Abstract: Provided is a composite wallboard and a preparation method thereof. The composite wallboard is prepared from raw materials. The raw materials include in parts by mass: 700 to 800 parts of calcined gypsum powder, 0.1 to 1.0 part of a retarder, 0.3 to 0.5 part of a foaming agent, 50 to 70 parts of inorganic fiber, 600 to 700 parts of water, 200 to 400 parts of a binder, 20 to 30 parts of a hydrophobic agent, 3 to 5 parts of an acid agent, and 3 to 5 parts of a pH regulator.

Abstract: Provided are an active and passive integrated fireproof heat-insulating board and a preparation method thereof, including: n passive fireproof layers and n or n+1 active fireproof layers, the passive fireproof layers and the active fireproof layers are overlapped with each other into a whole. Each passive fireproof layer includes an inorganic fiber felt and an aerogel; the aerogel is obtained by curing an aerogel stock solution having adhesiveness, and the aerogel stock solution includes, in parts by mass, 1000 to 4000 parts of silica sol, 50 to 150 parts of soluble silicate, 10 to 50 parts of a phosphate adhesive, 5 to 20 parts of quicklime, 5 to 50 parts of titanium dioxide, 10 to 50 parts of calcium stearate, 5 to 50 parts of a hydrophobic modifier, 5 to 50 parts of an acid-base regulator, and 1000 to 4000 parts of a solvent.

Abstract: Provided are a speech recognition method, a speech recognition apparatus, a computer readable storage medium, and an electronic device. The method comprises: obtaining a sample speech signal, decoding the sample speech signal, obtaining a decoding result, and extracting a first feature from the decoding result; extracting a target speech segment from the sample speech signal, obtaining a log magnitude spectrum of the target speech segment, and determining a second feature according to the log magnitude spectrum; combining the first feature and the second feature to obtain a third feature; training an untrained classifier by using the third feature so as to obtain a trained classifier; and obtaining a third feature to be recognized of a speech signal to be recognized, so as to determine whether the third feature to be recognized comprises a prepositive word.

Abstract: A steam generator for hair-straightening combs is provided, including an evaporation assembly and a heating plate assembly. The evaporation assembly includes an evaporation water tank and a water injection pipe. The evaporation water tank is provided with an evaporation groove and an air-spraying groove connected to the evaporation groove. The heating plate assembly is connected to the side of the evaporation water tank away from the evaporation groove. A first water-storing sound-insulating cotton block is provided in the evaporation tank and is located between the water injection pipe and the bottom of the evaporation groove. The first water-storing sound-insulating cotton block is used to achieve full contact of water in the first water-storing sound-insulating cotton block during evaporation, such that steam can be generated more evenly, excessive steam generation can be prevented, and noise generated during water evaporation can be effectively reduced.

Abstract: In some examples, a computing device refines feature information of query text. The device repeatedly determines attention information based at least in part on feature information of the image and the feature information of the query text, and modifies the feature information of the query text based at least in part on the attention information. The device selects at least one of a predetermined plurality of outputs based at least in part on the refined feature information of the query text. In some examples, the device operates a convolutional computational model to determine feature information of the image. The device network computational models (NCMs) to determine feature information of the query and to determine attention information based at least in part on the feature information of the image and the feature information of the query. Examples include a microphone to detect audio corresponding to the query text.

Abstract: System and method for aspect-level sentiment classification. The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to: receive an aspect term-sentence pair; embed the aspect term-sentence pair; parse the sentence using multiple parsers to obtain dependency trees, and perform edge union to obtain a merged graph; combine the embedding and the merged graph to obtain a relation graph; perform a relation graph neural network on the relation graph; extract hidden representation of the aspect term from updated relation neural network; and classify the aspect term based on the extracted representation to obtain a predicted classification label of the aspect term. During training, the computer executable code is further configured to calculate a loss function based on the predicted label and the ground truth label, and adjust parameters of models.

Abstract: A custom tone and vocal synthesis method and apparatus, an electronic device, and a storage medium. The synthesis method comprises: training a first neural network by means of a speaker record sample to obtain a speaker recognition model, the output training result of the first neural network being a speaker vector sample (S102); training a second neural network by means of an unaccompanied vocal singing sample and the speaker vector sample to obtain an unaccompanied singing synthesis model (S104); inputting a speaker record to be synthesized into the speaker recognition model to obtain speaker information output by the intermediate hidden layer of the speaker recognition model (S106); and inputting unaccompanied singing music information to be synthesized and the speaker information into the unaccompanied singing synthesis model to obtain a synthesized custom tone and vocal (S108).

