Abstract: Embodiments of the present disclosure relates to processing a request message. The method includes receiving a request message from a user, determining a text feature representation of the request message by using a trained text feature representation model, and determining one or more entries of reference knowledge associated with the request message in a knowledge base by using a trained reference recommendation model and based on the text feature representation. In the method, the text feature representation model is trained by using a general corpus and a set of historical request messages, and the reference recommendation model is trained by using a request message subset in the set of historical request messages that has been associated with the entries in the knowledge base.

Abstract: Embodiments of the present disclosure relate to a method, a device, and a computer program product for communication of the Internet of Things. The method includes receiving data of a first protocol from an access point of a first network, the data of the first protocol coming from an Internet of Things device wirelessly connected to the access point; converting the data of the first protocol into data of a second protocol through a gateway, the gateway having a first protocol stack corresponding to the first protocol and a second protocol stack corresponding to the second protocol; and sending the data of the second protocol to a core network node in a second network. According to the embodiments of the present disclosure, different types of networks can be converged with low cost and high efficiency through adaptation of protocol stacks between the different types of networks.

Abstract: In an illustrative embodiment, a method is disclosed for generating an image from fMRI data and EEG data. The method includes extracting a first feature map of the fMRI data, the first feature map being multidimensional data having a temporal dimension related to a sample collection time of the fMRI data, and converting the first feature map based on the temporal dimension of the first feature map and a first attention model. The method further includes extracting a second feature map of the EEG data, the second feature map being multidimensional data having a spatial dimension related to an electrode for collecting the EEG data, and converting the second feature map based on the spatial dimension of the second feature map and a second attention model. The method further includes generating an image based on the converted first feature map and the converted second feature map.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for video reconstruction. The method for video reconstruction includes: receiving a video segment comprising a plurality of image frames. The method further includes: determining an audio segment corresponding to the video segment. The method further includes: acquiring a plurality of mask maps corresponding to the plurality of image frames, respectively. The method further includes: reconstructing the video segment based on the audio segment, the plurality of image frames, and the plurality of mask maps.

Abstract: Embodiments of the present disclosure relate to a caching method, device, and computer program product for an edge server. The method includes acquiring a historical distribution of a set of variables associated with a network environment of the edge server, and generating one or more time series of the set of variables based on the historical distribution. The method further includes determining a caching strategy associated with the edge server based on the one or more time series of the set of variables. With the solution of the present disclosure, in an edge computing scenario, unnecessary overhead caused by ineffective caching can be reduced while ensuring smooth user experience.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing point clouds. The method includes performing upsampling on a first feature of a first point cloud of a target object. The method further includes determining a reference feature of a second point cloud of a reference object. The method further includes determining a second feature based on the first feature subjected to upsampling and the reference feature. The method further includes generating a third point cloud of the target object based on the second feature and the second point cloud of the reference object, where the third point cloud has a larger number of points than the first point cloud. Through embodiments of the present disclosure, a point cloud of the target object can be made denser, with increased accuracy, thereby providing a more detailed description of the target object.

Abstract: Embodiments of the present disclosure provide a method and an electronic device for point cloud processing. The method includes: obtaining a first point cloud based on an input point cloud, a point number of the first point cloud being greater than a point number of the input point cloud; obtaining a first group of point clouds based on the first point cloud, the first group of point clouds including a plurality of point clouds; obtaining a second group of point clouds based on the input point cloud and the first group of point clouds, the second group of point clouds including a plurality of point clouds; and obtaining a target point cloud based on the first point cloud and the second group of point clouds, a point number of the target point cloud being greater than the point number of the input point cloud.

Abstract: In a method for detecting a model drift provided in an illustrative embodiment of the present disclosure, training data in a training data set is converted into an input vector represented by Shapley values. A plurality of dimensions of the input vector indicates a plurality of input features of a decision tree model. The decision tree model has been trained for performing at least one of image classification, text classification, or data mining. The method also includes: clustering, on the basis of the input vector, the training data set, so as to obtain a plurality of data clusters. The method also includes: in response to receiving a first input, converting the first input into a first input vector represented by Shapley values. The method also includes: detecting a drift degree of the decision tree model on the basis of the first input vector and the plurality of data clusters.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for task allocation. The method includes: obtaining an initial state of a group of dedicated processing sources; determining, in response to a request for receiving a group of tasks, a set of candidate allocations each indicating allocation of the group of tasks to the group of dedicated processing resources; determining, based on the initial state, an operating state of the group of dedicated processing resources when executing the group of tasks according to each candidate allocation in the set of candidate allocations; and selecting a target allocation from the set of candidate allocations based on the operating state to enable the group of tasks to be executed on the group of dedicated processing resources according to the target allocation.

Abstract: Embodiments of the present disclosure relate to a question answering method, an electronic device, and a computer program product. The method includes: determining an answer library associated with a question; determining a restricted Boltzmann machine associated with the answer library, wherein the restricted Boltzmann machine is configured to determine a set of questions that the answer library can answer and association relationships between questions in the set of questions and the answer library; and determining, using the restricted Boltzmann machine, annotation information associated with the question and targeted to the answer library. With the technical solution of the present disclosure, it is possible to determine, while determining an answer library associated with the question, annotation information that is targeted to the answer library, and to enable customer service personnel to have a more thorough understanding of the determined answer library and obtain targeted recommendation information.

