7013 results about "Equipment computers" patented technology

The present application provides an image generation method and apparatus based on artificial intelligence, an electronic device, a computer readable storage medium, and a computer program product. The method comprises: acquiring a content text and acquiring a style image having a target style; carrying out text encoding processing on the content text to obtain a content text code of the content text, and extracting a style code from the style image; and on the basis of a dual-path cross attention mechanism corresponding to the style code and the content text code, carrying out inverse diffusion processing on a noise image to obtain a target image, wherein the target image is matched with the content of the content text, and the target image has the target style.

The invention relates to a question and answer model training method and device, a question and answer method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a training set is constructed, and cue words of a first category with a known attack category label and cue words of a second category with an unknown attack category label are arranged in the training set; training an initial reward model according to the cue word to obtain a reward model which is used for outputting a reward signal; inputting the cue word into the large language model, outputting to obtain predicted reply data, and inputting the predicted reply data and the cue word into a reward model to obtain a reward signal for the predicted reply data; and determining an updating strategy of the large language model according to the reward signal of the predicted reply data, and updating the large language model based on the updating strategy to obtain a trained question and answer model. By adopting the method, the recognition precision of the question and answer model for known attack types can be improved, and the omission ratio for unknown attack types can be reduced.

The present application provides a data processing method and apparatus, an electronic device, a computer readable storage medium and a computer program product. The method comprises: acquiring historical interaction information and a predicted interaction text corresponding to the historical interaction information; extracting a first acoustic feature and a first semantic feature of the historical interaction information, and extracting a second semantic feature of the predicted interaction text; performing fusion mapping on the basis of the first acoustic feature, the first semantic feature and the second semantic feature to obtain a first paralanguage feature; denoising initial noise on the basis of the second semantic feature and the first paralanguage feature to obtain a second acoustic feature of the predicted interaction text; and on the basis of the second acoustic feature, generating a voice signal corresponding to the predicted interaction text.

A model training method includes obtaining a training sample set including a triplet training sample that includes a source image, a template image, and a true value image, performing face swapping on the source image and the template image through a first image processing model having a re-parameterization structure to obtain a face-swapped image, obtaining a second image processing model corresponding to the first image processing model and being a pre-trained image processing model, calculating a fusion loss function of the first image processing model according to the second image processing model, the first face-swapped image, and the true value image, training the first image processing model according to the fusion loss function, and determining a model parameter of the first image processing model in response to a training convergence condition of the first image processing model being reached.

A control method for a support robot, the method comprising: in response to recognizing that a target object has an intent to require support, controlling a support robot to move toward the target object, and when the support robot moves to a target movement position, controlling a robot arm to move to a target joint position, wherein the target movement position and the target joint position are both determined on the basis of the relative position between the target object and a target sensor; and in the process of the robot arm moving to the target joint position or after the robot arm moves to the target joint position, when it is detected by means of a tactile sensor that an external force is applied to the robot arm, performing compliance control on the support robot. Further provided are a support robot, an electronic device, a computer storage medium, and a computer program.

The present application provides training and speech generation methods and apparatuses for a speech generation model, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises: obtaining a first speech generation model; obtaining sample data of a plurality of modalities; on the basis of a prompt image sequence and speech text, respectively calling a plurality of encoders to perform encoding, so as to obtain a multi-modal encoding vector sequence; on the basis of the multi-modal encoding vector sequence, calling a decoder to perform decoding, so as to obtain decoded text; determining a probability distribution for the decoded text and the sample data of the plurality of modalities, and determining a target loss on the basis of the probability distribution; and on the basis of the target loss, updating parameters of the decoder and at least one of the encoders, wherein the updated decoder and the plurality of updated encoders are configured to form a second speech generation model, and the second speech generation model is used to generate target speech text corresponding to a prompt image sequence of a target object.

The multi-ECU simulation test method includes: obtaining a pre-developed application applied to a target ECU; inputting the application into a pre-built multi-ECU simulation environment; querying a simulated vehicle-mounted ECU having a unique identifier the same as the target ECU from a plurality of simulated vehicle-mounted ECUs in the multi-ECU simulation environment as a target simulated ECU; and simulating a communication process of the target simulated ECU via a simulated controller area network or a simulated Internet network in the multi-ECU simulation environment, running the application based on the target simulated ECU, and outputting a running result of the application.

