Abstract: The present disclosure discloses an electroencephalogram (EEG) emotion recognition method based on a spiking convolutional neural network. In the present disclosure, after EEG emotion data is preprocessed, a differential entropy feature is extracted and a time window is intercepted, and then a spiking convolutional encoder is configured to encode the EEG emotion data; a spiking convolutional feature extractor extracts a spiking data feature; and a spiking fully connected classifier performs learning and classification. In the present disclosure, a spiking neural network combining a spiking convolutional layer and a spiking fully connected layer is trained directly to achieve an objective of EEG emotion classification.

Abstract: A display panel, including an active area and a peripheral area, which is located outside of the active area, wherein the active area comprises a base substrate, and a display structure layer and a touch structure layer sequentially arranged on the base substrate; the peripheral area includes an isolation dam, a first ground trace and a second ground trace arranged on the base substrate; and the first ground trace is located at a side of the isolation dam close to the active area, and the second ground trace is located at a side of the isolation dam away from the active area.

Abstract: Provided is an apparatus for fabricating a flexible display screen. The apparatus for the flexible display screen includes a roller mechanism and a jig, wherein the jig includes a bearing surface configured to bear a flexible display panel, the bearing surface being a curved surface; and the roller mechanism includes a roller, an axis of the roller being parallel to an element line of the bearing surface, and the roller being configured to roll on the bearing surface along a directrix of the bearing surface.

Abstract: A community question-answer (CQA) website answer sorting method and system combined with active learning. The sorting method comprises: step S1, performing question-answer data representation and modeling; and step S2, constructing a training set in combination with active learning, and predicting a sorting relationship of candidate question-answer pairs. Also provided is a community question-answer website answer sorting system combined with active learning. CQA website question-answer data is first represented and modeled, interference to answers sorting caused by long tail distribution of the community data is solved by means of a long tail factor, and an attention mechanism is introduced in a convolutional neural network to relieve a semantic gap problem among question-answer texts. Then, an unlabeled training set is also constructed, a sample is additionally selected from the unlabeled training set and labeled, and an answer sorting model is trained again after labeling results are merged.

Abstract: A compressor and a refrigeration apparatus are provided. The compressor has a compressor body, a reservoir and a connection pipe. The compressor body has a housing and a compression assembly disposed in the housing. A compression cavity is defined by the compression assembly and has an air suction port. A guide pipe is disposed at the housing. The reservoir has a suction pipe. The connection pipe is disposed in the guide pipe. A first end of the connection pipe is connected to the air suction port. The suction pipe is disposed in the connection pipe and connected to a second end of the connection pipe. The connection pipe can be a copper pipe. Each of the suction pipe and the guide pipe can be a steel pipe.

Abstract: A community question-answer (CQA) web site answer sorting method and system combined with active learning. The sorting method comprises: step S1, performing question-answer data representation and modeling; and step S2, constructing a training set in combination with active learning, and predicting a sorting relationship of candidate question-answer pairs. Also provided is a community question-answer website answer sorting system combined with active learning. CQA website question-answer data is first represented and modeled, interference to answers sorting caused by long tail distribution of the community data is solved by means of a long tail factor, and an attention mechanism is introduced in a convolutional neural network to relieve a semantic gap problem among question-answer texts. Then, an unlabeled training set is also constructed, a sample is additionally selected from the unlabeled training set and labeled, and an answer sorting model is trained again after labeling results are merged.

Abstract: Method and system for advertisement coordination through online bidding are provided. In one example, a bid request is received with respect to a plurality of advertisement opportunities. The plurality of advertisement opportunities is related to an online service. A plurality of advertisements is determined in accordance with the plurality of advertisement opportunities. An online bid associated with the plurality of advertisements is generated based on the bid request. The online bid is transmitted as a response to the bid request.

Abstract: Method and system for advertisement coordination through online bidding are provided. In one example, a first bid request and a second bid request are received with respect to a first advertisement opportunity and a second advertisement opportunity, respectively. A first advertisement and a second advertisement are determined for the first and second advertisement opportunities, respectively. A first online bid and a second online bid associated respectively with the first and second advertisements are generated. The first and second online bids are transmitted as a response to the first and second bid requests, respectively. A third bid request is received with respect to both the first and second advertisement opportunities. The first and second advertisement opportunities are related to an online service. A third online bid associated with both the first and second advertisements is generated. The third online bid is transmitted as a response to the third bid request.

Abstract: Method and system for advertisement coordination through online bidding are provided. In one example, a first bid request is received with respect to a first advertisement opportunity. A first advertisement is determined in accordance with the first advertisement opportunity. A first online bid associated with the first advertisement is generated based on the first bid request. The first online bid is transmitted as a response to the first bid request. A second bid request is received with respect to both the first advertisement opportunity and a second advertisement opportunity. The first and second advertisement opportunities are related to an online service. A second advertisement is determined in accordance with the second advertisement opportunity. A second online bid associated with both the first advertisement and the second advertisement is generated. The second online bid is transmitted as a response to the second bid request.

Abstract: Method and system for advertisement coordination through online bidding are provided. In one example, a bid request is received with respect to an advertisement opportunity related to an online service. The online service is to be presented with a first advertisement to a user. The first advertisement has been previously presented to the user. The user's behavior is obtained with respect to the first advertisement identified based on the bid request. A second advertisement is determined in accordance with the advertisement opportunity based on the user's behavior with respect to the first advertisement. An online bid associated with the second advertisement is generated based on the bid request. The online bid is transmitted as a response to the bid request.

Abstract: Method and system for advertisement coordination through online bidding are provided. In one example, a first bid request is received regarding a first advertisement opportunity. A first advertisement is determined for the first advertisement opportunity. A first online bid associated with the first advertisement is generated based on the first bid request. The first online bid is transmitted as a response to the first bid request. A second bid request is received regarding a second advertisement opportunity. The first and second advertisement opportunities are related to an online service. The user's behavior is obtained with respect to the first advertisement. A second advertisement is determined for the second advertisement opportunity based on the user's behavior with respect to the first advertisement. A second online bid associated with the second advertisement is generated. The second online bid is transmitted as a response to the second bid request.

Abstract: This disclosure relates to personalizing user interface (UI) elements of online content (a website, a mobile application, etc.) presented on a user device. The UI personalization technique may include, for a current online session, processing user-related data and context-related data to determine the UI element(s) and their attribute value(s) to be used for presentation of the online content during the current session. The user-related data include information regarding the user/user device, and the context data may include details about the online content (content type/topic, default UI attribute values, etc.) being accessed in the given online session. The user data and the context data may be processed based on modeling data related to users and their interaction with the UI of online content from different publishers and/or advertisers. Based on such processing, personalized UI element(s) and attribute values are determined and the online content is presented with the personalized UI.

Abstract: A numerical controlled colour light source system comprises a colour light-emitting tubes and a numerical control device for controlling said colour light tube. Therein, said colour light tube contains three tricolor light-emitting body which are arranged as equilateral triangle and controlled and drived by said numerical control device, and a light-blending cover shading said light-emitting body, Said light source system adapted to ad, decorating, scene and so on. Because a light tube can generate any color at any time by assembling a series of light-emitting tubes, it is possible to form a colour screen whose color and intensity can be to change optionally. The images and letters on said screen can generate different colour effects according to controlling.