Abstract: A text error correction method and apparatus, and an electronic device and a medium. The text error correction method includes: performing image encoding on an acquired image to be analyzed, so as to obtain image features (S101); performing text encoding on acquired noisy text, so as to obtain text features (S102); performing feature comparison on the image features and the text features according to a set attention mechanism, so as to obtain an error correction signal (S103); and predicting an initial text label according to the error correction signal by using a trained decoder, so as to obtain error-corrected text information (S104).

Abstract: The embodiments of the present disclosure relate to the technical field of computers. Disclosed are a method and apparatus for information fusion, a method and apparatus for data communication, and an electronic device and a non-transitory computer-readable storage medium. The method for information fusion includes: in response to that a communication triggering condition is met, acquiring a local parameter of each of workers in a distributed training system, where the communication triggering condition is that all key nodes complete tasks of the current round of training; selecting N key nodes participating in the next round of training, and fusing local parameters of the N key nodes to obtain a global parameter; and sending the global parameter to each of the workers, and sending a training command to the key nodes to the key nodes execute tasks of next round of training based on the global parameter.

Abstract: An image generating method and apparatus, and a device and a medium are disclosed. The method comprises: acquiring weakly correlated image-text data pairs, and creating an image-text data set according to the weakly correlated image-text data pairs, wherein the weakly correlated image-text data pairs are image-text data pairs in which images and texts have weak correlations (S11); training, by using the image-text data set, an image generation model which is preconstructed on the basis of an adversarial network, so as to obtain a trained image generation model, wherein the image generation model includes a generator for generating an image, and a discriminator for identifying the authenticity of the image and calculating a corresponding loss value (S12); and after when text data to be processed has been acquired, generating, by using the trained image generation model, an image corresponding to the said text data (S13).

Abstract: The person intention reasoning method includes: performing object detection on a to-be-reasoned image to obtain an object detection result; determining that an image portion corresponding to a detection bounding box of each person in the to-be-reasoned image is a to-be-reasoned sub-image of the corresponding person respectively, and acquiring a joint feature and an occlusion probability of a joint of the corresponding person; performing prediction and analysis on the joint feature of corresponding joint based on the occlusion probability to obtain a corresponding prediction feature, and performing correction based on the joint feature and the prediction feature of the joint of the corresponding person to obtain a corresponding correction feature; and performing person intention reasoning by using the object detection result and the correction feature of the joint of the corresponding person to obtain a corresponding person intention reasoning result.

Abstract: Disclosed are a person Re-identification (Re-ID) method, apparatus, and device and a storage medium, and the method includes: acquiring a data set, where pieces of data in the data set are unlabeled person images; performing block processing on each piece of data in the data set, performing random ordering on each piece of blocked data to obtain out-of-order data corresponding to each piece of data, and generating negative sample data corresponding to each piece of data based on each piece of data and the corresponding out-of-order data; and performing unsupervised learning based on each piece of data in the data set, the out-of-order data of each piece of data, and the negative sample data of each piece of data to obtain a corresponding ID network, and performing person Re-ID based on the ID network.

Abstract: A difference description statement generation method includes: performing feature concatenation on an image encoding feature and a text encoding feature; inputting a concatenated encoding feature to a preset image-text alignment unit constructed based on a preset self-attention mechanism to obtain a concatenated alignment feature; processing, by using a preset noise monitoring unit constructed based on the preset self-attention mechanism and a preset cross-attention mechanism, the text encoding feature, and an image alignment feature and a text alignment feature that are obtained by splitting the concatenated alignment feature respectively, to extract a difference signal; and generating a difference description statement based on the difference signal by using a preset difference description generation algorithm.

Abstract: A glass composition can include from 60 mol % to 69 mol % SiO2, from 10 mol % to 18 mol % Al2O3, from 2.3 mol % to 6.9 mol % Li2O, from 2.1 mol % to 6.7 mol % Na2O, and from 1.1 mol % to 9 mol % alkaline earth metal oxides. The glass composition can comprise a liquidus viscosity greater than or equal to 150 kP. The glass composition can include from 0.25 mol % to 1 mol % K2O, from 0.5 mol % to 4 mol % P2O5, and/or 0.5 mol % to 3.6 mol % B2O3. The glass composition can form anorthoclase or a feldspar solid solution. The glass composition can include MgO+Li2O?(CaO+SrO+Na2O+K2O) is from ?0.5 to ?4. The glass composition can include volume electrical resistivity is greater than or equal to 2×1015 Ohm-centimeters. The glass composition may have a fracture toughness of greater than or equal 0.75 MPa?m.