The invention relates to a task execution method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of artificial intelligence chips. The processing efficiency of execution of the calculation task and the communication task on the artificial intelligence chip can be improved. The method comprises the steps of obtaining a task flow; in the same task flow, enabling a first processing unit of the artificial intelligence chip to execute a calculation task, and enabling a second processing unit of the artificial intelligence chip to execute a communication task; wherein the calculation task does not depend on the communication task; the communication task depends on a corresponding computing task, and the communication task does not depend on a non-corresponding computing task.

Provided are a protein language model training method, a method for extracting an amino acid sequence representation by using a protein language model, a method for obtaining a new amino acid sequence by using a protein language model, a method for obtaining a related amino acid sequence by using a protein language model, a method for predicting an amino acid sequence perplexity by using a protein language model, an electronic device, a computer-readable medium, and a program product. The protein language model training method comprises: during a training process, executing at least one training sub-task amongst two training sub-tasks included in a first type of training task and a second type of training task; and, on the basis of a first loss value corresponding to the first type of training task and a loss value corresponding to the second type of training task, adjusting parameters of a protein language model to obtain a trained protein language model.

The invention relates to the technical field of voice processing, in particular to a mixed voice processing method, electronic equipment and a computer readable medium. The method comprises the following steps: collecting mixed voice and environment influence parameters; carrying out bionic frequency domain analysis on the mixed voice to obtain low-frequency attenuation compensation characteristic data; performing multipath effect propagation analysis on the low-frequency attenuation compensation characteristic data through the environmental influence parameters to generate channel distortion data; performing time domain-frequency domain joint deconvolution processing on the mixed voice by using the channel distortion data to generate a direct sound component and a reflected sound component; performing adversarial training based on the direct sound component and the reflected sound component to generate anti-multipath speech enhancement data; and constructing a dynamic frequency compensation filter based on preset environmental acoustic characteristics. Through the multi-stage signal processing, frequency compensation and real-time optimization technology, the output quality of the mixed voice is improved.

The invention discloses an eye movement tracking method, an eye movement tracking device, eye movement tracking equipment, computer equipment and a storage medium. The method comprises the following steps: calculating calibration gaze information and a calibration pupil position according to first event data collected by an event camera; determining a region of interest based on the calibrated pupil position; processing second event data collected by the event camera according to the region of interest to generate region of interest data, the collection time of the second event data being later than the collection time of the first event data; according to the region-of-interest data, calculating a current fixation position offset; according to the calibration gaze information and the current gaze position offset, the current gaze information is determined, the calibrated pupil position is updated based on the current gaze position offset, the gaze direction, the moving direction and the moving distance of the pupil are accurately captured in real time by utilizing the characteristics of high time resolution and the like of the event camera, and the eye movement tracking effect is effectively improved.

The invention relates to an input rewriting method and device of an intelligent question answering system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring dialogue data input by a user for the intelligent question-answering system, and judging whether the dialogue data needs to be rewritten or not; generating a plurality of candidate rewriting results by adopting a preset rewriting model, a predefined rewriting template and a preset rewriting rule under the condition of determining that the dialogue data needs to be subjected to type rewriting processing; inputting the plurality of candidate rewriting results into a pre-trained rewriting scoring model to obtain rewriting scores corresponding to the plurality of candidate rewriting results; and according to the rewriting score, determining a target rewriting result from the plurality of candidate rewriting results, and inputting the target rewriting result into the intelligent question and answer system. By adopting the method, the answer generation accuracy of the intelligent question-answering system can be improved.

Embodiments of the present invention provide a method and apparatus for suppressing transient current of a grid-forming converter, a computing device, a computer-readable storage medium, and a computer program product. The suppressing method comprises: calculating first virtual impedance on the basis of an actual voltage instantaneous value of a point of common coupling; calculating second virtual impedance on the basis of an actual current maximum amplitude of the point of common coupling; and suppressing the transient current of the grid-forming converter on the basis of the first virtual impedance and the second virtual impedance. In this way, by combining the actual voltage instantaneous value of the point of common coupling and the actual current maximum amplitude of the point of common coupling, transient current can be suppressed at the moment when a fault occurs in a grid-forming converter, thereby avoiding misoperation triggering of a protection apparatus, and ensuring that the grid-forming converter can restore stable operation once the fault is removed.

