Abstract: The disclosure provides a mower. The mower includes a vehicle frame, a walking assembly, a working assembly, a seat and a battery pack. The walking assembly includes a first walking wheel assembly and a second walking wheel assembly connected with the vehicle frame. The first walking wheel assembly and/or the second walking wheel assembly includes a main walking wheel and a hub motor, the main walking wheel is connected with the hub motor, and the hub motor is arranged outside a side of the vehicle frame. The working assembly is connected with the vehicle frame. The seat is arranged on the vehicle frame. The battery pack is lowered and mounted on the vehicle frame and extends below the seat.

Abstract: A fish school detection method and a system thereof, an electronic device and a storage medium are provided, the method includes inputting a to-be-detected fish school image into a fish school detection model; the fish school detection model including a feature extraction layer, a feature fusion layer and a feature recognition layer; extracting feature information of the to-be-detected fish school image based on the feature extraction layer, and determining a fish school feature map and an attention feature map based on an attention mechanism; fusing the fish school feature map and the attention feature map based on the feature fusion layer to determine a target fusion feature map; and determining a target fish school detection result based on the feature recognition layer and the target fusion feature map. Interference from environmental factors on detection results is eliminated, so as to effectively improve accuracy of the fish detection.

Abstract: A computer-implemented method, system and computer program product for improving accuracy of a vision model. Images of an object with a first set of perspectives are received from a dataset used to train the vision model. A three-dimensional model of the object is then generated using the images of the object from the dataset. Using the three-dimensional model of the object, images of the object with a second set of perspectives are obtained. For example, the second set of perspectives may include different perspectives than the perspectives of the object from the images contained in the dataset. The dataset used to train the vision model may then be augmented with such images of the object with a second set of perspectives. In this manner, the dataset used to train the vision model includes a greater number of perspectives of the object thereby improving the accuracy of the vision model.

Abstract: Embodiments of the disclosure provide a circuit for online adaptive direct current offset correction, which includes: an analog adder circuit, a digital-to-analog conversion circuit, a direct current detection circuit, an adaptive update signal generating circuit, an output circuit, and a mode selection circuit. Embodiments of the present disclosure also provide a zero-IF receiver including a circuit for online adaptive DC offset correction.

Abstract: Disclosed herein are various embodiments, for a content display and clustering system. An example embodiment operates by receiving a request to display the plurality of content items. At each of multiple levels different pairs of content items are identified and a similarity score is computed for each pair. A subset of pairs for which their similarity score exceeds a similarity threshold for the respective level are identified and clustered. This process is repeated for one or more iterations at the same level, and then the process is repeated for each of the multiple levels. A final clustered subset is identified, and output for display, responsive to the request to display the plurality of content items.

Abstract: Disclosed is a method for adapting a deep learning framework to a hardware device based on a unified backend engine, which comprises the following steps: S1, adding the unified backend engine to the deep learning framework; S2, adding the unified backend engine to the hardware device; S3, converting a computational graph, wherein the computational graph compiled and generated by the deep learning framework is converted into an intermediate representation of the unified backend engine; S4, compiling the intermediate representation, wherein the unified backend engine compiles the intermediate representation on the hardware device to generate an executable object; S5, running the executable object, wherein the deep learning framework runs the executable object on the hardware device; S6: managing memory of the unified backend engine.

Abstract: A light emitting substrate is provided. The light emitting substrate includes a plurality of light emitting controlling units arranged in M rows and N columns, M is an integer equal to or greater than one, N is an integer equal to or greater than one, wherein a respective one of the plurality of light emitting controlling units includes a plurality of light emitting elements arranged in J rows and I columns, J being an integer equal to or greater than one, I being an integer equal to or greater than one, a i-th column of the I columns of light emitting elements includes J rows of light emitting elements, 1?i?I; (M×J) number of first voltage signal lines; and (M×J) number of groups of second voltage signal lines.

Abstract: Embodiments of this application disclose a data interface equalization adjustment method and apparatus, a device, and a storage medium, and relate to the field of data interface technologies. The method includes: A second device determines equalization parameter indication information of a first transmitter TX on a first data interface. The second device sends a first equalization training sequence block ETSB to a corresponding RX on the first data interface through a TX on a second data interface, where the first ETSB carries the equalization parameter indication information and equalization target indication information, and the equalization target indication information indicates that the first TX is an equalization target. The first device determines the equalization target to be the first TX based on the equalization target indication information, and adjusts an equalization parameter of the first TX to an equalization parameter indicated by the equalization parameter indication information.

Abstract: An ambulance-type mobile catheter room for cardiovascular interventional surgery enables interventional diagnosis and treatment devices for acute and severe cardiovascular diseases to be deployed quickly, is flexible and high in adaptability, and provides hardware devices for cardiovascular diagnosis and treatment interventional surgeons to timely diagnose and treat patients. The ambulance-type mobile catheter room for cardiovascular interventional surgery includes an ambulance. The ambulance is internally provided with an antibacterial internal environment, a robotic angiography machine system, a wireless medical Internet of Things system, a self-generating system and an auxiliary system.

Abstract: An ultrasound scanning control method applied to an ultrasound scanning device is provided. The ultrasound scanning device includes an execution mechanism. The execution mechanism includes a mechanical arm and a probe. The ultrasound scanning control method includes controlling the mechanical arm to drive the probe to move according to a set scanning trajectory for performing an ultrasound scanning detection on a part to be examined. Once an actual pressure value between the probe and the part to be examined in each control cycle is sensed using the force sensor, a pressure value between the probe and the part to be examined is controlled to be a constant value based on the actual pressure value.