Abstract: Embodiments disclosed herein relate to a method, a device, and a computer program product for training an image classification model. The method includes: determining a first classification result obtained by the image classification model on pixel points of a sample image in a first training iteration, wherein the first classification result indicates that each of the pixel points belongs to one of a plurality of object classes; determining a second classification result obtained by the image classification model on the pixel points of the sample image in a second training iteration; determining, based on the first classification result and the second classification result, a first set of recall rates and a second set of recall rates for the plurality of object classes; and adjusting, based on the first set of recall rates and the second set of recall rates, the image classification model to obtain a trained image classification model.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for information-centric networking. In the method, a memory layer in a machine learning model is used to obtain, on the basis of an environmental state obtained from information-centric networking at a future moment, future information associated with a memory layer corresponding to the future moment, and the machine learning model is trained using the future information. By means of the solution, a model trained using future information can be obtained. By use of the model, information-centric networking based on reinforcement learning achieves a more efficient cache mechanism.

Abstract: A method comprises generating a distilled dataset from an input dataset, wherein the input dataset comprises a plurality of first data samples, and the distilled dataset comprises a plurality of second data samples. In the method, an input data sample is received, and similarities are computed between the input data sample and respective ones of the plurality of second data samples. The method further comprises selecting one or more second data samples of the plurality of second data samples based, at least in part, on the computed similarities, and retrieving one or more first data samples of the plurality of first data samples from the input dataset based, at least in part, on the selected one or more second data samples. The generating is performed, at least in part, using one or more machine learning models.

Abstract: A method includes: acquiring a set of operations to be performed on multiple computing units in the computing system; determining, based on the set of operations, the state of the multiple computing units, and an allocation model, an allocation action for allocating the set of operations to the multiple computing units and a reward for the allocation action, wherein the allocation model describes an association relationship among a set of operations, the state of multiple computing units, the allocation action for allocating the set of operations to the multiple computing units, and the reward for the allocation action; receiving an adjustment for the reward in response to determining that a match degree between the reward for the allocation action and a performance index of the computing system after the allocation action is performed satisfies a predetermined condition; and generating, based on the adjustment, training data for updating the allocation model.

Abstract: An apparatus comprises a processing device configured to receive a service request associated with a given asset, to obtain a log file associated with the given asset, to split the log file into log segments, to generate sets of log pattern identifiers for the log segments, and to determine risk scores for the log segments utilizing a machine learning model that takes as input the sets of log pattern identifiers and provides as output information characterizing risk of the log segments. The processing device is also configured to identify critical areas of the log file based at least in part on the determined risk scores, a given critical area comprising a sequence of log segments having determined risk scores above a designated risk score threshold. The processing device is further configured to analyze the identified critical areas to determine remedial actions to be applied for resolving the service request.

Abstract: Methods, apparatus, and processor-readable storage media for automatically extracting information from conversation text data using machine learning techniques are provided herein. An example computer-implemented method includes generating one or more embeddings from conversation text data by processing at least a portion of the conversation text data using a first set of machine learning techniques; extracting information associated with one or more predefined categories from at least one set of input conversation text data by processing at least a portion of the at least one set of input conversation text data using a second set of machine learning techniques in connection with at least a portion of the one or more embeddings; and performing one or more automated actions based at least in part on the extracted information.

Abstract: Embodiments of the disclosure provide a method, electronic device and computer program product for data transmission. The method may include enabling a management node to obtain status data of a plurality of work nodes from the plurality of work nodes managed by the management node in response to determining that a user terminal is to move from a first position to a second position different from the first position. The status data are at least associated with utilization rates of the plurality of work nodes. The method may further include determining a plurality of weights of the plurality of work nodes at least based on the status data of the plurality of work nodes. Moreover, the method may include loading content data requested by the user terminal to at least one work node in the plurality of work nodes based on the plurality of weights.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for model training. The method for model training includes: receiving, at an edge device, a machine learning model and distilled samples from a cloud server, wherein the machine learning model is trained on the basis of initial samples at the cloud server, and the distilled samples are obtained by distillation of the initial samples. The method further includes: acquiring, at the edge device, a newly collected input sample, and retraining, by the edge device, the machine learning model by using the distilled samples and the input sample. In this way, by updating a model using a distilled sample set at an edge device, the efficiency of updating the model can be improved, and then the accuracy of the model can be improved.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for image segmentation. The method may be executed by a trained image segmentation model. The method includes: obtaining a to-be-processed image, wherein the to-be-processed image includes objects of a plurality of categories. The method further includes: selecting a to-be-discarded category in the to-be-processed image according to a recall rate of each of the plurality of categories obtained in advance. The method further includes: processing the to-be-processed image based on a plurality of remaining categories in the plurality of categories other than the to-be-discarded category to obtain a segmented image. Through the method, computing resources required for a segmentation processing task can be greatly reduced, a processing amount of image data can be reduced, and an image processing speed can be increased.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for evaluating samples. The method includes receiving, at an edge device, a classification model from a cloud server. The method further includes acquiring a sample distribution corresponding to each class in a plurality of classes of the classification model. The method further includes acquiring an input sample which is marked as a first class in the plurality of classes. The method further includes determining whether the input sample conforms to a first sample distribution corresponding to the first class. The method further includes identifying, in response to the input sample conforming to the first sample distribution, the input sample as a trusted sample. The trusted sample indicates that the input sample is correctly marked. By the method, a noise sample with a wrong label can be recognized, thus avoiding model degradation during update.