The invention discloses an incidence relation establishing method, a version number generating method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of computers.The method comprises the steps that write-in requests of N read-write nodes are obtained, each write-in request carries to-be-written data and a version number of the corresponding read-write node. And writing the to-be-written data carried by each write-in request into the corresponding logic address section, wherein the version number is used for distinguishing the to-be-written data carried by different write-in requests. Transmitting the to-be-written data to the physical address section for storage, and respectively establishing an association relationship between the physical address section of each piece of to-be-written data and the version number corresponding to each piece of to-be-written data. Different read-write requests can be distinguished by using the version number, multi-version storage of the data is realized, the corresponding data can be traced through the version number, and the processing capability of the distributed storage system for concurrent write requests is remarkably improved.

A robot control method, comprising: acquiring the current state parameters of a robot to be controlled at the current moment; calling a state regulator to determine, on the basis of a preset dynamics model and the current state parameters, basic control parameters for each joint of said robot; performing parameter filtering processing on the basic control parameters to obtain safety control parameters for each joint of said robot; on the basis of the safety control parameters for each joint, determining motion control parameters for each joint of said robot; and on the basis of the motion control parameters for each joint, controlling each joint of said robot at the current moment. Further provided is a robot control apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

Computer vision techniques for configuring a robot having a robotic arm to interface with equipment to perform a task. The techniques include: capturing at least one image of the equipment: determining a position of a first alignment feature in the at least one captured image: determining, using the position of the first alignment feature in the at least one captured image, an alignment difference between a current alignment of the robot and the equipment with respect to a prior alignment of the robot and the equipment; and configuring the robot to interface with the equipment based on the alignment difference.

The invention relates to a vehicle obstacle avoidance trajectory planning method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining information of obstacles around a current vehicle; predicting driving tracks of all obstacles in a future preset time period according to the information of the obstacles around the current vehicle; under the condition that the condition that no fast approaching obstacle exists behind the current vehicle is obtained based on the driving track analysis, target obstacles needing to be subjected to in-lane obstacle avoidance are screened and recognized; calculating a lane occupation space of the target obstacle based on the driving data of the target obstacle; calculating the lane driving space of the current vehicle according to the lane occupation space of the target obstacle; and performing path planning and speed planning solution based on the lane driving space of the current vehicle, and generating an obstacle avoidance track of the current vehicle. By adopting the method, vehicles in the same direction of the adjacent lanes can be effectively avoided during driving on the expressway, and the driving safety is improved.

Various implementations of implants and implant surfaces for clinical rehabilitation or enhancement of a patient, related systems, and computer programs and methods for the design and manufacturing of implants are disclosed. A macroscale shape, a microscale surface texture, and a nanoscale surface topography are overlaid to increase, condition, and thereby functionalize an implant surface. A thin-film coating and / or laser interferometry is utilized to overlay on a machined implant substrate a nanoscale surface topography. Manufacturing the macroscale shape and the microscale texture may be performed with an ultrashort pulsed laser system in separate process steps. The design of a dental implant may be assisted by a self-learning computer program product, based on trained coupled shape models including, for example, mesh-based statistical shape and orientation models.

The invention provides a voice recognition method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: carrying out the voice activity detection of to-be-processed voice data, and obtaining a plurality of voice segments; determining the number of speakers in each voice segment; under the condition that the number of speakers in the voice segment is multiple, performing voice separation on the voice segment to obtain multiple audio segments; performing voice recognition on the plurality of audio segments to obtain a voice recognition result of each audio segment; performing feature extraction on the plurality of audio segments to obtain a voiceprint feature vector of each audio segment; the speakers are clustered based on the voiceprint feature vectors of the multiple audio segments, a clustering result is obtained, and the clustering result comprises the audio segment corresponding to each speaker; and obtaining a voice recognition result of each speaker in the to-be-processed voice data based on the clustering result and the voice recognition result of each audio segment. According to the embodiment of the invention, multi-channel multi-speaker speech recognition can be realized.

