Abstract: A method for accompaniment purity class evaluation and related devices are provided. Multiple first accompaniment data and a label corresponding to each of the multiple first accompaniment data are obtained, the label being used to indicate that corresponding first accompaniment data is pure instrumental accompaniment data or instrumental accompaniment data with background noise. An audio feature of each of the multiple first accompaniment data is extracted. Model training is performed according to the audio feature of each of the multiple first accompaniment data and the label corresponding to each of the multiple first accompaniment data, to obtain a neural network model for accompaniment purity class evaluation, a model parameter of the neural network model being determined according to an association relationship between the audio feature of each of the multiple first accompaniment data and the label corresponding to each of the multiple first accompaniment data.

Abstract: Systems and methods of generating an interface are disclosed. A request for an interface including a search query is received and a set of search results are generated via a search engine. A set of initial content campaigns are selected based on a category associated with the search query and are filtered based on a similarity score generated for the search query and each content campaign to generate a set of candidate content campaigns. The set of candidate content campaigns is filtered based on an exploration content score and an exploitation content score to generate a set of final content campaigns. An interface is generated including at least one content element selected from the set of final content campaigns and at least one content element selected from the set of search results. The interface is transmitted to the requesting system, which is configured to display the interface on a display.

Abstract: A method for audio sharing may include: establishing, by a first primary audio playing device of a first set of audio playing devices, a wireless connection with an audio sharing device, broadcasting, by the first primary audio playing device, a snoop enable message, the snoop enable message including information indicating a desired wireless communication channel, receiving, by the first primary audio playing device, a snoop consent event message sent on the desired wireless communication channel from a second primary audio playing device of a second set of audio playing devices, and snooping for and playing at least one audio packet sent on the desired wireless communication channel by an audio sharing device.

Abstract: A compact eyeprint imaging device is provided. The device includes a plano-convex lens, a right angle triangular prism, a micro lens array, an imaging detector and an external package. The plano-convex lens and the micro lens array are glued on an inclined face of the right angle triangular prism and two right angle faces of the right angle triangular prism are coated with reflecting films, so as to form an integrated combined optical unit, which is inserted into the external package together with the imaging detector. The device is wholly installed on a glasses frame. Light emitted by the eyeprint passes through the plano-convex lens to form parallel light beams, which are reflected twice through the two right angle faces of the right angle triangular prism and then focused through the micro lens array, so as to form a multi-aperture eyeprint image array on the imaging detector.

Abstract: A display substrate, a manufacturing method therefor and a display device are provided. The display substrate includes pixel light emitting regions and pixel spacer regions between adjacent pixel light emitting regions; in a plane perpendicular to the display substrate, the display substrate includes a base substrate and a light emitting structure layer on the base substrate, the light emitting structure layer at least includes an anode, a pixel definition layer and at least one photo spacer, a pixel opening is provided in the pixel definition layer in each pixel light emitting region, the pixel opening exposes the anode, a spacer opening is provided in the pixel definition layer in the pixel spacer region, the photo spacer is provided in the spacer opening, and an orthographic projection of the photo spacer on the base substrate is within a range of an orthographic projection of the spacer opening on the base substrate.

Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for audio sharing. In some embodiments, a method of audio sharing method to be performed by a first user device includes advertising an audio sharing message including a predetermined set identification, based on an indication from a user to share an audio content. The method further includes receiving, from a second audio playing device, an audio sharing confirmation message indicating that the second audio playing device has switched from an original set identification to the predetermined set identification. The method further includes establishing a third short-range wireless connection with the second audio playing device. The method further includes sending an audio data packet of the audio content to the first audio playing device, using the first short-range wireless connection, and the second audio playing device, using the third short-range wireless connection.