Abstract: A lithium aluminosilicate glass-based article includes greater than or equal to 55.0 mol % and less than or equal to 75.0 mol % SiO2, greater than or equal to 1.0 mol % and less than or equal to 18.0 mol % Al2O3, and greater than or equal to 9.0 mol % and less than or equal to 25.0 mol % Li2O. The glass-based article has a thickness less than 0.74 mm, a fracture toughness of the mid-plane composition of the glass-base article is greater than or equal to 0.75 MP??{square root over (m)}, and a depth of compression that is greater than or equal to 0.14t, where t is the thickness of the glass-based article. The glass-based article is designed to have a single guided mode in the prism coupling spectrum at a wavelength between 360 nm and 405 nm for at least one of the transverse-magnetic or transverse-electric polarization.

Abstract: The present application relates to the technical field of artificial intelligence, and discloses a visual positioning method and apparatus, a device, and a medium. The method includes: performing feature splicing on an image encoding feature and a text encoding feature; performing feature fusion on spliced encoding features to obtain a first fused encoding feature; performing noise correction on the first fused encoding feature and the text encoding feature on the basis of a preset cross-attention mechanism to obtain a corrected fused feature and a corrected text encoding feature, and performing feature fusion on the spliced encoding feature and the corrected text encoding feature to obtain a second fused encoding feature; and correcting a preset frame feature using a target encoding feature on the basis of the corrected fused feature and the second fused encoding feature to predict a regional position coordinate of a target visual object.

Abstract: Disclosed in the present disclosure are an image-text mutual retrieval model training method and apparatus, an image-text mutual retrieval method, and a device, applied to the technical field of retrieval. The image-text mutual retrieval model training method includes: acquiring training data pairs; inputting the training data pair in an initial model, and extracting text coding features of text training data and image coding features of image training data by using a text coding module and an image coding module in the initial model, respectively; calculating a training loss based on the text coding features and the image coding features, and performing parameter adjustment on the initial model based on the training loss; and in response to the training loss meeting a convergence condition, determining the initial model after the parameter adjustment as an image-text mutual retrieval model.

Abstract: A data synchronization method and apparatus, and a device and a storage medium are disclosed.

Abstract: Provided in the present application are a disk processing method and system, and an electronic device. The method comprises: when disk alarm information is detected, marking a corresponding alarm disk as a faulty disk; detecting the state of a disk group corresponding to the faulty disk; if the state of the disk group is degraded, marking the faulty disk as an isolation disk, and generating alarm information; if the state of the disk group is healthy, determining whether there is a redundant disk group; if there is no redundant disk group, operating the faulty disk according to a first preset rule, and generating alarm information; and if there is a redundant disk group, detecting the state of the redundant disk group, if the state of the redundant disk group is healthy, marking the faulty disk as the isolation disk, and generating alarm information, otherwise, operating the faulty disk according to a second preset rule, and generating alarm information.

Abstract: Embodiments of the present application disclose a natural language processing method and apparatus, a device, and a readable storage medium. The method includes: obtaining a target sentence to be processed, and determining each first entity in the target sentence; for each first entity, in response to the first entity being present in a preset entity set, determining, in the preset entity set, a second entity in maximum correlation with the first entity, generating extended information based on the determined second entity, and adding the extended information after a location of the first entity in the target sentence, to obtain an updated target sentence, where the second entity is any entity in the preset entity set other than the first entity; and inputting the updated target sentence to a bidirectional encoder representations from transformer (BERT) model, such that the BERT model performs a natural language processing task.

