Abstract: The present disclosure discloses an acoustic device and a support assembly. The support assembly may include a shell configured to provide a space for accommodating one or more components of the acoustic device. The support assembly may further include an interaction assembly configured to realize an interaction between a user and the acoustic device, wherein the interaction assembly include a first component and one or more second components, in response to receiving an operation of the user, the first component is configured to trigger at least one of the one or more second components to cause the acoustic device to perform a function corresponding to the at least one of the one or more second components.

Abstract: Disclosed is an earphone including: two speaker assemblies, a connection member, and a processing circuit. The connection member is configured to connect the two speaker assemblies, and the connection member provides, through a bending deformation, a clamping force for placing the two speaker assemblies on a head of a user, and the connection member includes a housing with an accommodation cavity. A bending sensor is disposed in the accommodating cavity, and the bending sensor is configured to generate a bending signal based on a bending state of the connection member. The processing circuit is configured to determine a placement state of the earphone based on the bending signal. The placement state includes one of a normal wearing state, an abnormal wearing state, or a free placement state.

Abstract: Embodiments of the present disclosure provide an acoustic output device, comprising: an acoustic output unit, a contact detection sensor, and a processor. The acoustic output unit includes a vibration unit and a casing, the casing at least including a contact region which is in contact with the face of a user; the contact detection sensor is located at the contact region; and the processor is configured to determine whether the user wears the acoustic output device based on an electrical signal generated when the contact detection sensor is in contact with the face of the user.

Abstract: The embodiments of the present disclosure provide a touch sensor device. The touch sensor device comprises a housing, configured to provide a touch region; and at least one sensor, configured to be fixed near the touch region. The at least one sensor includes: a signal transmitting unit, configured to generate a vibration signal under the action of an excitation signal; a signal receiving unit, configured to receive the vibration signal and generate an output signal; and a processor, configured to recognize a touch operation performed on the touch region according to the output signal.

Abstract: Disclosed is an earphone comprising two speaker assemblies and a connection member. The connection member is used to connect the two speaker assemblies. The connection member provides a clamping force for placing the two speaker assemblies at a user's head through a bending deformation. The connection member includes a housing with an accommodation cavity, a capacitance sensor is disposed in the accommodation cavity, and the capacitance sensor is configured to identify a bending state of the connection member. The capacitance sensor includes a shielding structure that has a constant potential and is used to reduce an effect of an external electric field on the capacitance sensor.

Abstract: Provide a sensing device comprising a cavity and an air pressure sensor disposed within the cavity. The cavity includes two elastic walls disposed opposite to each other and a rigid wall connecting the two elastic walls, wherein the rigid wall is in a form of a tubular structure, and the two elastic walls are configured to seal the tubular structure to form the cavity. A deformation of the two elastic walls changes air pressure within the cavity, and the air pressure sensor is configured to generate an electrical signal in response to the change of the air pressure.

Abstract: The embodiments of the present disclosure provide a sensor device. The sensor device comprises a sensitive element and a substrate. The substrate is configured to carry the sensitive element. The sensitive element includes a first conductive layer and a sensitive layer. The first conductive layer includes at least two conductive units. The at least two conductive units are arranged in a distributed manner. At least a portion of the sensitive layer is disposed between and in contact with the at least two conductive units. A resistance value of the sensitive element changes in response to bending of the sensor device.

Abstract: A strain sensor comprising a substrate is provided. The substrate is provided with a groove structure. An electrically conductive film is affixed to a surface of the substrate, and a crack is provided at a position of the electrically conductive film corresponding to the groove structure.

Abstract: The embodiments of the present disclosure provide a conductive structure and a flexible sensor having the same. The conductive structure comprises a substrate, including an accommodation groove; a solid conductor, at least partially accommodated in the accommodation groove, the solid conductor and the accommodation groove forming a first accommodation region; and a fluid conductor, filled in the first accommodation region and extending outside the accommodation groove, a projection of a contact region between the fluid conductor and the solid conductor along a depth direction of the accommodation groove and a projection of the solid conductor along the depth direction having an overlapping region. The flexible sensor comprises at least one sensing structure. Each sensing structure includes two electrode plates; and a dielectric flexible body. The flexible sensor further comprises a processor. Each of the two electrodes includes the conductive structure.

Abstract: An acoustic output device is provided. The acoustic output device includes a sound generation component, a support member, and a sensor. The sound generation component is configured to accommodate a sound generation unit that produces sound. The support member is configured to dispose the sound generation component near an ear without blocking an earhole. The sensor includes at least one ultrasonic transducer disposed inside the sound generation component. The sensor is configured to transmit a first ultrasonic signal to an outside of the sound generation component through the at least one ultrasonic transducer. The transducer is further configured to detect the second ultrasonic signal through the at least one ultrasonic transducer and determine a wearing state of the acoustic output device based on the detection. The second ultrasonic signal includes the first ultrasonic signal or a reflection signal of the first ultrasonic signal.