Abstract: A method for controlling a set of wireless earphones, including: establishing a first Bluetooth (BT) connection between a first earphone of the set of wireless earphones and a source apparatus; based on the source apparatus supporting Ultra Wide Band (UWB) connections: establishing a first UWB connection between the first earphone and the source apparatus, and a second UWB connection between a second earphone of the set of wireless earphones and the source apparatus; and receiving, by the first earphone, audio data from the source apparatus using the first UWB connection, wherein the audio data is received from the source apparatus by the second earphone using the second UWB connection

Abstract: The application discloses an ANPC power module. at least one power module, wherein the power module comprises six switch assemblies, a DC end, a GND end and an SW end, the six switch assemblies comprise two outer switches, two inner switches and two clamping switches, wherein an additional capacitor lead-out terminal is arranged at an electrical connection of each of the two inner switches and the two switch bridge arms, the capacitor lead-out terminal is used for setting a high-frequency filter capacitor, and two ends of the high-frequency filter capacitor are electrically connected with the capacitor lead-out terminals corresponding to the two switch bridge arms respectively. The application can effectively improve the instantaneous dynamic voltage spike of the high-frequency switching action, improve the oscillation frequency, increase the working voltage range of the device, and prevent the EMI noise from interference the devices outside of the ANPC power module.

Abstract: The application discloses an anti-driving interference power module which comprises at least one half-bridge power module. The half-bridge power module comprises a first switch device, a second switch device, a DC positive terminal and a DC negative terminal. The DC positive terminal, the first switch device, the second switch device and the DC negative terminal form a filtering loop which is the same as the second driving loop of the second switch device. According to the application, through the coupling design of the detour direction of the circuit, the driving crosstalk generated by the gate is inhibited for the device which does not need to be turned on, and mistaken opening of driving is avoided; and for the device needing to be opened, the turn-on level driven by the gate is enhanced, so that the reliability of the power module is higher.

Abstract: This application provides a motor, a watercraft propeller, and a watercraft. The motor includes: a housing with a cavity filled with insulating liquid; a stator fixed inside the cavity, with an inner rotating cavity on its inner side; and a agitation structure, rotating inside the inner rotating cavity, at least partially immersed in the insulating liquid, and configured to agitate the insulating liquid in a centrifugal or rotational form to contact and cool the stator. The agitation structure agitate the insulating liquid to the inner peripheral surface of the stator, allowing the stator to obtain the insulating liquid from the inner peripheral surface, ensuring uniform contact and heat exchange between the stator and the insulating liquid.

Abstract: Provided is a sodium ion battery cathode material and a preparation method therefor and application thereof. A chemical formula of the sodium ion battery cathode material is NamNixFeyMnzO2, where 0.1?x?0.25, 0.5?y?0.8, 0.1?z?0.25, 0.8?m?1.1, 0.95?x/z?1.05, and x+y+z=1, m, x, y and z are molar percentages of corresponding elements, respectively, and each component in the chemical formula satisfies charge conservation and stoichiometry conservation.

Abstract: A biochemical sludge and physicochemical sludge separate sampling device for identifying attributes of sludge, includes a sludge extraction assembly, and a biochemical reaction tank and a physicochemical reaction tank which are respectively connected to the sludge extraction assembly through connection pipelines. The sludge extraction assembly includes an outer shell, a porous plate clamped to an inner bottom of the outer shell, and a sampling dish. A drain pipe is arranged at a lower end of the outer shell. The sampling dish is provided with a biochemical sludge cavity and a physicochemical sludge cavity. Filter cloth is arranged at inner bottoms of the biochemical sludge cavity and the physicochemical sludge cavity. Electric extrusion stems are arranged at an inner top of the outer shell; and the electric extrusion stems are provided with extrusion plug plates.

Abstract: Embodiments of the present disclosure relate to devices, methods, apparatus, and medium for recurrent spiking neural network based equalization and demapping. A first communication device is configured to: obtain at least one parameter for a recurrent spiking neural network at the first communication device, wherein the at least one parameter is generated based on channel condition information between the first communication device and a second communication device; configure the recurrent spiking neural network based on the at least one parameter; and perform equalization and demapping on a signal received from the second communication device based on the recurrent spiking neural network. In this way, embodiments of the present disclosure provide a method for recurrent spiking neural network based equalization and demapping, thereby implementing a solution of a low power consumption joint equalization and demapping.

