Abstract: The present application provides a self-supervised learning method performed by a computer device. The method includes: performing a data enhancement on an original medical image to obtain a first enhanced image and a second enhanced image, the first enhanced image and the second enhanced image being positive samples of each other; performing feature extractions on the first enhanced image and the second enhanced image by a feature extraction model to obtain a first image feature of the first enhanced image and a second image feature of the second enhanced image; determining a model loss of the feature extraction model based on the first image feature, the second image feature, and a negative sample image feature, the negative sample image feature being an image feature corresponding to other original medical images; and training the feature extraction model based on the model loss.

Abstract: A control device includes: an acquisition unit that acquires detection data from a sensor that detects a running state of a vehicle that is able to run by unmanned driving; a determination unit that determines whether or not the vehicle is located in a specific area in which the detection data is susceptible to an influence of disturbance; and a running control unit that is able to control the running of the vehicle using the detection data, and, when the determination unit determines that the vehicle is located in the specific area, lowers a degree of contribution of the detection data to running control of the vehicle compared to a case where the determination unit determines that the vehicle is located outside the specific area.

Abstract: A test device and a method for testing a photovoltaic module, for testing anti-stepping performance of the photovoltaic module. The test device includes first and second test members spaced apart along a first direction. The first and second test members are configured to abut against the photovoltaic module and apply a preset load to the photovoltaic module. The first test member is at a first position when the first test member abuts against the photovoltaic module, the second test member is at a second position when the second test member abuts against the photovoltaic module, and along a movement direction of the first and second test members in a horizontal plane, the first and second positions are alternately spaced apart, to simulate force on the photovoltaic module when an operator walks on the photovoltaic module.

Abstract: Provided are a non-contact live detection apparatus and a live detection method. The non-contact live detection apparatus includes a processing unit and a detection unit and an image collection unit which are both communicatively connected to the processing unit. The detection unit includes an electromagnetic wave sensor and at least three ultrasonic sensors. The image collection unit is configured to collect an insulation defect picture of an overhead power line detected by the detection unit. The processing unit is configured to obtain the spatial coordinates, two-dimensional pixel coordinates, electromagnetic wave intensity, and ultrasonic intensity of an insulation defect location according to a detection result of the detection unit and perform identification on the insulation defect picture.

Abstract: Provided are a non-contact live detection apparatus and a live detection method. The non-contact live detection apparatus includes a processing unit and a detection unit and an image collection unit which are both communicatively connected to the processing unit. The detection unit includes an electromagnetic wave sensor and at least three ultrasonic sensors. The image collection unit is configured to collect an insulation defect picture of an overhead power line detected by the detection unit. The processing unit is configured to obtain the spatial coordinates, two-dimensional pixel coordinates, electromagnetic wave intensity, and ultrasonic intensity of an insulation defect location according to a detection result of the detection unit and perform identification on the insulation defect picture.

Abstract: Provided is a method for searching for a whole slide image performed by a computer device, which relate to the field of artificial intelligence. The method includes: cropping a whole slide image into a plurality of tissue images; generating, through an image encoder, image feature vectors respectively corresponding to the plurality of tissue images; clustering the image feature vectors respectively corresponding to the plurality of tissue images, to determine at least one key image from the plurality of tissue images; querying, based on image feature vectors respectively corresponding to the at least one key image, a database to obtain at least one target image package corresponding to the at least one key image; and determining a whole slide image to which at least one candidate tissue image comprised in the at least one target image package respectively belongs as a final search result.

Abstract: An image detection method and apparatus are disclosed.

Abstract: The present invention discloses a method and an apparatus for rebuilding a relightable implicit human body model. A human body is represented as a deformable implicit neural representation, and a geometric shape, material attributes, and ambient lighting of the human body are decomposed to obtain a relightable and drivable implicit human body model. In addition, a volumetric lighting grid including a plurality of spherical Gaussian models is introduced to represent complex lighting with spatial variation, and visible probes capable of changing in position with change in human pose are introduced to record dynamic self-occlusion caused by human motion. With the method, drivable implicit models capable of being used for high-fidelity human body relighting may be generated in cases of sparse video input and even monocular input.

