Abstract: A machine learning model that uses composite metrology data determines at least one parameter of a device under test using measured metrology data from the device. The composite metrology data is generated by merging measured metrology data from a reference device with synthetic metrology data calculated from a model of the reference device. The composite metrology data may be generated further based on a synthetic metrology data calculated from a model for a modified reference device. The modified reference device may be generated using variations of at least one parameter of the model to expand the parameter space of the training range.

Abstract: A method and system of controlling a multi-leaf collimator, wherein steps of the method includes: receiving treatment data, and the treatment data includes position information of N treatment points, conformal position information of N treatment points and radiation field shapes of N treatment points; controlling a treatment head to a conformal position of a first treatment point, and controlling the multi-leaf collimator to begin to conform to a radiation field shape of the first treatment point so as to start a treatment of the first treatment point; controlling the treatment head to a conformal position of a Kth treatment point, and controlling the multi-leaf collimator to begin to conform to a radiation field shape of the Kth treatment point so as to start a treatment of the Kth treatment point; carrying out the described operations repeatedly until the conformation of the radiation field shape and the treatment of all treatment points are completed.

Abstract: The present disclosure relates to a question recommending method, apparatus, and system. The method includes: constructing, by a server, an interest vector of a user according to a short-term interest, a long-term interest, and a group interest of the user, the interest vector of the user including multiple interest items; acquiring a candidate-for-recommendation question from a set of to-be-resolved questions according to the multiple interest items; estimating, according to a click-through rate (CTR) model, probability of answering the candidate-for-recommendation question by the user, and selecting a to-be-recommended question according to the estimated probability; and sending the to-be-recommended question to a client. In this way, a real-time comprehensive recommendation result can be obtained, and a question answering rate of an interactive question-and-answer platform can also be improved.

Abstract: The present disclosure relates to a question recommending method, apparatus, and system. The method includes: constructing, by a server, an interest vector of a user according to a short-term interest, a long-term interest, and a group interest of the user, the interest vector of the user including multiple interest items; acquiring a candidate-for-recommendation question from a set of to-be-resolved questions according to the multiple interest items; estimating, according to a click-through rate (CTR) model, probability of answering the candidate-for-recommendation question by the user, and selecting a to-be-recommended question according to the estimated probability; and sending the to-be-recommended question to a client. In this way, a real-time comprehensive recommendation result can be obtained, and a question answering rate of an interactive question-and-answer platform can also be improved.