549results about How to "Save computing resources" patented technology

The invention belongs to the technical field of image classification neural networks, and discloses a lightweight image classification neural network architecture system based on knowledge distillation. The invention provides a lightweight image classification neural network architecture system based on knowledge distillation. The lightweight image classification neural network architecture system comprises a data set preprocessing module, a teacher model preprocessing module, a subnet model construction module, a personalized training module, a real loss calculation module, a distillation loss calculation module, a total loss calculation module and a student model construction module. The invention provides a lightweight neural network architecture system based on knowledge distillation, and designs a brand new training mode by using the superiority of knowledge distillation for teacher model weight extraction: the knowledge distillation of teacher and student models is combined with a deep compression method; the system for constructing the lightweight network can be used for training various complex image classification neural networks so as to improve the network performance.

The invention relates to the field of drug target interaction, and discloses an application of a multi-modal feature fusion model in drug target binding affinity prediction, which comprises the following steps: S1, obtaining an original data set of drug target binding affinity, and taking a binding affinity index in the data set as a label of a training set and a test set; s2, acquiring representation information of other modals by using the drug sequence and target sequence representation provided in the original data set, preprocessing the acquired representation information of drugs and targets in different modals, and processing the representation information into a model acceptable feature vector form; and S3, respectively storing the multi-modal feature vectors of the drug and the target as well as the binding affinity tags in a form of pytorchsensor (. Pt). According to the method, shallow characterization of the drug and protein sequences is learned by applying the pre-training model, and the problem that a drug target binding affinity data set is insufficient is solved.

The invention, which relates to the technical field of offshore wave simulation, discloses a wave hydrodynamic numerical simulation method for a sea area with a breakwater, comprising the following steps: S1, determining a target sea area, and collecting sea chart data and water depth topographic data of the target sea area; s2, determining a shoreline position of the target sea area, and establishing a water depth terrain database of the target sea area; s3, setting grid precision, and constructing a wave hydrodynamic two-dimensional model of the target sea area; s4, setting boundary conditions for driving the wave hydrodynamic two-dimensional model, and setting initial parameters; and S5, based on the wave hydrodynamic two-dimensional model constructed in the S3, performing numerical simulation on the target sea area by using a sub-grid method to obtain the characteristic wave height and periodic data of the target sea area. According to the method provided by the invention, the calculation efficiency can be ensured, the wave transmission characteristics of the open type oyster reef are considered, and the influence of open type oyster reef construction on the wave hydrodynamic environment field can be accurately simulated.

The invention discloses a multi-class defect detection method and device based on a variational auto-encoder and a denoising network, and the method comprises the steps: obtaining an industrial product surface defect image, carrying out the preprocessing, and constructing a training set and a verification set; the training process of the method is divided into two stages: in the first stage, a preprocessed training image is input into a variational auto-encoder for training, feature distribution of the image is learned, and features of a normal image are captured by reconstructing the image; in the second stage, a denoising network and a feature guiding module are used for conducting secondary reconstruction on image features in the feature space of the variational auto-encoder, and therefore the reconstruction capacity and the multi-class reconstruction capacity of the model are enhanced; in the reasoning stage, multi-scale features of an original image and a reconstructed image are extracted through a feature extractor, feature comparison is carried out, and an abnormal scoring graph is generated. According to the method, normal information is reserved while the reconstruction capability of the variational auto-encoder is enhanced, and defect missing detection caused by reconstruction failure is effectively reduced.

The embodiment of the invention discloses a multi-unmanned aerial vehicle cooperative traffic state monitoring method, device and equipment and a medium, and relates to the technical field of multi-unmanned aerial vehicle cooperative control, and the method comprises the steps: carrying out the routing inspection in a preset routing inspection region through a plurality of unmanned aerial vehicles; identifying whether the traffic state is abnormal or not through the trained deep learning model; when it is recognized that the traffic state is abnormal, cooperative unmanned aerial vehicles are selected, the cooperative unmanned aerial vehicles are distributed to the traffic state abnormal areas, and traffic state data are cooperatively collected through the cooperative unmanned aerial vehicles; each cooperative unmanned aerial vehicle fuses the traffic state data of other cooperative unmanned aerial vehicles and then outputs fused traffic state data; and obtaining a real-time traffic state monitoring result based on the fused traffic state data of the cooperative unmanned aerial vehicle. According to the method, the same scene is perceived from different angles through the multiple unmanned aerial vehicles, data of multiple view angles can be fused, the accuracy of accident detection is improved, and data support can be provided for related departments to deal with traffic anomalous events.

