Abstract: A face image processing method includes: performing face detection on a to-be-processed image, to obtain at least one face region image included in the to-be-processed image and face key point information in the at least one face region image; and processing, for the at least one face region image, an image corresponding to a first region and/or an image corresponding to a second region in the face region image at least according to the face key point information in the face region image, wherein the image corresponding to the second region and the image corresponding to the first region are at least partially non-overlapping.

Abstract: A speech emotion detection system may obtain to-be-detected speech data. The system may generate speech frames based on framing processing and the to-be-detected speech data. The system may extract speech features corresponding to the speech frames to form a speech feature matrix corresponding to the to-be-detected speech data. The system may input the speech feature matrix to an emotion state probability detection model. The system may generate, based on the speech feature matrix and the emotion state probability detection model, an emotion state probability matrix corresponding to the to-be-detected speech data. The system may input the emotion state probability matrix and the speech feature matrix to an emotion state transition model. The system may generate an emotion state sequence based on the emotional state probability matrix, the speech feature matrix, and the emotional state transition model. The system may determine an emotion state based on the emotion state sequence.

Abstract: A method of planning a travel route includes: receiving a travel route planning request carrying travel parameters sent by a user terminal and determining travel spots of each travel spot type. If the travel parameters include the correlation data between travel spot types and travel time periods, finding the travel spots of the travel spot type corresponding to each travel spot type. If no correlation data is included, dividing a travel cycle specified in the travel parameters into at least one travel time period; computing a corresponding travel spot touring route for each travel time period based on predetermined mapping relationships between the travel spots of each travel spot type, the touring times and distances between different travel spots of the travel spot type; and returning the corresponding travel spot touring route to the user terminal. The present invention further discloses a planning server.

Abstract: A voice identity feature extractor training method includes extracting a voice feature vector of training voice, The method may include determining a corresponding I-vector according to the voice feature vector of the training voice. The method may include adjusting a weight of a neural network model by using the I-vector as a first target output of the neural network model, to obtain a first neural network model. The method may include obtaining a voice feature vector of target detecting voice and determining an output result of the first neural network model for the voice feature vector of the target detecting voice. The method may include determining an I-vector latent variable. The method may include estimating a posterior mean of the I-vector latent variable, and adjusting a weight of the first neural network model using the posterior mean as a second target output, to obtain a voice identity feature extractor.

Abstract: Aspects of the disclosure provide methods and mobile robots for providing information to a pedestrian. In some examples, a mobile robot includes processing circuitry. The processing circuitry obtains, via a sensor, sensing data that indicates an ambient environment of the mobile robot. The processing circuitry determines path indication information according to the sensing data. The path indication information includes a planned path of the mobile robot. The processing circuitry projects the path indication information on a target projection surface.

Abstract: The present invention provides an array substrate and a manufacturing method thereof, and a display device. The array substrate comprises a base substrate, a metal pattern layer, a data line pattern layer, and a scan line pattern layer. Wherein, the data line pattern layer or the scan line pattern layer and the metal pattern layer are arranged in different layers and are directly connected to the metal pattern layer. So that the data line pattern layer or the scan line pattern layer and the metal pattern layer are formed a parallel structure. Because the resistance of the parallel structure is smaller than the resistance of the data line pattern layer or the scan line pattern layer, the resistance of the parallel structure when is used as a data line or a scan line, is reduced, thereby the display effect is improved.

Abstract: Disclosed are a GOA circuit and a liquid crystal display device. The GOA circuit includes multistage GOA sub-circuits. Each stage of GOA sub-circuit includes a pull-up control unit, a pull-up unit, a transfer unit, a pull-down unit, a pull-down holding unit and a bootstrap unit. The bootstrap unit includes a first capacitor, a second capacitor, a first thin-film transistor and a second thin-film transistor. The first capacitor and the second capacitor are used as coupling capacitors for node Q so as to boost a voltage at node Q and enhance driving capability of the GOA circuit.

Abstract: A telephoto lens assembly comprises sequentially from an object side to an image side along an optical axis a first lens, a second lens, a stop, a third lens, a fourth lens, a fifth lens and a sixth lens. The first lens has negative refractive power and includes a convex surface facing the object side. The second lens has negative refractive power and includes a convex surface facing the image side. The third lens has positive refractive power. The fourth lens has refractive power. The fifth lens has refractive power. The sixth lens has positive refractive power. The fourth lens and the fifth lens are cemented.

Abstract: Disclosed are a gate driving circuit and a liquid crystal display device. The gate driving circuit comprises multi-stages of gate driving units. A gate driving unit at each stage includes a pull-down holding module which maintains an electric potential at an output terminal of a gate driving unit at a present stage at a negative electric potential. The influence of a right drift of a threshold voltage of an eighty-second transistor on the gate driving unit can be avoided, and further a speed of pulling down an electric potential at a first node can be increased.

Abstract: Disclosed are an array substrate and a liquid crystal display panel. The array substrate includes a plurality of gate lines and a plurality of data lines. The plurality of gate lines and the plurality of data lines are interleaved to form a plurality of pixel areas, and a pixel electrode is formed in each of the pixel areas. The pixel electrode is connected to a corresponding gate line and a corresponding data line via a thin film transistor. The array substrate further includes a common electrode, which is connected to a first pixel electrode and a second electrode via a thin film transistor. A signal in the first pixel electrode and a signal in the second pixel electrode have opposite polarities. The array substrate realizes automatic adjustment of a common electrode voltage, and corresponding regulators or machines are no longer needed. It is favorable to improvement of productivity and competitiveness of the array substrate and the liquid crystal display panel.

Abstract: The present invention provides an aortic arch intraoperative stent, wherein the aortic arch intraoperative stent comprising a main body (17) and one to three branches (5, 6, 7), The aortic arch intraoperative stent connects several circular waveform rings together via a cover membrane (25) to form the main body (17) and the branches (5, 6, 7), wherein each circular waveform ring comprises a circular elastic wire formed through head-to-tail connection. In addition, the present invention also provides a manufacturing method for the aortic arch intraoperative stent, comprising the following steps of: providing a cover membrane mandrel (40); making an inner membrane; assembling circular waveform rings; making an outer membrane; suturing a proximal fabric (12); and suturing a distal fabric (13).

Abstract: A pressure detection apparatus includes: a drive power supply, a differential circuit, a pressure calculation unit, and at least one pressure sensor. Each pressure sensor includes a first electrode plate, a second electrode plate, a third electrode plate, a first elastic dielectric layer, and a second elastic dielectric layer. One detection capacitor is formed between the first electrode plate and the second electrode plate, and one detection capacitor is formed between the first electrode plate and the third electrode plate. The pressure sensor is connected between the drive power supply and an input terminal of the differential circuit, and an output terminal of the differential circuit is connected to the pressure calculation unit.