Abstract: An ultrasonic detection method and ultrasonic imaging system for a fetal heart. Since after three-dimensional volume data is obtained, at least one point within a fetal heart in the three-dimensional volume data is identified, the spatial position where a fetal heart cross-section is located in the three-dimensional volume data is identified according to the point, and the fetal heart cross-section is then extracted from the three-dimensional volume data according to the identified spatial position, the fetal heart cross-section can be quickly acquired from the three-dimensional volume data. The present invention is simple and easy to use, and is convenient for a doctor to make a diagnosis.

Abstract: The three-dimensional ultrasound imaging method comprise emitting an ultrasonic wave to a fetal head; receiving an ultrasonic echo to acquire an ultrasonic echo signal; acquiring three-dimensional volume data of the fetal head according to the ultrasonic echo signal; detecting a median sagittal section from the three-dimensional volume data according to features of the median sagittal section of the fetal head; determining a facing orientation of the fetal head in the median sagittal section; displaying the median sagittal section as an image suitable for observation according to the facing orientation of the fetal head.

Abstract: A microwave-based thermal coupling chemical looping gasification method and device. The device includes: a microwave radiation cavity; a loading recess of a microwave absorbing material; and a quartz pipe reaction cavity between the microwave radiation cavity and the loading recess of a microwave absorbing material. A microwave generator consisting of magnetrons is provided at a central portion of the microwave radiation cavity and below the loading recess. An infrared temperature-measuring probe group is arranged at two ends of the magnetrons. Two ends of the microwave radiation cavity are connected to a first and second three-way valves, in communication with the ambient atmosphere and a protection gas charging device. A protection gas cooling device and a protection gas circulating fan are sequentially connected in series on a pipeline between the valves.

Abstract: The present invention provides a method for controlling a speed of a polypeptide passing through a nanopore and use thereof in determining an amino acid sequence of a polypeptide. Specifically, the method comprises: conjugating a polynucleotide to the polypeptide to give a polynucleotide-polypeptide conjugate, and applying a voltage across the nanopore in the presence of a polynucleotide binding enzyme to move the conjugate through the nanopore. The polynucleotide binding enzyme controls the movement of the polynucleotide and thereby controls the movement of the conjugated polypeptide in the nanopore, thus controlling the speed of the polypeptide passing through the nanopore. While controlling the speed of the polypeptide, the present invention reads a nanopore current signal during the process of the polypeptide passing through the nanopore to give an electrical signal of the polypeptide.

Abstract: The present application discloses a method and an apparatus for training a speech spectrum generation model, as well as an electronic device, and relates to the technical field of speech synthesis and deep learning. A specific implementation is as follows: inputting a first text sequence into the speech spectrum generation model to generate an analog spectrum sequence corresponding to the first text sequence, and obtain a first loss value of the analog spectrum sequence according to a preset loss function; inputting the analog spectrum sequence corresponding to the first text sequence into an adversarial loss function model, which is a generative adversarial network model, to obtain a second loss value of the analog spectrum sequence; and training the speech spectrum generation model based on the first loss value and the second loss value.

Abstract: A method for training a speech recognition model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the fields of speech recognition technologies, deep learning technologies, or the like, are disclosed. The method for training a speech recognition model includes: obtaining a fusion probability of each of at least one candidate text corresponding to a speech based on an acoustic decoding model and a language model; selecting a preset number of one or more candidate texts based on the fusion probability of each of the at least one candidate text, and determining a predicted text based on the preset number of one or more candidate texts; and obtaining a loss function based on the predicted text and a standard text corresponding to the speech, and training the speech recognition model based on the loss function.

Abstract: A series of isoreticular metal-organic frameworks composed of metal nodes connected by rigid trigonal prismatic organic linkers and having a 6,12-coordinatled alb network topology are provided. Also provided are methods of synthesizing the metal-organic frameworks and methods of using the metal-organic frameworks to catalyze the hydrolysis of organic molecules, such as nerve agents, having hydrolysable bonds.

Abstract: The embodiment of the present disclosure discloses a method for display processing of 3D image data and method and system for 3D ultrasonic imaging. The method includes: obtaining 3D volume data of the head of a target body; detecting a transverse section at a anatomical position from the 3D volume data according to image characteristic of the head of the target body in a transverse section related to the anatomical position; and displaying the transverse section.

Abstract: A neural network machine translation method comprises: obtaining a to-be-translated source sentence; converting the source sentence into a vector sequence; determining candidate objects corresponding to the vector sequence according to a prefix tree which is pre-obtained and built based on a target sentence database, and determining a target sentence as a translation result according to the candidate objects.

Abstract: A method for training a data processing model includes: acquiring sample data; acquiring an initial data processing model, the initial data processing model including a plurality of forward nodes for outputting a plurality of intermediate results corresponding to the sample data; determining a plurality of time-dependent features corresponding to the plurality of forward nodes; acquiring a data processing model to be trained by processing the initial data processing model based on the plurality of time-dependent features; and training the data processing model to be trained using the sample data and the plurality of intermediate results.

Abstract: The present disclosure provides a method of recognizing speech offline, electronic device, and a storage medium, relating to a field of artificial intelligence such as speech recognition, natural language processing, and deep learning. The method may include: decoding speech data to be recognized into a syllable recognition result; transforming the syllable recognition result into a corresponding text as a speech recognition result of the speech data.

