screenshot; performing character recognition and extraction on the screenshot based on an OCR algorithm; carrying out sample set construction on the recognized text content through keywords and regular expressions, and carrying out manual annotation; inputting the manually labeled sample set into a pre-trained deep learning model for model adjustment, and realizing violation judgment of texts in different scenes by dividing service scenes; and according to a discrimination result output by the deep learning model, carrying out statistics onscores of different APPs to obtain violation scores of the APPs. According to the invention, the data of the APP is collected and analyzed, so that the violation use condition of the APP can be effectively and quickly detecte