Abstract: Provided is an ensemble learning (EL)-based speaker verification method. The method includes: data acquisition and preprocessing; selecting and training a group of basic models, and optimizing model parameters; performing similarity scoring on an acquired pair of speaker feature embedding via the group of basic models; constructing a detection cost function (DCF); generating a weight, and performing weighted fusion on scoring results of the group of basic models based on the weight, to obtain a final ensemble model for speaker verification; based on a near-speaking or far-speaking test scenario of a voice sample, the scenario is distinguished and input into the ensemble model, to obtain a final similarity score after weighted fusion; and determining, based on a threshold, whether there is a same speaker, where if the similarity score is greater than the threshold, it is determined that there is a same speaker.

Abstract: Disclosed are a bus parking allocation method and apparatus considering operational preferences. The method includes: obtaining a bus station dataset, a parking lot dataset, a bus information dataset, and a bus departure/return dataset; obtaining a distance dataset containing distances between bus stations and parking lots; building a parking allocation model considering operational preferences; building an objective function of the parking allocation model, where one group of buses are allocated to one group of parking lots, with each bus being allocated to at most one parking lot, and the number of buses parked in each parking lot is less than or equal to a capacity of the parking lot; building bus preference lists and parking lot preference lists, and calculating the objective function while satisfying the preference lists, to minimize total parking costs of all buses, thereby obtaining parking allocation results considering operational preferences; and designing multiple visualization views for display.