Abstract: A difference description statement generation method includes: performing feature concatenation on an image encoding feature and a text encoding feature; inputting a concatenated encoding feature to a preset image-text alignment unit constructed based on a preset self-attention mechanism to obtain a concatenated alignment feature; processing, by using a preset noise monitoring unit constructed based on the preset self-attention mechanism and a preset cross-attention mechanism, the text encoding feature, and an image alignment feature and a text alignment feature that are obtained by splitting the concatenated alignment feature respectively, to extract a difference signal; and generating a difference description statement based on the difference signal by using a preset difference description generation algorithm.

Abstract: A method and apparatus for allocating a computing task of a neural network in heterogeneous resources, a computer device, and a storage medium. The method includes: acquiring task information of the computing task of the neural network and resource information of the heterogeneous resources; determining, according to the task information and the resource information, an allocation mode for allocating each subtask to the heterogeneous resources for execution and a task processing cost corresponding to each allocation mode; constructing a directed acyclic graph according to each allocation mode and each task processing cost; obtaining a value of a loss function corresponding to each allocation path according to the task processing cost corresponding to each subtask in an allocation path of the directed acyclic graph; and selecting a target allocation path according to the value of each loss function.

Abstract: An nGraph-based graphics processing unit (GPU) backend distributed training method and system, a computer-readable storage medium, and an electronic device. The method includes: receiving a training request, and obtaining corresponding training data; obtaining a Nvidia® Collective multi-GPU Communication Library (NCCL) file by means of a system path of the NCCL file linked to an nGraph framework; invoking an NCCL communication interface configuration according to the training request to obtain a training model, the NCCL communication interface is an NCCL file-based communication operation interface located at a GPU backend of the nGraph framework; and performing GPU backend training on the training data using the training model. The present application can satisfy an urgent need of a user for performing neural network distributed training on the basis of an nGraph GPU backend, thus further improving the performance of deep learning network training.

Abstract: Use of baicalin in preparation of a medicament for resisting pseudorabies virus (PRV) and diseases caused thereby is provided. The present disclosure relates to the technical field of medicine. It is found for the first time in the present disclosure that the baicalin has anti-PRV activity, has no obvious toxicity to cells in the using concentration range of 31.25-125 ?M, and shows an obvious inhibitory effect on PRV replication and proliferation in the concentration range of 62.5-125 ?M. It can be foreseen that the baicalin can be developed as a safe and effective anti-PRV medicament, and a novel anti-PRV medicament under existing application conditions of the baicalin, with an excellent application prospect.

Abstract: A load balancing method, apparatus and device for a parallel model training task, and a computer-readable storage medium, includes: acquiring data traffic and a theoretical computational amount of each network layer in a target model; determining a theoretical computing capability of each computing device, and obtaining an initial computational amount corresponding to each computing device according to the theoretical computing capability and the theoretical computational amount; performing a load balancing operation according to the initial computational amount by using multiple device critical layer position division rule, so as to obtain a plurality of initial balancing schemes; compiling statistics on time performance parameters corresponding to the initial balancing schemes, and determining an intermediate balancing scheme from the initial balancing schemes according to the time performance parameters; and adjusting the intermediate balancing scheme according to the data traffic, so as to obtain a final

Abstract: Disclosed are a person Re-identification (Re-ID) method, system, and device, and a computer-readable storage medium. The method includes: acquiring a sample set to be trained (S101); training a pre-constructed person Re-ID model by data re-sampling and cross-validation methods based on the sample set to be trained to obtain a trained person Re-ID model (S102); and performing person Re-ID based on the trained person Re-ID model, wherein persons in any two groups are of different classes after the sample set to be trained is grouped according to the cross-validation method (S103).

Abstract: An nGraph-based graphics processing unit (GPU) backend distributed training method and system, a computer-readable storage medium, and an electronic device. The method includes: receiving a training request, and obtaining corresponding training data; obtaining a Nvidia® Collective multi-GPU Communication Library (NCCL) file by means of a system path of the NCCL file linked to an nGraph framework; invoking an NCCL communication interface configuration according to the training request to obtain a training model, the NCCL communication interface is an NCCL file-based communication operation interface located at a GPU backend of the nGraph framework; and performing GPU backend training on the training data using the training model. The present application can satisfy an urgent need of a user for performing neural network distributed training on the basis of an nGraph GPU backend, thus further improving the performance of deep learning network training.