The invention relates to the technical field of unmanned aerial vehicle positioning, discloses an unmanned aerial vehicle accurate positioning method and device fusing multi-source positioning data, electronic equipment, a computer readable storage medium and a computer program product, and is used for solving the technical problem that accurate and stable positioning of an unmanned aerial vehicle cannot be realized in an indoor weak texture scene in the prior art. The method comprises the following steps: acquiring initial positioning data of an unmanned aerial vehicle in real time, the initial positioning data being at least from two information sources; constructing a positioning fusion algorithm based on an unscented Kalman filtering algorithm, evaluating the credibility of initial positioning data from each information source in real time, and calculating a positioning covariance matrix; and adjusting the fusion weight of each initial positioning data based on the positioning covariance matrix, and calling a positioning fusion algorithm to perform weighted fusion on the initial positioning data of each information source to obtain fusion positioning data of the unmanned aerial vehicle. According to the method, the positioning accuracy and stability of the unmanned aerial vehicle in a scene in which GPS signals are lacked and environment textures are weak can be improved.

The invention relates to a multi-agent cooperative recruitment method, system and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a target recruitment demand, and generating a task tree for the target recruitment demand through a preset dynamic decision-making mechanism in a main agent; determining a time sequence relationship and logic constraint information of each sub-task in the task tree, and calling target sub-agents in the sub-agents in sequence based on the time sequence relationship and the logic constraint information; the target sub-agent is used for executing the sub-task in the task tree; and generating a target recruitment task result until task execution results of the sub-tasks are obtained. By adopting the method, the recruitment efficiency can be improved.

The invention relates to a power system network security threat monitoring and early warning method and device, power equipment, a computer readable storage medium and a program product, and belongs to the field of power system network security. The method comprises the following steps: acquiring historical data and real-time data; obtaining first network feature data based on historical data, performing unsupervised learning training on the initial detection model, and taking abnormal data as second network feature data; marking the second network feature data as third network feature data; marking the first network feature data to obtain fourth network feature data to perform self-supervised learning training on the model, and obtaining first network attack features to construct a network attack feature library; performing semi-supervised learning training on the model based on the first network feature data and the third network feature data to obtain a detection model, and updating a network attack feature library; and detecting real-time data based on the detection model and the network attack feature library. The method can improve the accuracy of power system network security threat monitoring and early warning.

The invention relates to a task processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring data processing tasks from an edge processing node, and acquiring task demand information corresponding to each data processing task; acquiring node state information of each processing node in the computing power network; according to the node state information and task demand information carried by the data processing task, determining a target processing node by taking resource utilization rate maximization of each processing node in the computing power network as a target; determining a target transmission path and a target transmission protocol by taking maximization of transmission bandwidth and minimization of transmission delay as targets according to data size information and time delay requirements carried by the data processing task, and a network state and a transmission protocol of a target processing node; and transmitting the data processing task to the target processing node through the target transmission path and the target transmission protocol. By adopting the method, the task processing efficiency can be improved.

The invention relates to an image detection method and device for a mitral valve, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring multiple frames of images including a heart, and performing multi-scale feature extraction on the multiple frames of images to obtain multi-scale image features of each frame of image; for each frame of image, determining a mitral valve area of the heart in each frame of image according to the multi-scale image features of the image; determining the area of a mitral valve opening in each frame of image based on the mitral valve area of the heart in each frame of image; and generating a detection result of the mitral valve membrane of the heart according to the area of the mitral valve opening in each frame of image. By adopting the method, the problems that a traditional manual measurement method is time-consuming and is easily influenced by subjective factors and the like can be solved, the efficiency and accuracy of mitral valve evaluation are also remarkably improved, professional requirements on operators are reduced, and the flexibility and practicability of clinical application are enhanced.

A virtual object animation generation method and apparatus including obtaining a to-be-processed video, determining initial 3D pose information, two-dimensional (2D) pose information, and foot ground contact information of a target object in the to-be-processed video, determining pose change information between two adjacent video frames in the to-be-processed video based on the initial 3D pose information of the target object, determining to-be-corrected pose information of the target object based on the initial 3D pose information of the target object and the pose change information, performing correction processing on the to-be-corrected pose information of the target object based on the 2D pose information and the foot ground contact information of the target object, to obtain corrected pose information of the target object, and retargeting the corrected pose information to a virtual object by means of motion retargeting, to generate a virtual object animation video corresponding to the to-be-processed video.

