Abstract: An interactive method based on a large model, a training method, and an intelligent agent, which relate to fields of artificial intelligence, speech recognition, speech interaction, deep learning, large models, and application scenarios of knowledge search, autonomous driving, intelligent customer service, intelligent speech control, smart e-commerce, AI healthcare.

Abstract: Disclosed are a small peptide miPEP166i and use thereof in plant tissue culture, which relates to the technical field of plant genetic engineering. Through a comprehensive peptidomics workflow, the present disclosure systematically identifies miPEPs in three tissues of 84K poplar. By further translating the sequence within the primary transcript of identified miRNA166i, a root-specifically expressed small peptide, miPEP166i, is obtained. The amino acid sequence of the miPEP166i is as shown in SEQ ID NO.3. Upon verification, exogenous use of synthetically produced miPEP166i promotes the formation and elongation of adventitious roots in 84K poplar. The comprehensive annotation and functional analysis of miPEPs in 84K poplar presented in the present disclosure provide valuable genetic resources for their use in poplar and other forest trees.

Abstract: The present disclosure provides a power adjustment method of an upper electrode power supply of a semiconductor process apparatus. The method includes obtaining a processing load of an upper electrode power supply of a reference process chamber and a processing load of an upper electrode power supply of a current process chamber corresponding to semiconductor process step, when starting to perform a semiconductor process step, determining a power compensation coefficient for the current process chamber relative to the reference process chamber based on the processing load of the current process chamber and the processing load the reference process chamber, and controlling the upper electrode power supply to output compensation power. The compensation power is a product of the set power of the upper electrode power supply of the current process chamber corresponding to the semiconductor process step and the corresponding power compensation coefficient.

Abstract: The present disclosure provides a power adjustment method of an upper electrode power supply of a semiconductor process apparatus. The method includes obtaining a processing load of an upper electrode power supply of a reference process chamber and a processing load of an upper electrode power supply of a current process chamber corresponding to semiconductor process step, when starting to perform a semiconductor process step, determining a power compensation coefficient for the current process chamber relative to the reference process chamber based on the processing load of the current process chamber and the processing load the reference process chamber, and controlling the upper electrode power supply to output compensation power. The compensation power is a product of the set power of the upper electrode power supply of the current process chamber corresponding to the semiconductor process step and the corresponding power compensation coefficient.

Abstract: A method for compressing a neural network model includes acquiring a to-be-compressed neural network model. A first bit width, a second bit width and a target thinning rate corresponding to the to-be-compressed neural network model are determined. A target value is obtained according to the first bit width, the second bit width and the target thinning rate. Then the to-be-compressed neural network model is compressed using the target value, the first bit width and the second bit width to obtain a compression result of the to-be-compressed neural network model.

Abstract: An audio recognition method, a method of training an audio recognition model, and an electronic device are provided, which relate to fields of artificial intelligence, speech recognition, deep learning and natural language processing technologies. The audio recognition method includes: truncating an audio feature of target audio data to obtain at least one first audio sequence feature corresponding to a predetermined duration; obtaining, according to a peak information of the audio feature, a peak sub-information corresponding to the first audio sequence feature; performing at least one decoding operation on the first audio sequence feature to obtain a recognition result for the first audio sequence feature, a number of times the decoding operation is performed being identical to a number of peaks corresponding to the first audio sequence feature; obtaining target text data for the target audio data according to the recognition result for the at least one first audio sequence feature.

Abstract: A data processing method and device are provided. The method includes: performing a forward calculation of a neural network on global data to obtain intermediate data for a reverse calculation of the neural network; storing the intermediate data in a buffer unit; reading the intermediate data from the buffer unit; and performing the reverse calculation of the neural network on the intermediate data to obtain a result of the reverse calculation. According to embodiments, in the reverse calculation of the neural network, the number of accessing the global memory is reduced, thereby reducing the computational time cost and increasing the data processing speed.

Abstract: A technical solution for compressing a neural network model which relates to the field of artificial intelligence technologies, such as deep learning technologies, cloud service technologies, is disclosed. The method for compressing a neural network model includes: acquiring a to-be-compressed neural network model; determining a first bit width, a second bit width and a target thinning rate corresponding to the to-be-compressed neural network model; obtaining a target value according to the first bit width, the second bit width and the target thinning rate; and compressing the to-be-compressed neural network model using the target value, the first bit width and the second bit width to obtain a compression result of the to-be-compressed neural network model.

Abstract: The present disclosure discloses an interactive voice-control method and apparatus, a device and a medium. The method includes: obtaining a sound signal at a voice interaction device and recognized information that is recognized from the sound signal; determining an interaction confidence of the sound signal based at least on at least one of an acoustic feature representation of the sound signal and a semantic feature representation associated with the recognized information; determining a matching status between the recognized information and the sound signal; and providing the interaction confidence and the matching status for controlling a response of the voice interaction device to the sound signal.

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: A method for processing data includes: obtaining initial data; extracting data characteristics of the initial data; generating, based on the data characteristics, an initial memory consumption value required by a graphics processing unit (GPU) for processing the initial data; generating a recommendation processing parameter based on the initial memory consumption value; and obtaining target data by processing the initial data based on the recommendation processing parameter.

