Data type recognition, model training and risk recognition methods, apparatuses and devices
Data type recognition and model training methods and apparatuses, and computer devices are provided. The model training method includes acquiring a first sample data set, and using the first sample data set to train an anomaly detection model; and detecting an abnormal sample data set from a second sample data set by means of the anomaly detection model, and using the abnormal sample data set to train a classification model. By using this method, an amount of scoring events of the classification model can be reduced, and relatively balanced sample data sets can also be provided for training, to obtain the classification model with a higher accuracy.
1. A model training method for training an anomaly detection model and a classification model, comprising:
training the anomaly detection model, wherein the anomaly detection model is a first machine learning model configured to detect data of a first type, and the anomaly detection model is trained by: acquiring a first sample data set, wherein an amount of data of the first type in the first sample data set is greater than an amount of data of a second type in the first sample data set; and using the first sample data set to train the anomaly detection model; and
training the classification model, wherein the classification model is a second machine learning model configured to classify other data than the data of the first type detected by the anomaly detection model, and the classification model is trained by: detecting, by the anomaly detection model, an abnormal sample data set from a second sample data set; and using the abnormal sample data set to train the classification model.
2. The method according to claim 1 , before using the abnormal sample data set to train the classification model, the method further comprising:
optimizing the abnormal sample data set based on a feature optimization algorithm.
3. The method according to claim 1 , further comprising:
acquiring data to be recognized, and using the trained anomaly detection model to detect whether the data to be recognized is abnormal;
if the data to be recognized is detected not to be abnormal, determining that the data to be recognized is secure data; and
if the data to be recognized is detected to be abnormal, using the trained classification model to recognize that the data to be recognized is secure data or risky data.
4. The method according to claim 3 , wherein an amount of secure data is greater than an amount of risky data in the first sample data set.
5. A computer device, comprising:
a processor; and
a memory for storing instructions executable by the processor,
wherein the processor is configured to train an anomaly detection model and a classification model, the anomaly detection model being a first machine learning model configured to detect data of a first type, the classification model being a second machine learning model configured to classify other data than the data of the first type detected by the anomaly detection model;
wherein in training the anomaly detection model, the processor is further configured to: acquire a first sample data set, an amount of data of the first type in the first sample data set being greater than an amount of data of a second type in the first sample data set; and use the first sample data set to train the anomaly detection model; and
wherein in training the classification model, the processor is further configured to: detect, by the anomaly detection model, an abnormal sample data set from a second sample data set; and use the abnormal sample data set to train the classification model.
6. The computer device according to claim 5 , wherein before using the abnormal sample data set to train the classification model, the processor is further configured to:
optimize the abnormal sample data set based on a feature optimization algorithm.
7. The computer device according to claim 5 , wherein the processor is further configured to:
acquire data to be recognized, and use the trained anomaly detection model to detect whether the data to be recognized is abnormal;
if the data to be recognized is detected not to be abnormal, determine that the data to be recognized is secure data; and
if the data to be recognized is detected to be abnormal, use the trained classification model to recognize that the data to be recognized is secure data or risky data.
8. The computer device according to claim 7 , wherein an amount of secure data is greater than an amount of risky data in the first sample data set.
9. A non-transitory computer-readable storage medium having stored therein instructions that, when executed by a processor of a computer device, cause the computer device to perform a model training method for training an anomaly detection model and a classification model, the method comprising:
training the anomaly detection model, wherein the anomaly detection model is a first machine learning model configured to detect data of a first type, and the anomaly detection model is trained by: acquiring a first sample data set, wherein an amount of data of the first type in the first sample data set is greater than an amount of data of a second type in the first sample data set; and using the first sample data set to train the anomaly detection model; and
training the classification model, wherein the classification model is a second machine learning model configured to classify other data than the data of the first type detected by the anomaly detection model, and the classification model is trained by: detecting, by the anomaly detection model, an abnormal sample data set from a second sample data set; and using the abnormal sample data set to train the classification model.
10. The non-transitory computer-readable storage medium according to claim 9 , before using the abnormal sample data set to train the classification model, the method further comprising:
optimizing the abnormal sample data set based on a feature optimization algorithm.
11. The non-transitory computer-readable storage medium according to claim 9 , the method further comprising:
acquiring data to be recognized, and using the trained anomaly detection model to detect whether the data to be recognized is abnormal;
if the data to be recognized is detected not to be abnormal, determining that the data to be recognized is secure data; and
if the data to be recognized is detected to be abnormal, using the trained classification model to recognize that the data to be recognized is secure data or risky data.
12. The non-transitory computer-readable storage medium according to claim 11 , wherein an amount of secure data is greater than an amount of risky data in the first sample data set.