Abstract: A method for distributing an equity reward for federated learning based on an equity theory includes the following steps: applying Adams' equity theory to federated learning, analyzing, by a participant, all factors invested in a federated task comprehensively, then giving an expected reward for this task, calculating, by the task publisher, the reputation of the participant; participating, by the participant, in each round of a training task using a local data to evaluate data contribution, model contribution, and a waiting-time allowance of the participant, then combining contribution results of the three factors to evaluate the contribution of the participant; after a global model converges, dynamically adjusting weights of the three factors according to an objective function of the equity reward, with a goal that an actual reward of the participant is as close as possible to the expected reward, and obtaining and distributing the actual reward of the participant.

Abstract: A method, a system, and a device for rapidly exiting training are provided. The method includes: in a training procedure of a Vectored-Digital Subscriber Line (DSL) filter, comparing a feedback error value of the filter and/or a swing range of a filter coefficient with a preset threshold, and determining whether the filter meets a convergence condition according to a comparison result; and exiting the training procedure of the filter when the filter meets the convergence condition. The method, system, and device are applicable to a training procedure of a Vectored-DSL precoder or canceller, so as to rapidly exit the training procedure.

Abstract: A method, a system, and a device for power adjustment are provided. The method includes: determining whether transmission power of a line needs adjustment according to feedback errors during a training procedure of a Vectored-Digital Subscriber Line (Vectored-DSL) filter; and adjusting the transmission power when the transmission power of the line needs adjustment. By automatically determining whether the transmission power needs adjustment during a training procedure of a precoder or canceller, and adjusting the transmission power automatically when the transmission power needs adjustment, interference to other subscribers caused by the precoder or canceller during the training procedure is reduced, and call drops of the other subscribers are prevented.

Abstract: A filtering method, system, and equipment applied in digital communication technologies are disclosed in the embodiments of the present invention. The filtering method of the present embodiments includes: acquiring filtering coefficients of a part of all subcarriers according to data transmission errors; acquiring filtering coefficients of remaining subcarriers through an interpolation algorithm according to the filtering coefficients of the part of subcarriers; and finally, filtering the data corresponding to the multiple subcarriers according to the filtering coefficients of the part of subcarriers and the filtering coefficients of the remaining subcarriers. The part of subcarriers may be selected at a regular interval, or may be subcarriers which are located at a motion value away from the part of subcarriers selected in the previous update of the filtering coefficients. The method of the present embodiments reduces the amount of operation and hardware expenditure, and saves the cost.

Abstract: A filtering method, system, and equipment applied in digital communication technologies are disclosed in the embodiments of the present invention. The filtering method of the present embodiments includes: acquiring filtering coefficients of a part of all subcarriers according to data transmission errors; acquiring filtering coefficients of remaining subcarriers through an interpolation algorithm according to the filtering coefficients of the part of subcarriers; and finally, filtering the data corresponding to the multiple subcarriers according to the filtering coefficients of the part of subcarriers and the filtering coefficients of the remaining subcarriers. The part of subcarriers may be selected at a regular interval, or may be subcarriers which are located at a motion value away from the part of subcarriers selected in the previous update of the filtering coefficients. The method of the present embodiments reduces the amount of operation and hardware expenditure, and saves the cost.

Abstract: A line measurement method is provided. The method includes obtaining data of relation between a line length and an insertion loss phase radian, and obtaining data of relation between the line length and a loop attenuation parameter value; obtaining four length values from the data of relation between the line length and the insertion loss phase radian, and defining a length range to obtain the first and the second length range; and determining the boundary of the second length range close to a midpoint of the first length range, using a line length value corresponding to the boundary close to the midpoint as a measured line length, and using a line diameter corresponding to the line length value as a measured line diameter.

Abstract: A method, a system, and a device for rapidly exiting training are provided. The method includes: in a training procedure of a Vectored-Digital Subscriber Line (DSL) filter, comparing a feedback error value of the filter and/or a swing range of a filter coefficient with a preset threshold, and determining whether the filter meets a convergence condition according to a comparison result; and exiting the training procedure of the filter when the filter meets the convergence condition. The method, system, and device are applicable to a training procedure of a Vectored-DSL precoder or canceller, so as to rapidly exit the training procedure.

Abstract: A method, a system, and a device for power adjustment are provided. The method includes: determining whether transmission power of a line needs adjustment according to feedback errors during a training procedure of a Vectored-Digital Subscriber Line (Vectored-DSL) filter; and adjusting the transmission power when the transmission power of the line needs adjustment. By automatically determining whether the transmission power needs adjustment during a training procedure of a precoder or canceller, and adjusting the transmission power automatically when the transmission power needs adjustment, interference to other subscribers caused by the precoder or canceller during the training procedure is reduced, and call drops of the other subscribers are prevented.

Abstract: A line measurement method is provided. The method includes obtaining data of relation between a line length and an insertion loss phase radian, and obtaining data of relation between the line length and a loop attenuation parameter value; obtaining four length values from the data of relation between the line length and the insertion loss phase radian, and defining a length range to obtain the first and the second length range; and determining the boundary of the second length range close to a midpoint of the first length range, using a line length value corresponding to the boundary close to the midpoint as a measured line length, and using a line diameter corresponding to the line length value as a measured line diameter.