Abstract: A machine learning method is provided, including: obtaining training data, where the training data includes a training feature, training labels, and a training weight; inputting the training data to a first machine learning model, where the first machine learning model has first model data, the first model data includes a first model feature, first model labels, and first model weights, and the first model labels correspond to the first model weights in a one-to-one manner; and training the first machine learning model by using a training step to obtain a second machine learning model. The training step includes: when the first model feature matches the training feature, and one of the first model labels is the same as any of the training labels, adjusting the first model weight corresponding to the first model label that is the same as any of the training labels according to the training weight.

Abstract: A work log posting system includes a project database, a meeting record analysis module, a project classification module, and a work log module. The project database stores a plurality of keyword sets, each corresponding to a project. The meeting record analysis module analyzes a meeting record including a statement content, an attendance list, and a meeting period, to extract a plurality of terms from the statement content of the meeting record. The project classification module classifies the meeting record to one of the projects according to the relevance between the terms in the statement content and each keyword set. The work log module counts, according to the classification result of the meeting record, the meeting period attended by each person on the attendance list and the project to which the meeting period belongs, so as to preload the statistical result into a work log.