Abstract: An accompaniment classification method and apparatus is provided. The method includes the following. A first type of audio features of a target accompaniment is obtained (S301, S401). Data normalization is performed on each kind of audio features in the first type of audio features of the target accompaniment to obtain a first feature-set of the target accompaniment and the first feature-set is input into a first classification model for processing (S302, S402). A first probability value output by the first classification model for the first feature-set is obtained (S303, S403). An accompaniment category of the target accompaniment is determined to be a first category of accompaniments when the first probability value is greater than a first classification threshold (S404). The accompaniment category of the target accompaniment is determined to be other categories of accompaniments when the first probability value is less than or equal to the first classification threshold.

Abstract: Provided is a method for classifying videos. The method comprises: acquiring a target audio and a corresponding target video comprising human body actions; determining, based on a human body action matching degree of each target frame in the target video relative to a corresponding reference frame in a reference video, a total human body action matching degree score of the target video relative to the reference video; determining, based on an audio matching degree of each target audio segment in the target audio relative to a corresponding reference audio segment in a reference audio of the reference video, a total audio matching degree score of the target audio relative to the reference audio; and determining, based on the total human body action matching degree score and the total audio matching degree, a comprehensive classification result.

Abstract: The present invention relates to a method of preparing an oxide high entropy ceramic fiber; the oxide high entropy ceramic fiber of the present invention comprises five elements among Zr, Hf, Ti, Ce, Y, La, Gd, Er, Sm; the salt or precursor corresponding to the selected element is used as a metal source, anhydrous ethanol or anhydrous methanol is used as a solvent, polyvinylpyrrolidone or polyethylene oxide is used as a spinning aid to configure a spinning solution, the precursor fibers are prepared by electrostatic spinning, and the precursor fibers are heat-treated in air to obtain the oxide high-entropy ceramic fibers; the oxide high entropy ceramic fiber prepared by the present invention has a uniform diameter and good flexibility.

Abstract: Systems and methods for estimating advertisement impressions needed for detecting sales lift are disclosed. In some embodiments, based on an impression estimation request received from a computing device, a disclosed system determines an item set including items proposed to be advertised with an advertising campaign, and a time period proposed for the advertising campaign. Based on at least one model and historical transaction data associated with the item set, control sales data in the time period is computed for the item set without the advertising campaign. Based on a trained model and additional data associated with the item set, the system computes a number of impressions needed to detect a target sales lift compared to the control sales data in the time period for the item set with the advertising campaign. Based on the number of impressions, the system generates and transmits estimated impression data to the computing device.

Abstract: A metal product includes a metal substrate, at least one first hole, at least one second hole, and at least one third hole. The first hole is formed in a surface of the metal substrate. The second hole is formed in at least one of a portion of the surface of the metal substrate without the first hole and an inner surface defining the first hole. The third hole is formed in at least one of a portion of the surface of the metal substrate without the first hole and without the second hole, a portion of the inner surface defining the first hole without the second hole, and an inner surface defining the second hole. The first, second, and third holes enhance a bonding strength between the metal product and a material product. The disclosure also provides a metal composite and a method for manufacturing the metal product.

Abstract: A method and a device for audio repair and a readable storage medium are provided. The method includes the following. Multiple audio frames are sequentially inputted into a cache module, where the cache module is sequentially composed of multiple processing units, and a processing unit located at a center of the multiple processing units is a center processing unit (201). At least one audio frame contained in the center processing unit is assigned as a target frame (202). A noise point presented as a short-term high-energy pulse in the target frame is detected according to audio characteristics of the multiple audio frames in the cache module (203). The target frame is repaired to remove the noise point in the target frame (204).