Abstract: A method for measuring parameters in an ultrasonic image, includes: obtaining an ultrasound image by receiving ultrasound echoes from a target tissue with an ultrasound probe and contains an area representing the target tissue; displaying the ultrasound image; obtaining multiple measurement items to be measured; determining multiple anatomical feature items whose positions are to be determined during a measurement of the multiple measurement items according to a relevance among the multiple measurement items, to obtain a feature set that comprises the multiple anatomical feature items and whose anatomical feature items are different from each other; determining positions of the anatomical feature items in the feature set in the ultrasound image; calculating values of the multiple measurement items according to the positions of the anatomical feature items in the feature set; and outputting the values of the multiple measurement items.

Abstract: A method for measuring parameters in an ultrasonic image, includes: obtaining a pelvic ultrasound image, wherein the pelvic ultrasound image is acquired by receiving ultrasound echoes from a pelvic floor tissue with an ultrasound probe and contains an area representing the pelvic floor tissue; displaying the pelvic ultrasound image; determining a position of an inferoposterior margin of symphysis pubis in the pelvic ultrasound image; determining a horizontal axis according to the determined position of the inferoposterior margin of symphysis pubis; determining a position of a bladder neck in the pelvic ultrasound image; and calculating a distance from the determined position of the bladder neck to the determined horizontal axis to obtain a value of a bladder neck-symphyseal distance.

Abstract: A method for measuring parameters in an ultrasonic image, includes: obtaining a pelvic ultrasound image, wherein the pelvic ultrasound image is acquired by receiving ultrasound echoes from a pelvic floor tissue with an ultrasound probe and contains an area representing the pelvic floor tissue; displaying the pelvic ultrasound image; determining a position of an inferoposterior margin of symphysis pubis in the pelvic ultrasound image; determining a central axis of symphysis pubis in the pelvic ultrasound image; determining an axis that passes through the determined position of the inferoposterior margin of symphysis pubis and is at an angle of 135 degree with respect to the determined central axis of symphysis pubis; determining a position of a bladder neck in the pelvic ultrasound image; and calculating a distance from the determined position of the bladder neck to the determined axis to obtain a value of a bladder neck-symphyseal distance.

Abstract: A method for display processing of 3D image data includes obtaining 3D volume data of the head of a target body; detecting a transverse section at an anatomical position from the 3D volume data according to image characteristic of the head of the target body in a transverse section related to the anatomical position; and displaying the transverse section.

Abstract: A microwave-based thermal coupling chemical looping gasification method and device. The device includes: a microwave radiation cavity; a loading recess of a microwave absorbing material; and a quartz pipe reaction cavity between the microwave radiation cavity and the loading recess of a microwave absorbing material. A microwave generator consisting of magnetrons is provided at a central portion of the microwave radiation cavity and below the loading recess. An infrared temperature-measuring probe group is arranged at two ends of the magnetrons. Two ends of the microwave radiation cavity are connected to a first and second three-way valves, in communication with the ambient atmosphere and a protection gas charging device. A protection gas cooling device and a protection gas circulating fan are sequentially connected in series on a pipeline between the valves.

Abstract: Proposed are a method and apparatus for speech recognition, and a storage medium. The specific solution includes: obtaining audio data to be recognized; decoding the audio data to obtain a first syllable of a to-be-converted word, in which the first syllable is a combination of at least one phoneme corresponding to the to-be-converted word; obtaining a sentence to which the to-be-converted word belongs and a converted word in the sentence, and obtaining a second syllable of the converted word; encoding the first syllable and the second syllable to generate first encoding information of the first syllable; and decoding the first encoding information to obtain a text corresponding to the to-be-converted word.

Abstract: A three-dimensional ultrasonic imaging method includes transmitting an ultrasonic wave to a fetal head; receiving an ultrasonic echo, obtaining an ultrasonic echo signal, and obtaining the three-dimensional volume data of the fetal head according to the ultrasonic echo signal; according to the characteristics of a median sagittal section of the fetal head, detecting the median sagittal section in the three-dimensional volume data; and displaying the median sagittal section.

Abstract: The present application discloses a method and an apparatus for training a speech spectrum generation model, as well as an electronic device, and relates to the technical field of speech synthesis and deep learning. A specific implementation is as follows: inputting a first text sequence into the speech spectrum generation model to generate an analog spectrum sequence corresponding to the first text sequence, and obtain a first loss value of the analog spectrum sequence according to a preset loss function; inputting the analog spectrum sequence corresponding to the first text sequence into an adversarial loss function model, which is a generative adversarial network model, to obtain a second loss value of the analog spectrum sequence; and training the speech spectrum generation model based on the first loss value and the second loss value.

Abstract: A three-dimensional ultrasonic imaging method includes transmitting an ultrasonic wave to a fetal head; receiving an ultrasonic echo, obtaining an ultrasonic echo signal, and obtaining the three-dimensional volume data of the fetal head according to the ultrasonic echo signal; according to the characteristics of a median sagittal section of the fetal head, detecting the median sagittal section in the three-dimensional volume data; and displaying the median sagittal section.