Abstract: The present disclosure provides a network operator processing method, apparatus, electronic device and storage medium and relates to the field of artificial intelligence such as deep learning and knowledge graph. The method may include: regarding any operator in the network, performing condition analysis on the operator respectively; regarding the operator as an operator supporting spatial reuse and found from lookup if it is determined according to an analysis result that the operator satisfies a spatial reuse condition. The solution of the present disclosure may be applied to save manpower and time costs, and improve the accuracy of the lookup result.

Abstract: The disclosure provides a method, an apparatus, a device, and a computer-readable storage medium for speech synthesis in parallel. The method includes: splitting a piece of text into a plurality of segments; based on the piece of text, obtaining a plurality of initial hidden states of the plurality of segments for a recurrent neural network. The method further includes: synthesizing the plurality of segments in parallel based on the plurality of initial hidden states and input features of the plurality of segments.

Abstract: The present disclosure provides a method and apparatus of fusing operators, an electronic device and a storage medium, which relates to fields of deep learning, artificial intelligence and knowledge graph. The method includes: determining operator groups to be fused, according to an operator graph to be processed, wherein each operator group of the operator groups includes at least two operators in the operator graph respectively; obtaining a fused operator corresponding to the each operator group respectively; and for the fused operator, replacing corresponding operators in the operator graph with the fused operator respectively, and coupling dependence edges of the corresponding operators to the any fused operator, wherein the corresponding operators include operators in the operator group corresponding to the fused operator.

Abstract: A symmetric method for obtaining branch-mean-square-current components induced by sources and loads at individual buses in AC power networks is invented. Two linear expressions of bus injection active and reactive powers in terms of translation voltages and voltage angles of all buses are established at first. Then a linear symmetric matrix-equation model for the steady state of the network is built. Manipulating this model by Moore-Penrose pseudoinverse produces a linear symmetric matrix expression of translation voltages and voltage angles of all buses in terms of bus injection powers. Expressing the branch mean-square current in terms of source's and load's powers by this matrix expression, a symmetric algebraic calculation formula for obtaining the branch-mean-square-current components is produced after manipulating by Shapley value theorem, by which the obtaining of branch-mean-square-current components are achieved.

Abstract: The present disclosure discloses an interactive voice-control method and apparatus, a device and a medium. The method includes: obtaining a sound signal at a voice interaction device and recognized information that is recognized from the sound signal; determining an interaction confidence of the sound signal based at least on at least one of an acoustic feature representation of the sound signal and a semantic feature representation associated with the recognized information; determining a matching status between the recognized information and the sound signal; and providing the interaction confidence and the matching status for controlling a response of the voice interaction device to the sound signal.

Abstract: The disclosure provides a method, an apparatus, a device, and a computer-readable storage medium for speech synthesis in parallel. The method includes: splitting a piece of text into a plurality of segments; based on the piece of text, obtaining a plurality of initial hidden states of the plurality of segments for a recurrent neural network. The method further includes: synthesizing the plurality of segments in parallel based on the plurality of initial hidden states and input features of the plurality of segments.

Abstract: A data processing method and device are provided. The method includes: performing a forward calculation of a neural network on global data to obtain intermediate data for a reverse calculation of the neural network; storing the intermediate data in a buffer unit; reading the intermediate data from the buffer unit; and performing the reverse calculation of the neural network on the intermediate data to obtain a result of the reverse calculation. According to embodiments, in the reverse calculation of the neural network, the number of accessing the global memory is reduced, thereby reducing the computational time cost and increasing the data processing speed.

Abstract: A method for preparing a biflavone-cobalt complex includes using the amentoflavone as the ligand and the cobalt ion as the central ion, the amentoflavone-cobalt complex is obtained by reaction, and the structure of the complex is characterized by infrared spectroscopy, UV-vis absorption spectroscopy and high resolution mass spectrometry. Meanwhile, the antitumor and antioxidant activities of the amentoflavone-cobalt complex are studied in the present invention. MTT method shows that the amentoflavone-cobalt complex has better antitumor activity, and the antitumor activity thereof is stronger than that of the amentoflavone. Pyrogallol auto-oxidation method, ABTS method and FRAP method show that the antioxidan activity of the amentoflavone-cobalt complex is stronger than that of the amentoflavone itself. The formation of the flavonoid-cobalt complex enhances the antitumor and anti-oxidation activities of the amentoflavone, and is expected to be used in the development of drugs.

Abstract: A method for preparing a biflavone-cobalt complex includes using the amentoflavone as the ligand and the cobalt ion as the central ion, the amentoflavone-cobalt complex is obtained by reaction, and the structure of the complex is characterized by infrared spectroscopy, UV-vis absorption spectroscopy and high resolution mass spectrometry. Meanwhile, the antitumor and antioxidant activities of the amentoflavone-coablt complex are studied in the present invention. MTT method shows that the amentoflavone-cobalt complex has better antitumor activity, and the antitumor activity thereof is stronger than that of the amentoflavone. Pyrogallol auto-oxidation method, ABTS method and FRAP method show that the antioxidan activity of the amentoflavone-cobalt complex is stronger than that of the amentoflavone itself. The formation of the flavonoid-cobalt complex enhances the antitumor and anti-oxidation activities of the amentoflavone, and is expected to be used in the development of drugs.