Abstract: Provided is a model interpretation method, an image processing method, an electronic device and a storage medium, relating to the field of artificial intelligence, in particular to the field of deep learning. The model interpretation method includes: obtaining a token vector corresponding to an image feature input to a first model; obtaining a model prediction result output by the first model; and determining, according to a combination of an attention weight and a gradient, an association relation between the token vector input to the first model and the model prediction result output by the first model, where the association relation is used to characterize interpretability of the first model.

Abstract: Disclosed is a model training control method based on asynchronous federated learning, an electronic device and a storage medium, relating to data processing technical field, and especially to technical fields such as edge computing and machine learning. The method includes: sending a first parameter of a first global model to a plurality of edge devices; receiving a second parameter of a second global model returned by a first edge device of plurality of edge devices, the second global model being a global model obtained after the first edge device trains the first global model according to a local data set; and sending a third parameter of a third global model to a second edge device of the plurality of edge devices in a case of the third global model is obtained based on aggregation of at least one second global model.

Abstract: The present application provides a model training, image processing method, device, storage medium, and program product relating to deep learning technology, which are able to screen auxiliary image data with image data for learning a target task, and further fuse the target image data and the auxiliary image data, so as to train a built and to-be-trained model with the fusion-processed fused image data. This implementation can increase the amount of data for training the model, and the data for training the model is determined is based on the target image data, which is suitable for learning the target task. Therefore, the solution provided by the present application can train an accurate target model even if the amount of target image data is not sufficient.

Abstract: The present disclosure discloses a method and apparatus for displaying map points of interest, and an electronic device, relates to the field of artificial intelligence, and in particular to intelligent transportation. A specific implementation solution includes: acquiring features corresponding to multiple candidate points of interest; determining predicted popularity of the multiple candidate points of interest according to a mapping relation between each feature and each popularity and the features of the multiple candidate points of interest, and the mapping relation is determined based on the frequency of operations performed by a user for each sample point of interest in a historical time period; and displaying the candidate points of interest of which predicted popularity meets a preset popularity condition in a map. Therefore, the accuracy of the displayed points of interest may be enhanced.

Abstract: A method for model aggregation in federated learning (FL), a server, a device, and a storage medium are suggested, which relate to the field of artificial intelligence (AI) technologies such as machine learning. A specific implementation solution involves: acquiring a data not identically and independently distributed (Non-IID) degree value of each of a plurality of edge devices participating in FL; acquiring local models uploaded by the edge devices; and performing aggregation based on the data Non-IID degree values of the edge devices and the local models uploaded by the edge devices to obtain a global model.

Abstract: The present disclosure provides a region information processing method and apparatus, and relates to the field of artificial intelligence in computer technologies. The specific implementation is: acquiring a first distance between a first region and a second region, a first object set included in the first region, and a second object set included in the second region; determining spatial dependency information between the first region and the second region according to the first distance; determining object dependency information between the first region and the second region according to the first object set and the second object set; and determining a symbiosis between the first region and the second region according to the spatial dependency information and the object dependency information.

Abstract: A track restoration method, a track restoration device and a non-transitory computer-readable storage medium are provided, related to the field of intelligent transportation. The track restoration method includes: acquiring vehicle-passing data in a target area, where the vehicle-passing data is generated based on shooting data, and the shooting data is obtained by shooting a vehicle in the target area by a shooting device in the target area; restoring a driving track of the vehicle shot by the shooting device, based on the vehicle-passing data.

Abstract: Provided are an image occlusion method, a model training method, a device, and a storage medium, which relate to the technical field of artificial intelligence, in particular, to the field of computer vision technologies and deep learning, and may be applied to image recognition, model training and other scenarios. The specific implementation solution is as follows: generating a candidate occlusion region according to an occlusion parameter; according to the candidate occlusion region, occluding an image to be processed to obtain a candidate occlusion image; determining a target occlusion region from the candidate occlusion region according to visual security and data availability of the candidate occlusion image; and according to the target occlusion region, occluding the image to be processed to obtain a target occlusion image. In this manner, the image to be processed is desensitized while the accuracy of target recognition is ensured.

Abstract: A resource allocation method, including: determining a neural network model to be allocated resources, and determining a set of devices capable of providing resources for the neural network model; determining, based on the set of devices and the neural network model, first set of evaluation points including first number of evaluation points, each of which corresponds to one resource allocation scheme and resource use cost corresponding to the resource allocation scheme; updating and iterating first set of evaluation points to obtain second set of evaluation points including second number of evaluation points, each of which corresponds to one resource allocation scheme and resource use cost corresponding to the resource allocation scheme, and second number being greater than first number; and selecting a resource allocation scheme with minimum resource use cost from the second set of evaluation points as a resource allocation scheme for allocating resources to the neural network model.

Abstract: A technical solution relates to distributed machine learning, and relates to the field of artificial intelligence technologies, such as machine learning technologies, or the like. An implementation includes: acquiring, based on delay information, an optimal scheduling queue of a plurality of edge devices participating in training; and scheduling each edge device of the plurality of edge devices to train a machine learning model based on the optimal scheduling queue of the plurality of edge devices.