Abstract: The embodiments of the present disclosure disclose a system and method. The system may include at least one storage device configured to storage computer instruction; and at least one processor, in communication with the storage device. When executing the computer instructions, the at least one processor is configured to direct the system to perform operations including: obtaining a sensing signal of at least one sensing device; identifying a signal feature of the sensing signal; and determining, based on the signal feature, an operation of a target object associated with the at least one sensing device.

Abstract: The present disclosure provides a microphone including at least one acoustoelectric transducer and an acoustic structure. The acoustoelectric transducer is configured to convert a sound signal to an electrical signal. The acoustic structure includes a sound guiding tube and an acoustic cavity. The acoustic cavity is in acoustic communication with the acoustoelectric transducer, and is in acoustic communication with outside of the microphone through the sound guiding tube. The acoustic structure has a first resonance frequency, the acoustoelectric transducer has a second resonance frequency, and an absolute value of a difference between the first resonance frequency and the second resonance frequency is not less than 100 Hz. By disposing different acoustic structures, resonance peaks in different frequency ranges may be added to the microphone, which improves a sensitivity of the microphone near multiple resonance peaks, thereby improving a sensitivity of the microphone in the entire wide frequency band.

Abstract: A method for training a Neural Network (NN) model for imitating demonstrator's behavior. The method includes: obtaining demonstration data representing the demonstrator's behavior for performing a task, the demonstration data includes state data, action data and option data, wherein the state data correspond to a condition for performing the task, the option data correspond to subtasks of the task, and the action data correspond to the demonstrator's actions performed for the task; sampling learner data representing the NN model's behavior for performing the task based on a current learned policy; and updating the policy by using a generative adversarial imitation learning (GAIL) process based on the demonstration data and the learner data.

Abstract: A compound property prediction method is provided for an electronic device. The method includes obtaining chemical structure information of a target compound, the chemical structure information including an atom and a chemical bond, modeling a chemical structure graph according to the chemical structure information, the chemical structure graph including a first node corresponding to the atom and a first edge corresponding to the chemical bond, constructing an original node feature of the first node and an original edge feature of the first edge, performing a message propagation on the first edge according to the original node feature of the first node and the original edge feature of the first edge to obtain propagation state information of the first edge, and predicting properties of the target compound according to the propagation state information of the first edge.

Abstract: The present disclosure describes methods, apparatus, and storage medium for node classification and training a node classification model. The method includes obtaining a target node subset and a neighbor node subset corresponding to the target node subset from a sample node set labeled with a target node class, a neighbor node in the neighbor node subset being associated with a target node in the target node subset; extracting a feature subset of the target node subset based on the neighbor node subset by using a node classification model, the feature subset comprising a feature vector of the target node; performing class prediction for the target node subset according to the feature subset, to obtain a predicted class probability subset; and training the node classification model with a target model parameter according to the predicted class probability subset and a target node class subset of the target node subset.

Abstract: A compound property analysis method is provided. The method includes obtaining, according to a molecular structure of a compound, a feature vector of the compound, the feature vector including a node vector of each node and an edge vector of each edge, processing the feature vector by using a feature map extraction model branch to obtain a graph representation vector, and processing the graph representation vector by using a classification model branch to obtain a property of the compound. Thus, in the process of compound property analysis, the graph representation vector that can accurately represent a feature of the compound is obtained based on a graph data structure of the compound, and a classification property of the compound may be obtained based on the graph representation vector, thereby improving the accuracy of determining the classification property of the compound. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also provided.

Abstract: A compound property prediction method is provided for an electronic device. The method includes obtaining chemical structure information of a target compound, the chemical structure information including an atom and a chemical bond, modeling a chemical structure graph according to the chemical structure information, the chemical structure graph including a first node corresponding to the atom and a first edge corresponding to the chemical bond, constructing an original node feature of the first node and an original edge feature of the first edge, performing a message propagation on the first edge according to the original node feature of the first node and the original edge feature of the first edge to obtain propagation state information of the first edge, and predicting properties of the target compound according to the propagation state information of the first edge.

Abstract: The present disclosure describes methods, apparatus, and storage medium for node classification and training a node classification model. The method includes obtaining a target node subset and a neighbor node subset corresponding to the target node subset from a sample node set labeled with a target node class, a neighbor node in the neighbor node subset being associated with a target node in the target node subset; extracting a feature subset of the target node subset based on the neighbor node subset by using a node classification model, the feature subset comprising a feature vector of the target node; performing class prediction for the target node subset according to the feature subset, to obtain a predicted class probability subset; and training the node classification model with a target model parameter according to the predicted class probability subset and a target node class subset of the target node subset.