A first node group including at least three nodes is predefined in a distributed storage system. Each node of the first node group is configured to send data blocks stored in storage devices managed by the node to other nodes belonging to the first node group. A first node is configured to receive data blocks from two or more other nodes in the first node group. The first node is configured to create a redundant code using a combination of data blocks received from the two or more other nodes and store the created redundant code to a storage device different from storage devices holding the data blocks used to create the redundant code. Combinations of data blocks used to create at least two redundant codes in redundant codes created by the first node are different in combination of logical addresses of constituent data blocks.

Distributed storage system

The invention discloses a human skeleton behavior recognition method and device based on deep reinforcement learning. The method comprises: uniform sampling is carried out on each video segment in a training set to obtain a video with a fixed frame number, thereby training a graphic convolutional neural network; after parameter fixation of the graphic convolutional neural network, an extraction frame network is trained by using the graphic convolutional neural network to obtain a representative frame meeting a preset condition; the graphic convolutional neural network is updated by using the representative frame meeting the preset condition; a target video is obtained and uniform sampling is carried out on the target video, so that a frame obtained by sampling is sent to the extraction frame network to obtain a key frame; and the key frame is sent to the updated graphic convolutional neural network to obtain a final type of the behavior. Therefore, the discriminability of the selectedframe is enhanced; redundant information is removed; the recognition performance is improved; and the calculation amount at the test phase is reduced. Besides, with full utilization of the topologicalrelationship of the human skeletons, the performance of the behavior recognition is improved.

Human skeleton behavior recognition method and device based on deep reinforcement learning

The invention discloses a human body skeleton motion sequence behavior identification method The method includes acquiring human body skeleton node coordinates; serially connecting the nodes corresponding to the limbs of the human body skeleton to form the motion characteristic expressions of the limbs and the trunk; serially connecting the motion characteristic expressions of the limbs and the trunk to form the vector expression of the human body skeleton; arranging the vector expressions corresponding to the frames in the human body skeleton motion sequence according to time sequence to obtain a three dimensional matrix; performing the normalization of the values in the three-dimensional matrix and the normalization of the dimensions to obtain the image expression corresponding to the human body skeleton motion sequence; adaptively extracting the texture characteristic expression in the image expression by means of a convolutional neural network; and performing behavior class determination based on the texture characteristic expression and determining the behavior class of the human body skeleton motion sequence by voting The method can accurately identify people's behaviors based on the human body skeleton motion sequence without the need for complex data preprocessing

Human body skeleton motion sequence behavior identification method

The invention discloses an artificial intelligence operation method and device applied to games; the method comprises the following steps: receiving status information sent by a client end, wherein the status information is used for indicating present game status of the client end; using a built model to obtain motion indication information, wherein the motion indication information is used for indicating the next motion of the present game status, the model is obtained by training a plurality of motion combinations in the client end, and each motion combination comprises a plurality of motions executed in sequence; sending the motion indication information to the client end. The method and device can solve the technical problems that an artificial intelligence operation algorithm in the prior art is poor in game operation strategy programming capability.

Artificial intelligence operation method and device applied to game

The invention provides an image pixel classifying method based on the convolutional neural network The method mainly includes the steps of image inputting, self-help network processing, iterative processing, image thinning and estimation result obtaining The process includes estimating depth and camera motion by adopting the convolutional network and includes three stages that image pairs are sampled from a scene data set, and the image pairs with highlight conformity errors are discarded; the image pairs obtained after preprocessing are input into a self-help network to calculate optical flow, depth and camera motion; an iterative network is used for conducting iterative repetition multiple times to improve an existing estimation result; a high-resolution depth image and motion estimation are obtained after refining of a refining network The network is obviously superior to a traditional motion structure, and the result is more accurate and robuster; different from the network of estimating depth through the single image, the network learns the concept of learning, is capable of using motion parallax for processing a new type of scene and allows motion estimation

Double-frame depth and motion estimating method based on convolutional neural network

The present invention discloses a parallelized human body behavior identification method. According to the method, skeleton data of Kinect is used as input; a distributed behavior identification algorithm is implemented based on a Spark computing framework; and a complete parallel identifying process is formed. Acquisition of the skeleton data of a human body is based on scene depth acquisition capacity of Kinect and the data is preprocessed to ensure invariability of displacement and scale of characteristics; and a human body structural vector, joint included angle information and skeleton weight bias are respectively selected for static behavior characteristics and a dynamic behavior searching algorithm for a structural similarity is provided. On the identification algorithm, a neural network algorithm is parallelized on Spark; a quasi-newton method L-BFGS is adopted to optimize a network weight updating process; and the training speed is obviously increased. According to an identification platform, a Hadoop distributed file system HDFS is used as a behavior data storage layer; Spark is applied to a universal resource manager YARN; the parallel neural network algorithm is used as an upper application; and the integral system architecture has excellent extendibility.

Parallelized human body behavior identification method

The invention discloses a distributed file system architectural method supporting mass data access. The method is based on a distributed Hash table, and access nodes are obtained by conducting Hash mapping on a file path. By the adoption of the fully distributed type non-centralized architectural design, new nodes can join a cluster after several times of communications. A Kademlia algorithm is adopted for addressing among the nodes, and a routing table is divided and the distance between the nodes is obtained through exclusive-or operation to achieve skip of the most adjacent nodes. A leader is selected through a PaxosLease algorithm to handle the mapping operation on the nodes so as to solve the consensus problem. Block storage of fixed size is conducted on actual data of files, and redundant backup is conducted on the multiple nodes, so that the requirements for safety and distributed calculation are met. When an architectural system generated according to the architectural method processes mass files, the processing efficiency can be remarkably improved, and the good effect can be achieved in the environment with the low latency requirement.

Distributed file system architectural method supporting mass data access

The invention discloses a feature selection algorithm based on dynamic programming and K-means clustering. The feature selection algorithm includes that 1) data preprocessing is carried out to mainly solve the problems of data repetition and data attribute value missing in the feature data; 2) feature sub-sets are pre-selected by means of dynamic programming core idea and the within-class and between-class distance is taken as the performance function in the dynamic programming decision process; 3) an original K-means clustering algorithm is improved, the feature sub-sets generated at the dynamic programming stage are clustered by means of an improved K-means algorithm to reject redundant features, and the selected sub-sets are optimized. Based on the feature selection algorithm, the feature sub-sets being low in noise, high in correlation, and free of redundancy can be selected, the effective dimensionality reduction can be realized, the generalization ability and learning efficiency of the machine learning algorithm are improved, the running time of the algorithm is reduced, and finally a simple, efficient and easy-understand learning model is generated.

Bi Sheng

Papers

Parallelized human body behavior identification method

Distributed file system architectural method supporting mass data access

Feature selection algorithm based on dynamic programming and K-means clustering