Abstract: A method includes constructing a graph including a plurality of nodes for a set of sequences, wherein each node corresponds to a sequence in the set of sequences; for each node, determining an initial feature matrix of the node, wherein the initial feature matrix of the node includes initial vectors of various elements in a sequence corresponding to the node; and, inputting the initial feature matrix of the node of the graph into a graph sequence network to enable the graph sequence network to update the feature matrix of the node using the feature matrix(es) of adjacent node(s) of the node; and obtaining a feature matrix output by the graph sequence network of each node to perform a sequence-based classification prediction using output feature matrixes, wherein the feature matrix output for each node includes updated vectors corresponding to the various elements in the sequence corresponding to the node.

Abstract: A zero-gravity seat collapsing mechanism may have a base and a seat frame, a rear end of the seat frame may be rotatably connected to the base, upper linkage components may be rotatably connected to a front end of the seat frame, and lower linkage components being rotatably connected to a front end of the base. The upper linkage component and the lower linkage component may be hinged to each other by a pin. A collapsing piece may be fixedly connected to a side of each upper linkage component. The collapsing piece may have an adapter hole, a collapse channel, and a weakened portion formed between the adapter hole and the collapse channel. The upper linkage component may have a strip-shaped avoidance hole. The mechanism provides the beneficial effect of a seat being able to instantaneously restore from a zero-gravity mode to a normal seated mode.

Abstract: A device is for surface strengthening of a metal plate based ultrasonic vibration is provided. The device includes an ultrasonic vibration tool holder and a cutting tool. The ultrasonic vibration tool holder is internally provided with an ultrasonic transducer and an ultrasonic booster; the ultrasonic transducer is configured to transmit vibration to the ultrasonic booster, the ultrasonic booster is configured to drive longitudinal torsion vibration of the cutting tool; an end of the ultrasonic booster facing towards the cutting tool is provided with an adjustment assembly configured for adjusting a longitudinal torsion angle and a rotation speed. Since the device includes the adjustment assembly, the longitudinal torsion angle and the rotation speed of the device can be adjusted according to different processing requirements, so as to perform ultrasonic vibration extrusion strengthening on surfaces of titanium alloy plates and improve surface integrity including microhardness and residual stress.

Abstract: A device is for surface strengthening of a metal plate based ultrasonic vibration. The device includes an ultrasonic vibration tool holder and a cutting tool. The ultrasonic vibration tool holder is internally provided with an ultrasonic transducer and an ultrasonic booster; the ultrasonic transducer is configured to transmit vibration to the ultrasonic booster, the ultrasonic booster is configured to drive longitudinal torsion vibration of the cutting tool; an end of the ultrasonic booster facing towards the cutting tool is provided with an adjustment assembly configured for adjusting a longitudinal torsion angle and a rotation speed. Since the device includes the adjustment assembly, the longitudinal torsion angle and the rotation speed of the device can be adjusted according to different processing requirements, so as to perform ultrasonic vibration extrusion strengthening on surfaces of titanium alloy plates and improve surface integrity including microhardness and residual stress.

Abstract: A method for end-to-end speech enhancement based on a neural network, including: obtaining a time-domain smoothing feature of an original speech signal by performing feature extraction on the original speech signal using a time-domain convolution kernel; and, obtaining an enhanced speech signal by performing combined feature extraction on the original speech signal and the time-domain smoothing feature of the original speech signal.

Abstract: A human-computer interaction method and apparatus. Said method may include: receiving information of at least one modality of a user (201); identifying, on the basis of the information of the at least one modality, intention information of the user and user emotional features corresponding to the intention information (202); determining, on the basis of the intention information, reply information to the user (203); selecting, on the basis of the user emotional features, character emotional features to be fed back to the user (204); and generating, on the basis of the character emotional features and the reply information, a broadcast video of an animated character corresponding to the character emotional features (205).

Abstract: Provided are a speech recognition method, a speech recognition apparatus, a computer readable storage medium, and an electronic device. The method comprises: obtaining a sample speech signal, decoding the sample speech signal, obtaining a decoding result, and extracting a first feature from the decoding result; extracting a target speech segment from the sample speech signal, obtaining a log magnitude spectrum of the target speech segment, and determining a second feature according to the log magnitude spectrum; combining the first feature and the second feature to obtain a third feature; training an untrained classifier by using the third feature so as to obtain a trained classifier; and obtaining a third feature to be recognized of a speech signal to be recognized, so as to determine whether the third feature to be recognized comprises a prepositive word.

Abstract: System and method for aspect-level sentiment classification. The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to: receive a sentence having a labeled aspect term and context; convert the sentence into a dependency tree graph; calculate an attention matrix of the dependency tree graph based on one-hop attention between any two nodes of the graph; calculate multi-head attention diffusion for any two nodes from the attention matrix; obtain updated embedding of the graph using the multi-head diffusion attention; classify the aspect term based on the updated embedding of the graph to obtain predicted classification of the aspect term; calculate loss function based on the predicted classification and the ground truth label of the aspect term; and adjust parameters of models in the computer executable code based on the loss function.