Abstract: Described are a method, system, and computer program product for generating robust graph neural networks using universal adversarial training. The method includes receiving a graph neural network (GNN) model and a bipartite graph including an adjacency matrix, initializing model parameters of the GNN model, initializing perturbation parameters, and sampling a subgraph of a complementary graph based on the bipartite graph. The method further includes repeating until convergence of the model parameters: drawing a random variable from a uniform distribution; generating a universal perturbation matrix based on the subgraph, the random variable, and the perturbation parameters; determining Bayesian Personalized Ranking (BPR) loss by inputting the bipartite graph and the universal perturbation matrix to the GNN model; updating the perturbation parameters based on stochastic gradient ascent; and updating the model parameters based on stochastic gradient descent.

Abstract: A dual-motor drive assembly and a vehicle are disclosed. The dual-motor drive assembly comprises a first motor and a second motor arranged coaxially, a first gear transmission, a second gear transmission, and one or more idle gear pairs. The first gear transmission is driven by the first motor, and the second gear transmission is driven by the second motor. The idle gear pairs are respectively arranged in the first gear transmission and the second gear transmission and are configured to increase a distance between an output shaft of the first motor and an end shaft of the first gear transmission.

Abstract: A reshaping method for metal product includes acquiring position data information of a workpiece; converting the position data information into coordinate information, and fitting the coordinate information to obtain a surface contour curve of the workpiece; comparing the surface contour curve with a standard contour curve to generate a comparison result; obtaining reshaping information of the workpiece based on the comparison result; and controlling the reshaping system to reshape the workpiece. The disclosure acquires position data information of the workpiece by measuring, converts the position data information into coordinate information, fits the coordinate information to obtain the surface contour curve of the workpiece, compares the surface contour curve with the standard contour curve to obtain deformation situation, and reshapes the workpiece according to the reshaping information based on the deformation situation, which improves efficiency of workpiece reshaping and reducing labor costs.

Abstract: The present disclosure discloses a distributed model compilation system. A master node of the system determines the logic calculation graph of the model based on model information, divides the logic calculation graph into multiple logic calculation sub-graphs, generates a distributing message for each logic calculation sub-graph, and then transmits the distributing message to a slave node. Each of the slave nodes allocates a local computing resource to compile the logic calculation sub-graph based on the received distributing message, and transmits compilation completion information to the master node. The master node determines the completion of model compilation based on the compilation completion information returned by each slave node, and executes the target work based on the compiled model.

Abstract: The present disclosure provides a display assembly and a display device, the display assembly includes: a flexible display panel including a first display area, a second display area and a bending area formed between the first display area and the second display area, a metal resilient member fixedly attached to one side of the flexible display panel, a metal support located on a side, away from the flexible display panel, of the metal resilient member, a first conductive adhesive structure located at the edge of the bending area and connecting the first support part and the metal resilient member, and a second conductive adhesive structure located at the edge of the bending area and connecting the second support part with the metal resilient member, wherein the metal support is fixedly attached to the metal resilient member by an adhesive layer.

Abstract: Some embodiments include an integrated structure having vertically-stacked conductive levels alternating with dielectric levels. A layer over the conductive levels includes silicon, nitrogen, and one or more of carbon, oxygen, boron and phosphorus. In some embodiments the vertically-stacked conductive levels are wordline levels within a NAND memory array. Some embodiments include an integrated structure having vertically-stacked conductive levels alternating with dielectric levels. Vertically-stacked NAND memory cells are along the conductive levels within a memory array region. A staircase region is proximate the memory array region. The staircase region has electrical contacts in one-to-one correspondence with the conductive levels. A layer is over the memory array region and over the staircase region. The layer includes silicon, nitrogen, and one or more of carbon, oxygen, boron and phosphorus.

Abstract: A detection circuit, a driving circuit, and a display panel and a driving method therefor are provided. The detection circuit includes an acquisition circuit and a processing circuit. The acquisition circuit includes a test transistor and an energy storage element, where, for the test transistor, a control end is configured to be coupled to the data signal terminal, a first end is configured to be written with a detection signal, and a second end is coupled to the energy storage element; and a structural characteristic of the test transistor is identical to a structural characteristic of the driving transistor. The processing circuit is coupled to the second end of the test transistor, and configured to detect a voltage at the second end of the test transistor as a detection voltage and regulate the data signal according to the detection voltage.

Abstract: Disclosed herein are various embodiments, for a content display and clustering system. An example embodiment operates by receiving a request to display the plurality of content items. At each of multiple levels different pairs of content items are identified and a similarity score is computed for each pair. A subset of pairs for which their similarity score exceeds a similarity threshold for the respective level are identified and clustered. This process is repeated for one or more iterations at the same level, and then the process is repeated for each of the multiple levels. A final clustered subset is identified, and output for display, responsive to the request to display the plurality of content items.

Abstract: This disclosure relates to a method and an apparatus for processing a sample. The method includes acquiring an identification of each cassette in a basket and an identification of each sample contained in the cassette by reading an electronic tag of the cassette, wherein the identification of the cassette and the identification of the sample contained in the cassette are stored in an associated manner in the electronic tag of the cassette; acquiring information of each sample from a library information system based on the identification of the sample; and recording the information of each sample for use in subsequent processing of the sample.