Abstract: The present disclosure provides an application log coding output method, a device, a system, and a computer readable storage medium. The method comprises: loading a conversion appender using an extension mechanism of a native logger, loading a log converter and a native appender for outputting a log message using the conversion appender, the log converter comprising one or more log sub-converters, and loading the log sub-converters specified by an initialization parameter using the log converter; receiving the log message sent by the native logger using the conversion appender, scheduling the log sub-converters specified by the initialization parameter to execute log coding, and sending the processed log to the native appender for secure output. By using the method, diversified log coding output can be achieved without retrofitting an application, and the method is more friendly to developers.

Abstract: Provided is a method for searching for a whole slide image performed by a computer device, which relate to the field of artificial intelligence. The method includes: cropping a whole slide image into a plurality of tissue images; generating, through an image encoder, image feature vectors respectively corresponding to the plurality of tissue images; clustering the image feature vectors respectively corresponding to the plurality of tissue images, to determine at least one key image from the plurality of tissue images; querying, based on image feature vectors respectively corresponding to the at least one key image, a database to obtain at least one target image package corresponding to the at least one key image; and determining a whole slide image to which at least one candidate tissue image comprised in the at least one target image package respectively belongs as a final search result.

Abstract: An internal and external coupling shear resistance locking control system and monitoring method of tunnel surrounding rocks, comprises an internal shear resistance and monitoring system of tunnel surrounding rocks, an external shear resistance and monitoring system of tunnel surrounding rocks, a relative shear displacement monitoring system of the tunnel walls and the roof and floor layers, and an anchor agent installation system; holes are expanded in the anchor cable drilling holes passing through coal-rock interface areas of the coal walls and roof and floor rock layers to form shear misalignment tolerance cavities; monitoring pressure values of measuring bags and liquid discharge in the shear misalignment tolerance cavities to determine shear deformations of the shear misalignment tolerance cavities, monitoring forces on anchor cables, compensating pull rods and shear resistance steel strips, and adjusting the shear resistance of the anchor cable and steel belt through the compensation rod structure.

Abstract: A method for perceiving a road environment, a vehicle control method, a training method, an electronic device, an autonomous driving vehicle, and a storage medium, which relate to fields of artificial intelligence technology, computer vision, deep learning and large model technologies, and may be applied to scenarios such as autonomous driving and unmanned driving. The method for perceiving a road environment includes: acquiring an associated-region lane attribute and an information to be detected, where the information to be detected is collected by an onboard sensor and represents a target region where a vehicle is traveling, the associated-region lane attribute corresponds to an associated region, and the associated region and the target region meet a predetermined similarity condition; and processing the associated-region lane attribute and the information to be detected by using an onboard perception model to obtain a road perception information of the target region.

Abstract: Disclosed is a multi-directional input apparatus, including: a casing formed with a space, an operating body, a pressing plate, a supporting seat, a spiral spring, a connecting seat, a connecting seat, a connecting seat, a circuit board, an elastic sheet, and a magnetic sensing component. An opening portion is provided at an upper part of the space; the operating body is provided with an operating portion protruding upward from the opening portion and a shaking portion provided inside the space, and the shaking portion is provided with a fixed port; the circuit board is provided in the space; the magnetic sensing component includes a magnet provided in the fixed port and a magnetic sensor electrically connected to the circuit board; and the operating body, the magnet and a sensing portion of the magnetic sensor are coaxially provided.

