Method of completing a task

A server for completing a task, the task being of a given type of task, the server comprising:

• a processor;
• and
• a non-transient memory communicatively connected to the processor, the non-transient memory storing instructions that when executed by the processor, cause the server to:
• receive an indication of a first result of the task having been completed by a human assessor, the human assessor having a quality score indicative of a reliability of the first result;
• execute a machine learning algorithm (MLA) to complete the task by the MLA to generate a second result of the task, the MLA having a quality score indicative of a reliability of the second result;
• determine a confidence level parameter indicative of a probability of the first result being correct, the determining the confidence level parameter being based on the first result, the second result, the quality score of the human assessor, and the quality score of the MLA;
• determine whether the probability indicated by the determined confidence level parameter exceeds a pre-defined threshold probability;
• and
• in response to determining that the probability indicated by the determined confidence level parameter exceeds the pre-defined threshold probability, process the task as having been completed with the first result.