Abstract: A data processing method in a data processing device is provided. First to-be-processed data input into a neural network are obtained. Iterative training is performed on the neural network for a first preset number of times by using first target data in the first to-be-processed data, to obtain a seed model of the neural network. First newly added data generated after an elapse of time corresponding to the first time window is obtained, and the first newly added data and the first to-be-processed data are combined into second to-be-processed data. Iterative training is performed on the seed model for a second preset number of times by using second target data in the second to-be-processed data, to obtain a first incremental model of the neural network. A first preset area overlaps between the second time window and the first time window. The first incremental model online is published.

Abstract: A method and a device for selecting data content to be pushed to a terminal are disclosed. In some embodiments, the method includes: acquiring a user identifier, and acquiring a characteristic value, corresponding to the user identifier, in a preset user attribute type; acquiring data content, and searching for a decision tree object corresponding to the data content; locating a leaf node corresponding to the user identifier in the decision tree object based on the characteristic value, corresponding to the user identifier, in the preset user attribute type; and acquiring the number of clicks and the number of pushes stored in the located leaf node, generating a selection reference value based on the number of clicks and the number of pushes, and selecting, based on the selection reference value, data content to be pushed to a terminal corresponding to the user identifier.

Abstract: A data processing method in a data processing device is provided. First to-be-processed data input into a neural network are obtained. Iterative training is performed on the neural network for a first preset number of times by using first target data in the first to-be-processed data, to obtain a seed model of the neural network. First newly added data generated after an elapse of time corresponding to the first time window is obtained, and the first newly added data and the first to-be-processed data are combined into second to-be-processed data. Iterative training is performed on the seed model for a second preset number of times by using second target data in the second to-be-processed data, to obtain a first incremental model of the neural network. A first preset area overlaps between the second time window and the first time window. The first incremental model online is published.

Abstract: A method and a device for selecting data content to be pushed to a terminal are disclosed. In some embodiments, the method includes: acquiring a user identifier, and acquiring a characteristic value, corresponding to the user identifier, in a preset user attribute type; acquiring data content, and searching for a decision tree object corresponding to the data content; locating a leaf node corresponding to the user identifier in the decision tree object based on the characteristic value, corresponding to the user identifier, in the preset user attribute type; and acquiring the number of clicks and the number of pushes stored in the located leaf node, generating a selection reference value based on the number of clicks and the number of pushes, and selecting, based on the selection reference value, data content to be pushed to a terminal corresponding to the user identifier.

Abstract: The present disclosure provides a method and system for implementing an analytic function based on MapReduce. The method includes: a table scan operator acquiring a data row from a file block, and sending the data row to a reduce sink operator; upon receipt of the data row, the reduce sink operator determining a reduce key, a partition key, and a sort key of the analytic function, and sending the data row to an analysis operator by means of a MapReduce framework; and upon receipt of the data row, the analysis operator analyzing the data row to obtain an analytic result, and forwarding the data row and the analytic result to a subsequent operator. The present disclosure can implement an analytic function in a distributed data warehouse of the MapReduce framework, thereby solving a problem that the analytic function cannot be used in the distributed data warehouse based on the MapReduce framework to perform data analytical processing.

Abstract: The present disclosure is applied to the technical field of data processing, and provided are a capacity-based multi-task scheduling method, apparatus and system. The method comprises: a scheduling node receiving a request for acquiring a task sent by a task executing node, the request carrying with a current load value and an available memory space of the task executing node; and the scheduling node deciding whether the current load value is less than a threshold, and carrying out task scheduling for the task executing node according to the available memory space of the task executing node if the current load value is less than the threshold. The present disclosure can effectively avoid the problems of overload, load, in sufficient memory, etc. of the task execution node, and increase the resource utilization rate of the task execution node and the task scheduling and executing efficiency.