Method, electronic device, and computer program product for generating logs

An electronic device, comprising:

• at least one processor;
• and
• memory coupled to the at least one processor and having instructions stored therein, wherein the instructions, when executed by the at least one processor, cause the electronic device to perform operations comprising:
• generating, by a generator of a machine learning system comprising the generator and a discriminator, a pseudo-log based on a generating condition and random noise, the generator and the discriminator collectively comprising a generative adversarial network of the machine learning system;
• determining, by the discriminator, event types of log messages in a real log and the pseudo-log;
• determining, by the discriminator, a feature matrix of log sequences in the real log and the pseudo-log based on the event types;
• determining, by the discriminator, authenticity of the real log and the pseudo-log based on the feature matrix;
• and
• training the generator and the discriminator based on the authenticity, wherein the generator is trained at least in part while fixing the discriminator under a first set of one or more conditions, and the discriminator is trained at least in part while fixing the generator under a second set of one or more conditions.

A computer program product that is tangibly stored on a non-transitory computer-readable medium and comprises machine-executable instructions, wherein the machine-executable instructions, when executed by a machine, cause the machine to perform operations comprising:

• generating, by a generator of a machine learning system comprising the generator and a discriminator, a pseudo-log based on a generating condition and random noise, the generator and the discriminator collectively comprising a generative adversarial network of the machine learning system;
• determining, by the discriminator, event types of log messages in a real log and the pseudo-log;
• determining, by the discriminator, a feature matrix of log sequences in the real log and the pseudo-log based on the event types;
• determining, by the discriminator, authenticity of the real log and the pseudo-log based on the feature matrix;
• and
• training the generator and the discriminator based on the authenticity, wherein the generator is trained at least in part while fixing the discriminator under a first set of one or more conditions, and the discriminator is trained at least in part while fixing the generator under a second set of one or more conditions.