The invention discloses a tooth three-dimensional digital model registration and tooth neck line extraction method based on oral scanning and CBCT, and relates to the field of tooth three-dimensional digital model registration. Comprising the following steps: respectively acquiring three-dimensional oral images of oral scanning and CBCT (cone beam computed tomography), and automatically segmenting three-dimensional structures of dental crowns and teeth by utilizing pre-trained V-Net and ToothNet image segmentation models. Alignment and registration of two modal images are realized through a feature extraction network, an information exchange network and a rigid transformation network. The feature extraction network extracts local and global features by using far-point sampling and a dynamic graph convolutional neural network, the self-attention and cross-attention module performs feature enhancement and information exchange between the same mode and different modes, and based on a registration result, a tooth neck line is further extracted and optimized. According to the method, the tooth three-dimensional digital model can be quickly and accurately registered, a high-precision tooth neck line extraction result is provided, the manpower and time cost of a medical institution can be reduced, and the medical efficiency is improved.

The invention discloses a Carnot battery system coupled with an uninterrupted low-temperature heat source and an integrated optimization method of the Carnot battery system. The Carnot battery system comprises a high-temperature heat pump system, a heat storage system and a power circulation system, in the charging process, the high-temperature heat pump system operates, and waste heat of the uninterrupted low-temperature heat source module is improved into high-grade heat energy to be stored in the heat storage system through renewable energy source electric power; in the discharging process, the power circulation system operates, gradient utilization is conducted on heat energy stored in the heat storage system and an uninterrupted low-temperature heat source in the discharging stage, and generated mechanical energy is converted into electric energy through a generator and output to a power grid. The system configuration does not depend on the working medium type, and the comprehensive utilization rate of the uninterrupted low-temperature heat source and the back-and-forth efficiency of the Carnot cell are improved; according to the integrated optimization method, the working medium is coded to become a continuous variable capable of being synchronously optimized, and the optimal charge-discharge cycle working medium combination and system operation parameters suitable for different operation conditions can be obtained only through one-time optimization.

A CAE simulation result visualization system supporting multiple interaction modes comprises a multi-resolution rendering module used for obtaining interaction behaviors of a user and dynamically adjusting the resolution of a rendering area according to the interaction behaviors of the user; the key frame and time step screening module is used for analyzing the input simulation data, automatically screening out key frames and detecting the time step change of the simulation data according to a time sequence analysis method; the data compression and simplification module is used for compressing the data by using a feature-preserving compression algorithm, performing incremental storage and sparse representation on the compressed data, and recording data changes; and the dynamic local playing and frame-skipping rendering module is used for acquiring a user local time playing instruction, and processing user local time and non-user local time respectively through a frame-skipping rendering method so as to realize multi-frame rendering and switching. According to the method, the data analysis efficiency is improved, the rendering and data transmission efficiency is improved, and computing resources are saved.

The invention discloses a crack propagation simulation analysis method based on a real-structure thermal barrier coating under cyclic load, which comprises the following steps: creating a finite element model according to a thermal barrier coating sample; setting material attributes and section characteristics in the finite element model; after parameters are set, a thermal cycle load is applied to the surface of the finite element model, analysis is carried out after grid division, and an Odb file is obtained; and copying the finite element model, taking the Odb file as a boundary condition, and carrying out thermal-mechanical coupling to obtain thermal stress and crack expansion conditions after thermal circulation. The analysis method is simple, the real service condition and the microstructure are fitted, the expected research effect is achieved for finite element simulation, and accurate simulation data can be obtained.

The invention discloses a method for dynamically calling multiple models for a deep learning algorithm and a service architecture. The method comprises the steps that a client sends a request to a scheduling service through a standard AP I interface; after the scheduling service receives the request, key information of the request is analyzed and extracted to generate a task queue, and a Server server is selected; the scheduling service acquires state data provided by the Agent service in real time, and performs task allocation according to the load condition of the Server; the scheduling service stores the selected task information into a database, and marks a'to-be-processed 'state in a task state table; after receiving the scheduling task, the Server calls a model management service to load a specified reasoning model; and S6, after the reasoning task is executed, the reasoning service pool informs a scheduling service of a result through a callback mechanism. The method has the advantages that the processing capacity and efficiency of the deep learning task are improved, the requirements of different tasks are met by dynamically calling multiple models, meanwhile, resource use is optimized, and the expandability of the system is guaranteed.

