Method, device, and computer program product for error evaluation
Embodiments of the present disclosure provide a method, device, and computer program product for error evaluation. A method for error evaluation comprises in accordance with a determination that an error occurs in a data protection system, obtaining context information related to an operation of the data protection system; determining, based on the context information and using a trained deep learning model, a type of the error in the data protection system from a plurality of predetermined types, the deep learning model being trained based on training context information and a label on a ground-truth type of an error associated with the training context information; and providing the determined type of the error in the data protection system. In this way, it is possible to achieve automatic classification of errors in the data protection system, thereby improving the efficiency in error classification and saving the operation costs. Therefore, more rapid and more accurate measures can be taken to handle the errors.
1. A method for error evaluation, comprising:
in accordance with a determination that an error occurs in a data protection system, obtaining context information related to an operation of the data protection system, wherein the context information comprises screenshot information for a user interface of a client device of the data protection system when the error occurs;
determining, based on the context information and using a trained deep learning model, a type of the error in the data protection system from a plurality of predetermined types, the deep learning model being trained based on training context information and a label on a ground-truth type of an error associated with the training context information; and
providing the type of the determined error in the data protection system.
2. The method of claim 1 , wherein the context information further comprises at least one of the following types of information:
log information of the data protection system, the log information indicating events occurring in the data protection system recorded according in a temporal sequence; or
system status information of the data protection system.
3. The method of claim 2 , wherein the system status information indicates at least one of the following:
an usage rate of a total storage space of the data protection system,
an usage rate of a storage capacity allocated to a user of the data protection system,
an usage rate of an operating system of the data protection system,
an usage rate of a memory space of the data protection system,
a text system status of the data protection system,
a data garbage collection status of the data protection system,
a time duration since last data garbage collection of the data protection system,
an amount of protected data of the data protection system,
a processor status of the data protection system,
a number of device nodes in the data protection system,
a hardware type in the data protection system, or
a network connection status of the data protection system.
4. The method of claim 2 , wherein determining the type of the error in the data protection system comprises:
performing at least one of the following:
extraction of a first feature representation of the log information using a first feature extraction part of the deep learning model trained for processing a type of log information,
extraction of a second feature representation of the screenshot information using a second feature extraction part of the deep learning model trained for processing a type of screenshot information, or
extraction of a third feature representation of the system status information using a third feature extraction part of the deep learning model trained for processing a type of system status information; and
determining, based on at least one of the extracted first feature representation, second feature representation and third feature representation, the type of the error in the data protection system using a model part of the deep learning model trained for feature fusion.
5. The method of claim 4 , wherein determining the type of the error in the data protection system comprises performing the extraction of the second feature representation of the screenshot information using the second feature extraction part of the deep learning model trained for processing the type of screenshot information, and
wherein the second feature extraction part of the deep learning model comprises a Convolutional Neural Network (CNN) model structure configured to extract image features from an image associated with the screenshot information.
6. The method of claim 1 , wherein determining the type of the error in the data protection system comprises:
determining whether a rule-based decision model is capable of determining a type of the error in the data protection system from the context information; and
in accordance with a determination that the rule-based decision model cannot determine a type of the error in the data protection system, determining the type of the error in the data protection system using the deep learning model.
7. The method of claim 1 , wherein the deep learning model is re-trained for the plurality of determined types and a new type of error in accordance with a determination of a potential occurrence of the new type of error in the data protection system, such that the deep learning model is capable of determining the new type of error from context information related to the data protection system.
8. The method of claim 1 , wherein the plurality of predetermined types comprise one or more of the following types of errors: a hardware error, a system parameter configuration error, a network connection error, an error related to a third-party service of the data protection system, and an error in a data protection application.
9. The method of claim 1 , wherein the screenshot information comprises a screenshot of a graphical user interface (GUI) of the client device of the data protection system when the error occurs.
