Dell Products Inc.

Emc IP Holding Company LLC

Jiacheng Ni

Zhen Jia

Zijia Wang

Jinpeng Liu

Qiang Chen

Wenbin Yang

Min Gong

Bin He

Danqing Sha

Wenlei Wu

GuangZhou Zhou

Zhisong Liu

Chenxi Hu

Stefanie Menghuan Chen

Kay Ke Shan

Pengfei Wu

Victor Fong

Sanping Li

Jin Li

Tianxiang Chen

Xuwei Tang

Jin Ru Yan

Chun Xi Chen

Qicheng Qiu

Bo Wei

Spencer Sheng

Spenser Sheng

Ke Shan

Rong Sheng

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for acquiring an image. The method includes distilling an original image set through a capsule neural network model to generate a distilled image set, wherein the distilled image set includes a plurality of distilled images. The method further includes acquiring a first feature of a first image through the capsule neural network model. The method further includes acquiring a plurality of distilling features of the plurality of distilled images respectively through the capsule neural network model. The method further includes determining a plurality of similarities between the first feature and the plurality of distilling features respectively. The method further includes acquiring at least one original image matching the first image based on the plurality of similarities.

Method, electronic device, and computer program product for acquiring image

Embodiments of the present disclosure relate to a method, a device, and a computer program product for text to speech. The method includes encoding a reference waveform of a first speaker to obtain an encoded style feature separated from a second speaker. The method further includes transferring the encoded style feature to a spectrogram obtained by encoding an input text, to obtain a style transferred spectrogram. The method further includes converting the style transferred spectrogram into a time-domain speech waveform. According to the method for text to speech in the present disclosure, a comparative learning framework can also flexibly and effectively synthesize speech with a style of a target speaker, thus realizing lightweight speech style transfer, making it possible to learn high-quality and recognizable features of speech synthesis, and realizing effective speaker feature learning. In addition, the model will be beneficial to other downstream tasks.

Method, device, and computer program product for text to speech

Embodiments of the present disclosure provide an image processing method, an electronic device, and a computer program product. The method may include receiving a sub-image containing a target object and location information of the target object from a first computing node, the sub-image being intercepted from a monitoring image by the first computing node through target detection, the monitoring image being acquired by a roadside device and containing the target object, and the first computing node being located near the roadside device. The method may further include determining classification information of the target object based on the sub-image at a second computing node different from the first computing node. In addition, the method may further include generating safety hint information for the target object at the second computing node at least based on the classification information and the location information.

Image processing method, electronic device, and computer program product

The present disclosure relates to a method, a device, and a computer program product for model comparison. The method includes generating a detection image based on an original image. The method further includes obtaining a first classification result by sending the detection image to a target model, and obtaining a second classification result by sending the detection image to a to-be-detected model. In addition, the method further includes comparing the first classification result with the second classification result, and determining, in response to the first classification result being the same as the second classification result, that the target model is the same as the to-be-detected model. The method of the present disclosure can verify whether the to-be-detected model plagiarizes the target model without knowing any internal structure, parameters, weights, and other information of the to-be-detected model.

Method, device, and computer program product for model comparison

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.

Question answering method, electronic device, and program product

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for analyzing samples. The method includes acquiring a set of feature representations associated with a set of samples. The set of samples illustratively have classification information for indicating classifications of the set of samples. The method further includes adjusting the set of feature representations so that distances between feature representations of samples corresponding to the same classification are less than a first distance threshold. The method further includes training a classification model based on the adjusted set of feature representations and the classification information. The classification model is illustratively configured to receive an input sample and determine a classification of the input sample. In this manner, a relatively accurate classification model can be trained using a small number of samples, thereby reducing computation time and required computation capacity.

Method, electronic device, and computer program product for analyzing samples

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for monitoring. The method includes receiving, at a second node, a target image from a first node, where the target image is determined as being of a first category based on performing target detection on a road monitoring image obtained by the first node, and the second node is closer to a cloud end than the first node. The method further includes determining, at the second node, a second category of the target image, where the second category is a subcategory of the first category; and in response to the second category being a preset category, sending a warning corresponding to the second category to a terminal device associated with the road monitoring image. According to the method of the embodiments of the present disclosure, the accuracy of road monitoring warnings can be improved.