The invention provides a road environment perception method and a perception model training method, and relates to the technical field of image processing, in particular to the fields of automatic driving, computer vision, deep learning and neural network models. The specific implementation scheme of the road environment sensing method comprises the following steps of: obtaining image features from a look-around image of a vehicle by utilizing a feature extraction network of a first sensing model; wherein the look-around image is obtained according to a plurality of image acquisition devices at different angles; determining a bird's-eye view feature map according to the image features and the bird's-eye view query vector by using a coding network of a first perception model; and respectively determining output results of the plurality of perception tasks according to the bird's-eye view feature map by using the plurality of head networks of the first perception model. According to the technical scheme provided by the invention, computing resources consumed by simultaneous execution of multiple visual tasks can be effectively reduced, and the real-time performance and task effects of the multiple visual tasks are ensured.

The invention discloses an infrared target detection method based on knowledge distillation and fast multi-scale fusion, and the method comprises the steps: constructing an infrared target detection model based on a teacher-student network, dividing an obtained infrared target image into a training set and a test set, inputting the data of the training set into the model for training, and obtaining a trained model; and inputting the test set for testing, inputting a to-be-detected infrared target image into the model after the test is completed, and outputting an infrared target detection result to complete infrared target detection. According to the method, a knowledge distillation technology is utilized, a high-complexity teacher network model is used for assisting student network model training, a fast multi-scale fusion module and a fast self-adaptive sensitivity strategy are designed for a teacher network and a student network, computer storage space and computing resources are saved, small target positioning is more accurate, and the method is more practical. And features of different levels of the small target are reserved, a large amount of storage space and computing resources are effectively relieved, and accurate detection of the infrared small target is realized.

The invention discloses a transcutaneous electrical stimulation device based on a large language model, and relates to the technical field of wearable devices. The transcutaneous electrical stimulation equipment based on the large language model comprises a data acquisition and preprocessing module, a feature extraction and fusion module, a model training and prediction module and a real-time information processing and response module, real-time data processing and intervention capabilities are integrated, human body data can be analyzed in real time, electrical stimulation parameters can be automatically adjusted, an instant treatment or adjustment scheme is provided for the problems of arrhythmia, chronic pain and the like, and the timeliness and effectiveness of treatment are greatly improved. And secondly, by fusing the physiological signal features and the symptom text features, the equipment can more comprehensively understand the health condition of the user, so that a more accurate treatment scheme is provided. Besides, the equipment also has the functions of anomaly detection and trend analysis, can predict potential health risks, and triggers an alarm in time when a serious anomaly is detected, thereby effectively guaranteeing the life safety of the user.

The invention discloses a government affair field question-answering system based on a retrieval type enhanced large model and a use method thereof, and belongs to the technical field of artificial intelligence. The problems that wrong answers can be given due to the difference of related policy documents of different regions or administrative divisions, and hot questions with many questions are answered in a historical generation mode are solved. The government affair field question-answering system based on the retrieval type enhanced large model comprises a database module, a historical record matching module, a first large model module, a policy query module and a second large model module. Different region or administrative division information and policy documents are combined, a government affair field question and answer system based on a retrieval type enhanced large model is perfected, and when the question and answer system is used for questioning, accurate reply based on the different region or administrative division information and the related policy documents can be given more conveniently and quickly.

The invention relates to the technical field of numerical simulation, in particular to a grid model generation method for the fluid displacement process of well cementation engineering. The method comprises the following steps: acquiring geological data of a well cementation project area, and constructing an initial geological model; well cementation engineering design data are obtained, well cementation engineering topological structure modeling is carried out, and a well cementation engineering topological structure model is obtained; according to the initial geologic model and the well cementation engineering topological structure model, fluid dynamic simulation is carried out, and a fluid characteristic matrix is obtained; performing fluid displacement process simulation according to the fluid characteristic matrix to obtain fluid displacement process data; performing fluid displacement process optimization on the well cementation engineering design data based on the fluid displacement process data to obtain optimized fluid displacement process data, and performing resource allocation redistribution on the well cementation engineering design data according to the optimized fluid displacement process data to obtain optimized well cementation engineering design data. According to the invention, the accuracy of fluid displacement simulation can be improved.

The invention discloses a small-scale greenhouse gas emission prediction method based on a pre-training model, and belongs to the field of greenhouse gas emission prediction. According to the method, a greenhouse gas monitoring micro station is arranged in a park, data such as greenhouse gas concentration and meteorological factors are collected in real time, and high-precision traceability of a greenhouse gas emission source and accurate accounting of greenhouse gas emission can be achieved in combination with a high-precision meteorological numerical value mode, a backward trajectory tracking algorithm, a receptor model and a diffusion model; the greenhouse gas emission amount is predicted in real time by calling the pre-training model, and the prediction efficiency and accuracy are remarkably improved. Different from a mode that a traditional model depends on a large amount of historical data training, the pre-training model can be finely adjusted on the basis of a small amount of existing data, so that effective learning and prediction are realized. According to the method, a large amount of time and computing resources are saved, the environmental change can be quickly responded, and real-time and accurate emission prediction is provided.