10. An electronic device, comprising:
a processor; and
a memory coupled to the processor, the memory storing instructions to be executed, the instructions, when executed by the processor, causing the electronic device to perform acts of:
in accordance with a determination that an error occurs in a data protection system, obtaining context information related to an operation of the data protection system, wherein the context information comprises screenshot information for a user interface of a client device of the data protection system when the error occurs;
determining, based on the context information and using a trained deep learning model, a type of the error in the data protection system from a plurality of predetermined types, the deep learning model being trained based on training context information and a label on a ground-truth type of an error associated with the training context information; and
providing the determined type of the error in the data protection system.
11. The electronic device of claim 10 , wherein the context information further comprises at least one of the following types of information:
log information of the data protection system, the log information indicating events occurring in the data protection system recorded according in a temporal sequence; or
system status information of the data protection system.
12. The electronic device of claim 11 , wherein the system status information indicates at least one of the following:
an usage rate of a total storage space of the data protection system,
an usage rate of a storage capacity allocated to a user of the data protection system,
an usage rate of an operating system of the data protection system,
an usage rate of a memory space of the data protection system,
a text system status of the data protection system,
a data garbage collection status of the data protection system,
a time duration since last data garbage collection of the data protection system,
an amount of protected data of the data protection system,
a processor status of the data protection system,
a number of device nodes in the data protection system,
a hardware type in the data protection system, or
a network connection status of the data protection system.
13. The electronic device of claim 11 , wherein determining the type of the error in the data protection system comprises:
performing at least one of the following:
extraction of a first feature representation of the log information using a first feature extraction part of the deep learning model trained for processing a type of log information,
extraction of a second feature representation of the screenshot information using a second feature extraction part of the deep learning model trained for processing a type of screenshot information, or
extraction of a third feature representation of the system status information using a third feature extraction part of the deep learning model trained for processing a type of system status information; and
determining, based on at least one of the extracted first feature representation, second feature representation and third feature representation, the type of the error in the data protection system using a model part of the deep learning model trained for feature fusion.
14. The electronic device of claim 13 , wherein determining the type of the error in the data protection system comprises performing the extraction of the second feature representation of the screenshot information using the second feature extraction part of the deep learning model trained for processing the type of screenshot information, and
wherein the second feature extraction part of the deep learning model comprises a Convolutional Neural Network (CNN) model structure configured to extract image features from an image associated with the screenshot information.
15. The electronic device of claim 10 , wherein determining the type of the error in the data protection system comprises:
determining whether a rule-based decision model is capable of determining a type of the error in the data protection system from the context information; and
in accordance with a determination that the rule-based decision model cannot determine a type of the error in the data protection system, determining the type of the error in the data protection system using the deep learning model.
16. The electronic device of claim 10 , wherein the deep learning model is re-trained for the plurality of determined types and a new type of error in accordance with a determination of a potential occurrence of the new type of error in the data protection system, such that the deep learning model is capable of determining the new type of error from context information related to the data protection system.
17. The electronic device of claim 10 , wherein the plurality of predetermined types comprise one or more of the following types of errors: a hardware error, a system parameter configuration error, a network connection error, an error related to a third-party service of the data protection system, and an error in a data protection application.
18. The electronic device of claim 10 , wherein the screenshot information comprises a screenshot of a graphical user interface (GUI) of the client device of the data protection system when the error occurs.
19. A computer program product being tangibly stored on a non-transitory computer readable medium and comprising computer-executable instructions which, when executed, cause a processor to perform operations, the operations comprising:
in accordance with a determination that an error occurs in a data protection system, obtaining context information related to an operation of the data protection system, wherein the context information comprises screenshot information for a user interface of a client device of the data protection system when the error occurs;
determining, based on the context information and using a trained deep learning model, a type of the error in the data protection system from a plurality of predetermined types, the deep learning model being trained based on training context information and a label on a ground-truth type of an error associated with the training context information; and
providing the type of the determined error in the data protection system.
20. The computer program product of claim 19 , wherein the context information comprises at least one of the following types of information:
log information of the data protection system, the log information indicating events occurring in the data protection system recorded according in a temporal sequence; or
system status information of the data protection system.