Abstract: An adaptive file storage method and apparatus is disclosed. The method includes determining a cold and hot attribute of a file, and performing coding storage processing or transcoding storage processing on the file according to the cold and hot attribute of the file. Therefore, a requirement of the cold and hot attribute of the file for storage overheads and restoration costs can be fully considered. In addition, the used coding technology has high reliability and a high coding speed. Therefore, comprehensive performance in multiple dimensions of storage overheads, restoration costs, reliability, and an coding speed can be improved.

Abstract: An image analysis method, including: obtaining influencing factors of t frames of images, where the influencing factors include self-owned features of h target subjects in each of the t frames of images and relational vector features between the h target subjects in each of the t frames of images, self-owned features of each target subject include a location feature, an attribute feature, and a posture feature, and t and h are natural numbers greater than 1; and obtaining a panoramic semantic description based on the influencing factors, where the panoramic semantic description includes a description of relationships between target subjects, relationships between actions of the target subjects and the target subjects, and relationships between the actions of the target subjects.

Abstract: A method for extracting structured data from an image is provided. The method includes: obtaining a first information set and a second information set in the image by using an image text extraction model, where the image includes at least one piece of structured data; obtaining at least one text subimage in the image based on at least one piece of first information included in the first information set; identifying text information in the at least one text subimage; and obtaining at least one piece of structured data in the image based on the text information in the at least one text subimage and at least one piece of second information included in the second information set. By using the image text extraction model and a text identification model, structured data extraction efficiency and accuracy are improved.

Abstract: An object detection model training method performed by a computing device, includes obtaining a system parameter including at least one of a receptive field of a backbone network, a size of a training image, a size of a to-be-detected object in the training image, a training computing capability, or a complexity of the to-be-detected object, determining a configuration parameter based on the system parameter, establishing a variable convolution network based on the configuration parameter and a feature map of the backbone network, recognizing the to-be-detected object based on a feature of the variable convolution network, and training the backbone network and the variable convolution network, where a convolution core used by any variable convolution layer may be offset in any direction in a process of performing convolution.

Abstract: In an object detection model training method, a classifier that has been trained in a first phase is duplicated to at least two copies, and in a training in a second phase, each classifier obtained through duplication is configured to detect to-be-detected objects with different sizes, and train an object detection model based on a detection result.

Abstract: A method and a device for training a model in a distributed system are disclosed, so as to reduce load of a master node (101) during model training. The method includes: receiving, by a parameter server (1022) in a first slave node (102), a training result sent by a parameter client (1021) in at least one slave node (102) in the distributed system, where the first slave node (102) is any slave node (102) in the distributed system, and a parameter client (1021) in each slave node (102) obtains a training result by executing a training task corresponding to a sub-model stored on a parameter server (1022) in the slave node (102); and updating, by the parameter server (1022) in the first slave node (102) based on the received training result, a sub-model stored on the parameter server in the first slave node.

Abstract: A method and an apparatus for reconstructing a cube in a multidimensional online analytical processing (MOLAP) system, where a cube is reconstructed based on a received reconstruction request and data stored in an old cube, and there is no need to acquire, from a database, data required for updating the cube, thereby ensuring data integrity when model reconstruction and data reconstruction are performed in the MOLAP system.

Abstract: Embodiments of the present invention disclose a data processing apparatus. The apparatus is configured to: after calculating a set of gradient information of each parameter by using a sample data subset, delete the sample data subset, read a next sample data subset, calculate another set of gradient information of each parameter by using the next sample data subset, and accumulate a plurality of sets of calculated gradient information of each parameter, to obtain an update gradient of each parameter.

Abstract: A method for training a neural network model are disclosed. Each training period includes K iterations, and for an ith iteration of one of N worker modules within each training period, each worker module performs in parallel the following steps: calculating a model parameter of an (i+1)th iteration based on a local gradient of the ith iteration and a model parameter of the ith iteration, and if i is less than K, calculating a local gradient of the (i+1)th iteration based on the model parameter of the (i+1)th iteration and sample data of the (i+1)th iteration; and pulling, by the worker module, a global gradient of an rth iteration from a server module and/or pushing, by the worker module, a local gradient of an fth iteration to the server module. In this way, time windows of a calculation process and a communication process overlap, thereby reducing time delay.

Abstract: A method and a device for training a model in a distributed system are disclosed, so as to reduce load of a master node (101) during model training. The method includes: receiving, by a parameter server (1022) in a first slave node (102), a training result sent by a parameter client (1021) in at least one slave node (102) in the distributed system, where the first slave node (102) is any slave node (102) in the distributed system, and a parameter client (1021) in each slave node (102) obtains a training result by executing a training task corresponding to a sub-model stored on a parameter server (1022) in the slave node (102); and updating, by the parameter server (1022) in the first slave node (102) based on the received training result, a sub-model stored on the parameter server in the first slave node.

Abstract: An adaptive file storage method and apparatus is disclosed. The method includes determining a cold and hot attribute of a file, and performing coding storage processing or transcoding storage processing on the file according to the cold and hot attribute of the file. Therefore, a requirement of the cold and hot attribute of the file for storage overheads and restoration costs can be fully considered. In addition, the used coding technology has high reliability and a high coding speed. Therefore, comprehensive performance in multiple dimensions of storage overheads, restoration costs, reliability, and an coding speed can be improved.

Abstract: A feature set determining method includes obtaining, according to a received feature set determining request, data used for feature learning. The feature set determining request includes a learning objective of the feature learning. The method includes performing type analysis on the data to divide the data into first-type data and second-type data. The method includes performing semi-supervised learning on the first-type data to extract multiple first-type features. The method includes performing adaptive learning on the second-type data to extract multiple second-type features. The method includes evaluating the first-type features and the second-type features to obtain an optimal feature set.

Abstract: An advertisement recommendation method and an advertisement recommendation server. The method includes: acquiring webpage visit information and advertisement click information; predicting, according to the webpage visit information and the advertisement click information, probabilities of clicking x advertisements when the ith user among m users visits the jth webpage; determining a novelty factor corresponding to each respective advertisement of the x advertisements; and determining, from the x advertisements according to the probabilities of clicking the x advertisements and the novelty factor corresponding to the respective advertisement, p advertisements to be recommended to the ith user.

Abstract: A method and an apparatus for reconstructing a cube in a multidimensional online analytical processing (MOLAP) system, where a cube is reconstructed based on a received reconstruction request and data stored in an old cube, and there is no need to acquire, from a database, data required for updating the cube, thereby ensuring data integrity when model reconstruction and data reconstruction are performed in the MOLAP system.