The invention relates to an image processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a zooming operation, obtaining a current zooming magnification of a current image frame and a target zooming magnification currently issued by a camera application; determining a zoom scene type according to the current zoom ratio and the target zoom ratio; obtaining a corresponding target zooming curve according to the zooming scene type, and obtaining a transition zooming magnification between a current zooming magnification and a target zooming magnification by using the target zooming curve; and processing the acquired image data based on the transition zoom magnification to obtain the image data under the transition zoom magnification. The gradual change of the field angle of the image data in the focus-varying scene is realized, the sudden change of the field angle is avoided, and the picture change is smoother.

The invention relates to a data analysis method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a to-be-processed text, and performing word segmentation processing on the to-be-processed text to obtain a word segmentation data set; performing analysis processing on the word segmentation data in the word segmentation data set through a hybrid expert model, and determining a weight value corresponding to each expert network in the hybrid expert model based on an analysis processing result and a gating network; performing sorting processing and cumulative probability calculation on the weight values corresponding to the expert networks, and determining the number of the expert networks and a target expert network based on a cumulative probability calculation result; and based on a target expert network of the expert network number and a weight value corresponding to the target expert network, determining an analysis decision result of the word segmentation data until analysis decision results of all word segmentation data in the word segmentation data set are obtained, and determining a data analysis result of the to-be-processed text. By adopting the method, the overall decision-making accuracy of the hybrid expert model is improved.

Embodiments of the present application relate to speech processing technology. The embodiments of the present application provide a data processing method and apparatus based on artificial intelligence, an electronic device, a computer program product, and a computer readable storage medium. The method comprises: acquiring speech, and acquiring emotion data corresponding to the speech; performing first speech content feature extraction processing on the speech to obtain a first speech content feature corresponding to the speech, and performing emotion feature extraction processing on the emotion data to obtain emotion features corresponding to the speech; performing fusion processing on the first speech content feature and the emotion features to obtain a fusion feature corresponding to the speech; and performing animation parameter mapping processing on the fusion feature to obtain controller parameters corresponding to the speech, wherein the controller parameters are used for controlling a virtual object model to be presented in a target image, and the target image matches the content of the speech and the emotion data.

The invention provides a voice quality inspection method and device, electronic equipment and a computer readable storage medium, relates to the technical field of artificial intelligence, and is suitable for the field of financial science and technology. The method comprises the following steps: acquiring target dialogue voice; performing text conversion on the target dialogue voice to obtain a target dialogue text; performing semantic division on the target dialogue text to obtain target semantic blocks and semantic block categories; performing information search on a preset knowledge graph according to the target semantic block to obtain an entity triple text; reading sentences in a preset semantic sentence database according to the semantic block categories to obtain standard semantic sentences; performing text fusion according to the semantic block category, the standard semantic sentence, the target semantic block and the entity triple text to obtain a target quality inspection prompt text; and performing quality inspection on the target quality inspection prompt text to obtain a voice quality inspection result. According to the embodiment of the invention, the voice quality inspection accuracy can be improved.

The invention relates to an application method of a GPU (Graphics Processing Unit) in design rule inspection in the field of integrated circuits, in particular to a layout design rule inspection method, system and equipment, a medium and a product. The layout design rule checking method comprises the following steps: inputting initial layout data, analyzing a design rule checking task to be executed, and marking the priority and complexity level of the task; the method comprises the following steps: dividing layout data into a plurality of data blocks according to regions on the basis of regional characteristics of the layout data, distributing tasks and corresponding data blocks to a GPU computing core according to task priorities and complexity levels, and distributing new data blocks according to the overall load condition of the GPU computing core after the GPU computing core completes data block processing, and repeating the steps until all tasks are executed, and outputting a layout design rule check result. The system, the computer equipment, the computer readable storage medium and the computer program product have the same beneficial effects as the layout design rule checking method.