Abstract: A method for distributing network layers in a neural network model includes: acquiring a to-be-processed neural network model and a computing device set; generating a target number of distribution schemes according to network layers in the to-be-processed neural network model and computing devices in the computing device set, the distribution schemes including corresponding relationships between the network layers and the computing devices; according to device types of the computing devices, combining the network layers corresponding to the same device type in each distribution scheme into one stage, to obtain a combination result of each distribution scheme; obtaining an adaptive value of each distribution scheme according to the combination result of each distribution scheme; and determining a target distribution scheme from the distribution schemes according to respective adaptive value, and taking the target distribution scheme as a distribution result of the network layers in the to-be-processed neural n

Abstract: A method for generating an electronic report, an electronic device and a storage medium, related to the field of large data and the field of artificial intelligence, are disclosed. The method for generating an electronic report includes: establishing a template tree comprising a plurality of branches, wherein the branches comprise at least one intermediate node and bottom layer nodes comprising identification information; and calling, for respective branches, data groups corresponding to the identification information of the bottom layer nodes from a database, respectively, and displaying the called data groups at positions corresponding to the bottom layer nodes in an electronic report. Labor consumption may be reduced, and advantages of low cost, high efficiency, automation and routinization may be achieved.

Abstract: A method of training a model, a method of determining an asset valuation, a device, a storage medium, and a program product, which relate to a field of artificial intelligence, in particular to fields of deep learning and natural language understanding. A specific implementation can include: determining an event-level representation according to a first set of feature data; performing a multi-task learning for a first model according to the event-level representation, to obtain first price distribution data, and transmitting the first price distribution data to a central server; determining a first intra-region representation according to a second set of feature data; adding a noise signal to the first intra-region representation, and transmitting the noised intra-region representation to a client; and adjusting a parameter of the first model according to a noised parameter gradient in response to the noised parameter gradient being received from the central server.

Abstract: A method for generating a federated learning model is provided. The method includes obtaining images; obtaining sorting results of the images; and generating a trained federated learning model by training a federated learning model to be trained according to the images and the sorting results. The federated learning model to be trained is obtained after pruning a federated learning model to be pruned, and a pruning rate of a convolution layer in the federated learning model to be pruned is automatically adjusted according to a model accuracy during the pruning.

Abstract: A federated learning method and system, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of computer vision and deep learning technologies. The method includes: performing a plurality of rounds of training until a training end condition is met, to obtain a trained global model; and publishing the trained global model to a plurality of devices. Each of the plurality of rounds of training includes: transmitting a current global model to at least some devices in the plurality of devices; receiving trained parameters for the current global model from the at least some devices; performing an aggregation on the received parameters to obtain a current aggregation model; and adjusting the current aggregation model based on a globally shared dataset, and updating the adjusted aggregation model as a new current global model for a next round of training.

Abstract: A method for generating a federated learning model is provided. The method includes obtaining images; obtaining sorting results of the images; and generating a trained federated learning model by training a federated learning model to be trained according to the images and the sorting results. The federated learning model to be trained is obtained after pruning a federated learning model to be pruned, and a pruning rate of a convolution layer in the federated learning model to be pruned is automatically adjusted according to a model accuracy during the pruning.

Abstract: A method for processing synthetic features is provided, and includes: the synthetic features to be evaluated and original features corresponding to the synthetic features are obtained. A feature extraction is performed on the synthetic features to be evaluated based on a number S of pre-trained samples, to obtain meta features with S samples. S is a positive integer. The meta features are input into the pre-trained meta feature evaluation model for a binary classification prediction, to obtain a probability of binary classification. Quality screening is performed on the synthetic features to be evaluated according to the probability of the binary classification, to obtain second synthetic features to be evaluated. The second synthetic features are classified in a good category. The second synthetic features and original features are input into a first classifier for evaluation. classified in a poor category.

Abstract: A method for training a longitudinal federated learning model is provided, and is applied to a first participant device. The first participant device includes label data. The longitudinal federated learning model includes a first bottom layer sub-model, an interaction layer sub-model, a top layer sub-model based on a Lipschitz neural network and a second bottom layer sub-model in a second participant device. First bottom layer output data of the first participant device and second bottom layer output data sent by the second participant device are obtained. The first bottom layer output data and the second bottom layer output data are input into an interaction layer sub-model to obtain interaction layer output data. Top layer output data is obtained based on the interaction layer output data and the top layer sub-model. The longitudinal federated learning model is trained according to the top layer output data and the label data.

Abstract: A method for data processing is provided. The method includes obtaining first retrieving data associated with a first user and a first retrieving result selected by the first user from at least one retrieving result corresponding to the first retrieving data. The first retrieving data is labelled with an intention tag indicating a retrieving intention of the first user. The method further includes obtaining second retrieving data that is used by a second user to conduct retrieving and selecting the first retrieving result within a predetermined time period. The method further includes assigning the intention tag to the second retrieving data.

Abstract: A method of determining a regional land usage property, an electronic device and a storage medium, which relate to a field of an information technology, in particular to a field of a deep learning. The method includes: acquiring a human interaction information between a plurality of regions at a specified time; updating an initial representation vector of each of the regions according to the human interaction information, so as to obtain an embedding representation vector of each of the regions; selecting a target region from the regions, and selecting a plurality of static neighbor regions within a preset range around the target region; generating a feature map of the target region according to the embedding representation vector of the target region and the embedding representation vectors of the plurality of static neighbor regions; and predicting a land usage property of the target region by using the feature map.