The invention belongs to the technical field of wind power prediction, and particularly discloses a short-term wind power prediction method and system for a fan icing scene, and the method comprises the steps: constructing an icing model suitable for a fan blade, and solving key parameters in the icing model under a set meteorological condition in an auxiliary manner through icing simulation; acquiring meteorological data and icing data under a fan icing scene in a set time range of a to-be-measured area, inputting the meteorological data into the trained basic prediction model to obtain a wind power basic prediction result, and inputting the icing data and wind speed data into the trained power loss prediction model to obtain a power loss prediction result; and obtaining a final short-term wind power prediction result for the fan icing scene based on the wind power basic prediction result and the power loss prediction result. According to the method, the calculation accuracy of the icing data can be improved in the earlier stage of saving calculation resources, so that the reliability of a power prediction result is improved.

The invention discloses a multi-scale Transform image rain removal method based on residual channel prior guidance, and the method comprises the steps: obtaining a rain image, inputting the rain image into a trained image rain removal processing network, and obtaining a rain-removed image. The training process of the image rain removal processing network comprises the following steps: acquiring a rain image sample and a corresponding real rain-free image; extracting a prior feature map of the rain image sample by using a residual channel prior extraction module; extracting features of the rain image sample by using a context feature extraction module to obtain shallow layer features of rain fringes on different scales; performing feature fusion to obtain a first comprehensive feature map; processing the first comprehensive feature map by using L recursive Transform extraction modules (RSTMs) to obtain an image after rain removal; and calculating the loss between the image after rain removal and a real rain-free image corresponding to the input rain image sample, and optimizing network parameters through back propagation of the loss. According to the invention, rain stripes can be removed from different directions and scales, so that the rain-removed image is more consistent with a real image.

A wild animal species identification method based on incremental learning belongs to the field of target detection, and comprises the following steps: constructing a known category species detection data set, training a known category species detection model, selecting representative samples of each category species, and storing expression characteristics of each category species; constructing a species discrimination data set, and training a species discrimination model; manually checking new species sample data; and constructing a species detection fine tuning data set, updating a known category species detection model based on a feature playback class increment strategy, and updating a species discrimination model based on a feature-level sample playback class increment strategy. The method has the capability of identifying whether species belong to known categories in a training set; according to the method, after the data of the newly-added species category is acquired, the ability of identifying the new species can be learned at the minimum calculation cost; according to the method, the intermediate expression features of partial representative samples of old data are stored locally and then merged with the new category of data, and then the network is finely adjusted, so that the computing resource consumption is low.

The invention discloses a general image evaluation method based on a hybrid expert model, which can be applied to various image evaluation scenes to automatically evaluate the quality or aesthetics of images. According to the method, a visual encoder and a text encoder are used for extracting visual and text features of an image respectively, and a quality or aesthetic score is calculated through an adapter. The visual encoder and the text encoder are integrated with a hybrid evaluation expert module, the hybrid evaluation expert module combines a shared evaluation expert and a self-adaptive evaluation expert, the shared evaluation expert is responsible for learning general evaluation knowledge, the self-adaptive evaluation expert dynamically learns specific data sets, expert contribution is adjusted through a router, and labeling deviation in multi-data-set training is effectively managed. Furthermore, a scene-based difference prompt strategy is implemented, the model adaptability is enhanced through a scene specific prompt word, the annotation deviation between data sets is reduced, and the evaluation accuracy is improved. The method not only improves generalization and adaptability of the model, but also optimizes parameter efficiency and training efficiency, and has a wide application prospect.

The invention relates to a power data federated learning privacy protection method based on efficient homomorphic encryption. The method comprises the following steps: step 1, a client initializes a neural network model; step 2, the server side encrypts and updates local neural network model gradient parameters uploaded by the client side; 3, the server side executes gradient average aggregation operation, the server side does not need to decrypt, the encrypted gradient parameters uploaded by the client side are directly calculated, an average value is solved, and therefore global gradient parameters are updated; step 4, after each client receives the updated global gradient, carrying out decryption calculation operation; 5, loading the updated weight parameters of the neural network model into a local neural network model, and performing neural network model training by using a local data set; the problems that an existing encryption technology is large in operand, large in computing resource overhead and low in algorithm efficiency, and privacy leakage exists in the transmission and analysis process of power data can be solved.

