Abstract: Disclosed are a shield tunnel segment structure and a construction method thereof. The shield tunnel segment structure includes segment blocks sequentially spliced in a circumferential direction. Each segment block forms a closed annular segment structure, and outer diameters of adjacent annular segment structures gradually increase in an axial direction. At least two adjacent segment blocks of the same annular segment structure form an annular inner groove, and at least one segment block of the adjacent annular segment structures is provided with an inner bump which matches the annular inner groove. At least two adjacent segment blocks of the same annular segment structure form an annular outer groove, and at least one segment block of the adjacent annular segment structures is provided with an outer bump which matches the annular outer groove. The annular outer grooves and the annular inner grooves are staggered in the circumferential direction.

Abstract: The present application discloses a method and apparatus for training a semantic representation model, a device and a computer storage medium, which relates to the field of natural language processing technologies in artificial intelligence.

Abstract: Embodiments of this application provide a data processing method and apparatus, a device, and a medium.

Abstract: A data processing method is provided. In the method, a first model that includes N network layers is obtained. The first model is trained with a first data set that includes first data and training label information of the first data, N being a positive integer. The first model is trained with a second data set. The second data set including second data and training label information of the second data, the second data being quantized. A first unquantized target network layer of the N network layers is quantized. Further, an updated first model that includes the quantized first target network layer is trained with the second data set to obtain a second model.

Abstract: The present disclosure relates to data processing method and apparatus. The method includes: acquiring local model parameters respectively corresponding to N local recognition models; acquiring M parameter fusion modes associated with a local model parameter set, and performing parameter fusion on the local model parameter set respectively according to each parameter fusion mode, so as to obtain M alternative global models; and acquiring evaluation indexes of the M alternative global models respectively in a multimedia verification data set, determining a target global model in the M alternative global models according to the evaluation indexes, and transmitting the target global model to N clients, the N clients updating parameters of a local recognition model associated with the target global model according to the target global model respectively, so as to obtain an object recognition model.

Abstract: This application provides a protein structure information prediction method and apparatus, a device, and a storage medium, and relates to the field of biological information technologies. The method includes: performing sequence alignment query in a first database according to an amino acid sequence of a protein to obtain multi-sequence aligned data; performing feature extraction on the multi-sequence aligned data to obtain an initial sequence feature; processing the initial sequence feature by using a sequence feature augmentation model to obtain an augmented sequence feature of the protein; and predicting structure information of the protein according to the augmented sequence feature. When the structure information of the protein is predicted based on artificial intelligence (AI), the foregoing solution can improve the prediction efficiency of protein structure information while ensuring the prediction accuracy of the protein structure information.

Abstract: This application provides a semantic segmentation network structure generation method performed by an electronic device, and a non-transitory computer-readable storage medium.

Abstract: An acceleration and compression method for a deep convolutional neural network based on quantization of a parameter provided by the present application comprises: quantizing the parameter of the deep convolutional neural network to obtain a plurality of subcode books and respective corresponding index values of the plurality of subcode books; acquiring an output feature map of the deep convolutional neural network according to the plurality of subcode books and respective corresponding index values of the plurality of subcode books. The present application may implement the acceleration and compression for a deep convolutional neural network.

Abstract: An acceleration and compression method for a deep convolutional neural network based on quantization of a parameter provided by the present application comprises: quantizing the parameter of the deep convolutional neural network to obtain a plurality of subcode books and respective corresponding index values of the plurality of subcode books; acquiring an output feature map of the deep convolutional neural network according to the plurality of subcode books and respective corresponding index values of the plurality of subcode books. The present application may implement the acceleration and compression for a deep convolutional neural network.

Abstract: An image matching method based on cascaded binary encoding includes using a hashing look-up with multiple hashing tables to coarsely filter candidate key-points in an image to produce a candidate subset of key-points, projecting the candidate subset into a high-dimensional Hamming space, and building a “Hamming distance-memory address” hashing table. An optimal matching key-point is discovered by querying the hashing table. The image matching method has high processing speed and matching quality, which can be used for efficient and accurate image matching.

Abstract: This invention involves an image matching method based on the cascaded binary encoding. The stated method includes: Procedure S1, using the hashing look-up with multiple hashing tables to coarsely filter candidate key-points in the image to produce a candidate subset of key-points; Procedure S2, projecting the candidate subset into a high-dimensional Hamming space; Procedure S3, a “Hamming distance-memory address” hashing table is built, and the optimal matching key-point is discovered by querying this hashing table. The image matching method proposed in this invention has high processing speed and matching quality, which can be used for efficient and accurate image matching.