Abstract:
A classification model training method includes obtaining a positive training set and a first negative training set, where the positive training set includes samples of a positive sample set in a corpus, where the first negative training set includes samples of an unlabeled sample set in the corpus, training, using the positive training set and the first negative training set, to obtain a first classification model, determining, using the first classification model, a pseudo negative sample in the first negative training set, removing the pseudo negative sample from the first negative training set, updating the first negative training set to a second negative training set, and training, using the positive training set and the second negative training set, to obtain a target classification model.
Abstract:
A graph data query method and apparatus are disclosed, where the method includes: acquiring a partition number and a layer number of a query vertex; determining, based on the partition number and the layer number of the query vertex, a partition number and a layer number of a candidate vertex indicated by a query condition, and using the partition number and the layer number of the candidate vertex respectively as a candidate partition number and a candidate layer number; forming a candidate set using a vertex whose partition number and layer number satisfy any group of a candidate partition number and a candidate layer number; and performing graph data query in the candidate set according to the query condition.
Abstract:
A method, an apparatus, and a system for mutual communication between processes of a many-core processor are provided that relate to the field of many-core operating systems The method is executed by a target kernel, where the target kernel corresponds to a target processor core. The method includes acquiring a message header of a message from a quick message channel (QMC); executing a central processing unit (CPU) pre-fetching command according to the message header, so that a message body that is in the message stored in a shared memory and corresponds to the message header is loaded to a cache that corresponds to the target processor core; and switching to a target process, so that the target process acquires the message body from the cache. The embodiments of the present invention apply to a scenario of mutual communication between processes of a many-core processor.
Abstract:
A graph data query method and apparatus are disclosed, where the method includes: acquiring a partition number and a layer number of a query vertex; determining, based on the partition number and the layer number of the query vertex, a partition number and a layer number of a candidate vertex indicated by a query condition, and using the partition number and the layer number of the candidate vertex respectively as a candidate partition number and a candidate layer number; forming a candidate set using a vertex whose partition number and layer number satisfy any group of a candidate partition number and a candidate layer number; and performing graph data query in the candidate set according to the query condition.
Abstract:
A method, an apparatus, and a system for mutual communication between processes of a many-core processor are provided that relate to the field of many-core operating systems The method is executed by a target kernel, where the target kernel corresponds to a target processor core. The method includes acquiring a message header of a message from a quick message channel (QMC); executing a central processing unit (CPU) pre-fetching command according to the message header, so that a message body that is in the message stored in a shared memory and corresponds to the message header is loaded to a cache that corresponds to the target processor core; and switching to a target process, so that the target process acquires the message body from the cache. The embodiments of the present invention apply to a scenario of mutual communication between processes of a many-core processor.
Abstract:
The present invention discloses a platform, method, and device for managing an application, and belongs to the field of the Internet. The platform includes a mall and a store, where the mall includes: a management module configured to record and maintain information of an application store, application information, and user information; an application store creation module configured to create the application store according to store implementation logic, so that the application store presents an application according to the implementation logic; and a transaction management module configured to complete billing and charging of the application according to information maintained by the management module; and the store includes: a store interface management module configured to manage and present the application, so that the application is presented in a set presentation manner.
Abstract:
The disclosure provides gesture recognition methods and apparatuses, and relate to the field of artificial intelligence. One example gesture recognition method includes obtaining an image stream, and determining, based on a plurality of consecutive frames of hand images in the image stream, whether a user makes a preparatory action. When the user makes the preparatory action, continuing to obtain an image stream, and determining a gesture action of the user based on a plurality of consecutive frames of hand images in the continuously obtained image stream. Next, further responding to the gesture action to implement gesture interaction with the user. In this application, in order to reduce the erroneous recognition occurring in a gesture recognition process, the preparatory action is determined before gesture recognition is performed.
Abstract:
This application discloses an image segmentation method in the field of artificial intelligence. The method includes: obtaining an input image and a processing requirement; performing multi-layer feature extraction on the input image to obtain a plurality of feature maps; downsampling the plurality of feature maps to obtain a plurality of feature maps with a reference resolution, where the reference resolution is less than a resolution of the input image; fusing the plurality of feature maps with the reference resolution to obtain at least one feature map group; upsampling the feature map group by using a transformation matrix W, to obtain a target feature map group; and performing target processing on the target feature map group based on the processing requirement to obtain a target image.
Abstract:
An image processing method includes detecting human skeleton key points of a character in an image, and for the to-be-processed image, generating a cropping region based on the human skeleton key points and a preset rule, and using the to-be-processed image selected by using the cropping region as an output object. The human skeleton key points and the preset rule are set based on photographing experience.
Abstract:
In a method for selecting pictures from a sequence of pictures of an object in motion, a computerized user device determines, for each picture in the sequence of pictures, a value of a motion feature of the object. Based on analyzing the values of the motion feature of the pictures in the sequence, the device identifies a first subset of pictures from the pictures in the sequence. The device then selects, based on a second selection criterion, a second subset of pictures from the first subset of pictures. The pictures in the second subset are displayed to a user for further selection.