Hewlett Packard Enterprise Development LP

Apollo Intelligent Connectivity (beijing) Technology Co., Ltd.

Beijing Jiaotong University

Hangzhou H3c Technologies Co., Ltd

Yumei Zhang

Hao Liu

Lihao Cheng

Rui Wang

Wei Zheng

Long Zhang

Jin Hu

Weiliang Chen

Gui He

Ci Liang

A semantic segmentation network model uncertainty quantification method based on evidence inference. The method comprises the steps of constructing an FCN network model, and training the FCN network model by using a training data set to obtain a trained FCN network model for semantic segmentation of image data; transplanting a D-S theory of evidence to the trained FCN network model to obtain a reconstructed FCN network model; and inputting to-be-segmented image data into the reconstructed FCN network model, outputting a classification result of a to-be-segmented image by the FCN network model, and calculating a classification result uncertainty value of each pixel point by using the D-S theory of evidence index.

Semantic segmentation network model uncertainty quantification method based on evidence inference

A data processing method includes: in the case where an operation state of an audio/video device in a target driving device is an out of operation state, generating an out of operation state notification message of the audio/video device; and sending the out of operation state notification message to a push client for stopping a data push between the push client and a push server using the out of operation state notification message.

Method and apparatus for processing data of a target driving device, electronic device and medium

Embodiments of the present disclosure provide a method and apparatus for recognizing speech. An embodiment of the method includes: in response to detecting a speech frame, converting the speech frame into a current text in real time; in response to there being no previously saved historical text, inputting the current text into a semantic parsing model to obtain a parsing result; in response to the parsing result including a valid intention slot, ending a speech endpoint detection to complete the recognition; and outputting an instruction corresponding to the valid intention slot.

Method and apparatus for recognizing speech

According to an example of the present disclosure, a service template providing a service may be found according to type of the service. A resource zone matching the service template may be found from a resource pool. A network resource matching a service unit in the service template may be found from the resource zone. A network parameter configured for the service unit may be sent to the network resource.

Network configuration auto-deployment

According to an example, a service request may be received. A service template providing a service may be found according to type of the service in the service request. A resource zone matching the service template may be found from a resource pool. A network resource may be found from the resource zone matching the service template according to a network model role zone of a service unit in the service template. The network resource and the service unit belong to the same network model role zone and the network resource may match the service unit.

Growing community of inventors

Beijing, China

Yumei Zhang