Abstract: An internal and external coupling shear resistance locking control system and monitoring method of tunnel surrounding rocks, comprises an internal shear resistance and monitoring system of tunnel surrounding rocks, an external shear resistance and monitoring system of tunnel surrounding rocks, a relative shear displacement monitoring system of the tunnel walls and the roof and floor layers, and an anchor agent installation system; holes are expanded in the anchor cable drilling holes passing through coal-rock interface areas of the coal walls and roof and floor rock layers to form shear misalignment tolerance cavities; monitoring pressure values of measuring bags and liquid discharge in the shear misalignment tolerance cavities to determine shear deformations of the shear misalignment tolerance cavities, monitoring forces on anchor cables, compensating pull rods and shear resistance steel strips, and adjusting the shear resistance of the anchor cable and steel belt through the compensation rod structure.

Abstract: An connecting structure includes a connecting board, a first component connecting to one side of the connecting board; and a second component connecting to the other side of the connecting board. A perpendicular projection of the first component on a preset plane overlaps a perpendicular projection of the second component on the preset plane, and the preset plane is parallel to a plane on which one side of the connecting board is located. A padding element is disposed between the first component and the connecting board. The structure can reduce occupation of transverse space inside the electronic device and help make a profile of the electronic device smaller.

Abstract: The application provides a data encryption and decryption method, device, storage medium, and encrypted file, and relates to the technical field of data processing. The method for data encryption includes: obtaining a first key, and performing an obfuscation operation on the first key and data to be encrypted to obtain obfuscation operation result data; obtaining a second key, and obtaining a first signature of the obfuscation operation result data according to the second key; obtaining a third key, and encrypting the first key, the data to be encrypted and the first signature using the third key to obtain a target ciphertext; obtaining a fourth key, and obtaining a second signature of the target ciphertext according to the fourth key; generating an encrypted file including the target ciphertext and the second signature. With the technical solutions of the application, security of data protection can be improved.

Abstract: Disclosed are a multidirectional input device, a game machine handle, and a game machine. The multidirectional input device includes a housing, an operation body, a pressing board, a resetting assembly, a circuit board, and a magnetic induction assembly. A space is formed in the housing, and an opening portion is formed at an upper portion of the space. The operation body includes an operation portion protruding upwards from the opening portion. The pressing board is shaped in a disc. The resetting assembly includes a spiral spring. One end of the spiral spring is configured to press a top of the pressing board onto a lower portion of the operation body, and another end of the spiral spring is configured to press a bottom of the space. The circuit board is provided in the space. The magnetic induction assembly includes a magnetic body and a magnetic sensor.

Abstract: A motor, a compressor and a refrigeration device are provided. The motor has a stator and a rotor. The stator has a stator core and a winding. The stator core is provided with multiple stator protruding teeth. The winding are wound on the teeth. The rotor has a rotor core and a permanent magnet. The permanent magnet is arranged on the rotor core. A ratio of the number of the stator protruding teeth to the number of phases of the winding is adaptable to adjust the strength of a demagnetization reverse magnetic field generated by energizing the winding.

Abstract: Provided are a method and a device for converting a current and a moment and a rehabilitation robot, which relate to the technical field of current moment conversion. The method is applied to a controller of a rehabilitation robot; and the method comprises: acquiring to-be-processed current data; searching for a conversion relationship corresponding to the to-be-processed current data from a pre-stored current conversion relationship table based on the to-be-processed current data, wherein the current conversion relationship table stores at least one set of corresponding relationships of current data and conversion relationship; and converting the to-be-processed current data into a corresponding target moment using the conversion relationships.

Abstract: A photovoltaic device and a method for mounting a photovoltaic device are provided. The photovoltaic device includes a color steel tile, a bonding layer, and a photovoltaic assembly. The color steel tile includes an angle relaxation portion. The bonding layer is arranged on a top wall of the angle relaxation portion. The photovoltaic assembly is located on one side of the color steel tile and connected to the color steel tile through the bonding layer. The bonding layer includes a first bonding portion and a second bonding portion arranged along a first direction. In the first direction, a ratio of a dimension of the first bonding portion to a dimension of the second bonding portion ranges from 0.1 to 0.5. The first bonding portion temporarily fix the photovoltaic assembly, while the second bonding portion mainly fix the photovoltaic assembly.