Abstract: In a neural network training method, a training device trains a neural network model based on a second training data set to obtain a target neural network model. The neural network model includes an expert network layer, which includes a first expert network of a first service field. The training device determines an initial weight of the first expert network based on a first word vector matrix, and obtains the first word vector matrix through training based on a first training data set of the first service field.

Abstract: A method and apparatus for scheduling an item, and a computer-readable storage medium are provided. The method can include acquiring a first time sequence corresponding to a target item in a target warehouse, the first time sequence including shipment volume information of the target item corresponding to each unit time within a first historical period. The method can further include determining, according to the first time sequence and a target period to be predicted, total shipment volume information of the target item within a target period through a shipment prediction model, the shipment prediction model including a plurality of parallel first time sequence sub-models and a weighted sub-model which is connected to an output of each of the first time sequence sub-models, and scheduling the target item in the target warehouse according to the total shipment volume information and current inventory information of the target item in the target warehouse.

Abstract: A clustering method includes: multiple data to be clustered are acquired, the data to be clustered including exact matching information; multiple data sets consisting of data to be clustered with same exact matching information are determined; a clustering center is determined according to the amount of data to be clustered in each of the multiple data sets; and the multiple data to be clustered are clustered according to the clustering center to obtain target clusters. Accordingly, multiple data sets each consisting of data to be clustered with same exact matching information are determined, and a clustering center is determined according to the amount of the data to be clustered in each of the multiple data sets, so that unreasonable determination of the clustering centers can be improved, and accuracy of a clustering algorithm can further be improved.

Abstract: A method and apparatus for scheduling an item, and a computer-readable storage medium are provided. The method can include acquiring a first time sequence corresponding to a target item in a target warehouse, the first time sequence including shipment volume information of the target item corresponding to each unit time within a first historical period. The method can further include determining, according to the first time sequence and a target period to be predicted, total shipment volume information of the target item within a target period through a shipment prediction model, the shipment prediction model including a plurality of parallel first time sequence sub-models and a weighted sub-model which is connected to an output of each of the first time sequence sub-models, and scheduling the target item in the target warehouse according to the total shipment volume information and current inventory information of the target item in the target warehouse.

Abstract: A location information processing method and apparatus, a storage medium, and a processor are provided. The method includes obtaining motion information of a plurality of first terminals at a current moment; generating a location sequence of the plurality of first terminals according to the motion information, the location sequence indicating correspondence between locations of the plurality of first terminals and one or more future moments; receiving a first viewing request from a target terminal, the first viewing request requesting to view locations of the plurality of first terminals at a target moment, the target moment being one of the future moments; searching the location sequence for the locations of the plurality of first terminals at the target moment according to the first viewing request; and sending indication information to the target terminal, the indication information indicating the locations of the plurality of first terminals at the target moment.

Abstract: A clustering method includes: multiple data to be clustered are acquired, the data to be clustered including exact matching information; multiple data sets consisting of data to be clustered with same exact matching information are determined; a clustering center is determined according to the amount of data to be clustered in each of the multiple data sets; and the multiple data to be clustered are clustered according to the clustering center to obtain target clusters. Accordingly, multiple data sets each consisting of data to be clustered with same exact matching information are determined, and a clustering center is determined according to the amount of the data to be clustered in each of the multiple data sets, so that unreasonable determination of the clustering centers can be improved, and accuracy of a clustering algorithm can further be improved.

Abstract: A location information processing method and apparatus, a storage medium, and a processor are provided. The method includes obtaining motion information of a plurality of first terminals at a current moment; generating a location sequence of the plurality of first terminals according to the motion information, the location sequence indicating correspondence between locations of the plurality of first terminals and one or more future moments; receiving a first viewing request from a target terminal, the first viewing request requesting to view locations of the plurality of first terminals at a target moment, the target moment being one of the future moments; searching the location sequence for the locations of the plurality of first terminals at the target moment according to the first viewing request; and sending indication information to the target terminal, the indication information indicating the locations of the plurality of first terminals at the target moment.

Abstract: A computer-implemented method for combining static and dynamic code analysis may include 1) identifying executable code that is to be analyzed to determine whether the executable code is capable of leaking sensitive data, 2) performing a static analysis of the executable code to identify one or more objects which the executable code may use to transfer sensitive data, the static analysis being performed by analyzing the executable code without executing the executable code, 3) using a result of the static analysis to tune a dynamic analysis to track the one or more objects identified during the static analysis, and 4) performing the dynamic analysis by, while the executable code is being executed, tracking the one or more objects identified during the static analysis to determine whether the executable code leaks sensitive data via the one or more objects. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A computer-implemented method for dynamically modifying rules for selecting suitable mobile networks. The method may include (1) identifying a set of predefined rules for selecting suitable mobile networks with which to connect, (2) obtaining a training data set that includes data about at least one candidate mobile network, (3) using machine learning to dynamically adjust, based at least in part on the training data set, the set of predefined rules, and (4) connecting to a suitable mobile network identified by the dynamically adjusted set of predefined rules. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A computer-implemented method for combining static and dynamic code analysis may include 1) identifying executable code that is to be analyzed to determine whether the executable code is capable of leaking sensitive data, 2) performing a static analysis of the executable code to identify one or more objects which the executable code may use to transfer sensitive data, the static analysis being performed by analyzing the executable code without executing the executable code, 3) using a result of the static analysis to tune a dynamic analysis to track the one or more objects identified during the static analysis, and 4) performing the dynamic analysis by, while the executable code is being executed, tracking the one or more objects identified during the static analysis to determine whether the executable code leaks sensitive data via the one or more objects. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A computer-implemented method for detecting malware may include 1) identifying an application configured to use a permission on a mobile computing platform, the permission enabling the application to access a feature of the mobile computing platform, 2) determining that the application is configured to use the permission while executing as a background application on the mobile computing platform, 3) determining that the use of the permission is suspect based on the application being configured to use the permission while executing as the background application, and 4) performing a remediation action in response to determining that the use of the permission is suspect. Various other methods, systems, and computer-readable media are also disclosed.