Method, electronic device, and computer program product for road monitoring

Embodiments of the present disclosure relate to a model optimization method, an electronic device, and a computer program product. This method includes: determining an initial learning rate combination for a deep learning model, wherein the initial learning rate combination includes a plurality of learning rates, each learning rate being determined for one of a plurality of layers of the deep learning model, and the plurality of learning rates including static learning rates and dynamic learning rates; and adjusting the initial learning rate combination to obtain a target learning rate combination, wherein an accuracy rate achieved when the target learning rate combination is used to train the deep learning model is higher than or equal to a first threshold accuracy rate. With the technical solution of the present disclosure, a deep learning model can be optimized by setting learning rates for each layer of the deep learning model.

Model optimization method, electronic device, and computer program product

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for distributed data processing. A method in one embodiment comprises obtaining an input for a data processing task based on a multi-head attention mechanism, the data processing task comprising a first subtask and a second subtask, the first subtask corresponding to a first attention head in the multi-head attention mechanism, and the second subtask corresponding to a second attention head in the multi-head attention mechanism. The method further comprises transmitting the input to a first dedicated computing resource and a second dedicated computing resource, the first dedicated computing resource corresponding to the first subtask, and the second dedicated computing resource corresponding to the second subtask, and performing the first subtask and the second subtask on the input for obtaining an output of the data processing task.

Method, electronic device, and computer program product for distributed data processing

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for session switching. The method includes: establishing a first session with a first terminal in response to a session request initiated by the first terminal. The method further includes: generating first response information to first request information from the first terminal. The method further includes: determining a first confidence level of the first response information; and determining, in response to the first confidence level being lower than a confidence level threshold, to switch the first session to a second session between the first terminal and a second terminal. The method for session switching according to embodiments of the present disclosure can provide a fast and satisfactory response to a request made by a user, thereby effectively satisfying the user requirements and significantly improving the user experience.

Method, electronic device, and computer program product for session switching

Embodiments disclosed herein include a method, an electronic device, and a computer program product for data processing. The method includes determining a first set of feature vectors representing samples in a data set. The method also includes generating a second set of feature vectors by performing a first transformation on the first set of feature vectors, wherein distribution skewness of the second set of feature vectors in a feature space is smaller than that of the first set of feature vectors. The method also includes generating a third set of feature vectors by performing a second transformation on the second set of feature vectors, wherein the third set of feature vectors and the second set of feature vectors have different distances between vectors. The method also includes selecting target samples as representatives from the samples based on a distribution of the third set of feature vectors in the feature space.

Method, electronic device, and computer program product for data processing

Embodiments of the present disclosure provide a method, a device, and a computer program product for updating a model. The method includes: determining a performance metric of a trained machine learning model at runtime; determining a homogeneity degree between a verification data set processed by the machine learning model at runtime and a training data set used to train the machine learning model; determining a type of a conceptual drift of the machine learning model based on the performance metric and the homogeneity degree; and performing an update of the machine learning model based on the type of the conceptual drift, where the update includes a partial update or a global update. In this way, a desired performance of the machine learning model can be maintained, while avoiding excessive time costs and computational resource costs caused by frequent global updates.

Method, device, and computer program product for updating model

Embodiments of the present disclosure relate to a method for generating a cross-modality encoder. The method includes: extracting a sample video feature of a sample video, a sample audio feature of a sample audio, and a sample text feature of a sample text, wherein contents of the sample video, the sample audio, and the sample text are associated with each other. The method further includes: generating, by the cross-modality encoder, a first cross-modality sample feature by combining the sample video feature, the sample audio feature, and the sample text feature; generating a scrambled cross-modality sample feature by performing a scrambling operation on the cross-modality feature; generating by the cross-modality encoder a second cross-modality sample feature by encoding the scrambled cross-modality sample feature; and tuning the cross-modality encoder based on the first cross-modality sample feature and the second cross-modality sample feature.

Method, electronic device, and computer program product for generating cross-modality encoder

Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for training a model. The method may include determining image features, audio features, and text features of a reference object based on reference image information, reference audio information, and reference text information associated with the reference object, respectively. The method may also include constructing a feature tensor from the image features, the audio features, and the text features. In addition, the method may further include decomposing the feature tensor into a first feature vector, a second feature vector, and a third feature vector corresponding to the image features, the audio features, and the text features, respectively, to determine a loss function value of the model. The method may also include updating parameters of the model based on the loss function value.

Method, electronic device, and computer program product for training model

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.

Growing community of inventors

Shanghai, China

Jiacheng Ni