The invention discloses a multi-modal prompt learning method based on retrieval enhancement, which can align a text encoder and a visual encoder of VLMs at the same time, adopts a retrieval enhancement strategy, captures cross-modal information through a cross-attention mechanism, realizes efficient multi-modal interaction, generates an adaptive embedded prompt based on the cross-modal information, and improves the learning efficiency. A multi-modal representation space is flexibly aligned, a learnable vector library (LTL) is introduced, the prompt generation effect is further optimized, excellent performance in various scenes is ensured, the accuracy of self-adaptive prompt can be enhanced through a retrieval enhancement strategy and a cross-modal cooperative sensing technology, efficient interaction of multi-modal information is achieved in combination with the learnable vector library, and the self-adaptive prompt effect is improved. Computing resources needed by fine tuning are reduced, the generalization ability of the model and the processing performance of complex tasks are remarkably improved, and a new solution is provided for efficient adaptation and optimization of large-scale pre-training VLMs.

The invention discloses an Internet of Things cross-domain payment method with a privacy protection function. The method comprises the steps of initialization, storage, uploading, verification, cross-chain interaction, settlement and timeout. According to the method, the validity of the content can be verified under the condition of not leaking any content by adopting the zero-knowledge proof technology, the specific position of group members, namely each site, can be hidden by adopting the group signature technology, the position information of a user is hidden, and the position privacy of the user is protected; the anonymous block chain technology hides the transfer relationship between the real user and the corresponding virtual user, so that the user identity privacy is effectively protected; according to the cross-chain channel technology, information transfer between sites on different block chains is realized, the cross-chain interaction efficiency is improved, and the cross-domain payment requirements between different block chains in different industries are met; the intelligent contract, the zero-knowledge certification technology and the group signature technology realize privacy protection and realize distributed automatic verification of information with relatively low chain cost, so that verification efficiency is improved, and computing resources and cost are saved.

The invention provides a skin state classification method based on progressive transfer learning and modal domain adaptation, relates to the technical field of skin state recognition based on a neural network, and aims to realize a skin health state classification method which is accurate and efficient and is not limited by labeled data volume and not influenced by clinical modals. Comprising the following steps: constructing a plurality of intermediate data sets through unlabeled samples in different types of skin state fields; adjusting color space and feature distribution of the plurality of intermediate data sets based on HSV color space conversion and a CycleGAN model; on the basis of modal domain adaptation, a progressive transfer learning strategy is adopted, parameters of an identification model are finely adjusted step by step through a plurality of intermediate data sets, and data sources of unlabeled and label-free skin images of different sources and different types are adopted as labels of the skin images; and adjusting the identification model according to the marked target data set through a self-adaptive unfreezing method. The method has the advantages of improving the classification accuracy and reducing the dependence on the marked data.

The invention belongs to the technical field of information science, and particularly relates to a disease survival prediction method based on a multi-scale pathological image and multi-modal data, which comprises the following specific steps: digital pathological image data processing, gene representation data processing, multi-modal data interaction and survival analysis. According to the method, image blocks corresponding to two magnification factors of x40 and x20 are used as input of a model, and integration of multi-scale information is realized by adopting an early fusion strategy; compared with a method of repeatedly calculating the same position by adopting a multi-view WSI, the method provided by the invention adopts a non-overlapping image segmentation and blocking mode, so that the over-fitting of the model can be prevented to a certain extent, and the efficiency of the model is improved.

The invention provides a discrete element simulation method of an implicit particle environment, which comprises the following steps: S1, fully mixing an ore grinding medium and a ground material, taking the mixture as a whole, and measuring a stacking angle; s2, constructing an ore grinding medium discrete element model of implied particles; s3, constructing a discrete element model of the accumulation angle measuring device; and S4, parameter optimization and discrete element simulation. The maximum error between the collision energy spectrum obtained through simulation of the method and conventional simulation is only 3.3%, meanwhile, it is avoided that a large number of mineral particles are added into simulation calculation, a large number of calculation resources are saved, and energy, speed and other information of mutual collision between media in the ore grinding operation process can be rapidly and accurately obtained.

The invention discloses a voice recognition emergency braking system and method for an intelligent driving vehicle, relates to the technical field of voice recognition emergency braking, and solves the problem that when emergency braking is performed through voice recognition, the situation that in-vehicle volumes of different users have different characteristics in different time periods is neglected, and emergency braking is performed according to the different characteristics, so that the emergency braking efficiency is improved. And the technical problem of difficulty in self-optimization of the time period in division is solved. The method comprises the following steps: acquiring sound data when a vehicle runs; dynamically planning the time period of each day, analyzing the historical volume in the vehicle to obtain the characteristic volume of each time period in the vehicle, and obtaining a discrimination factor based on the characteristic volume, the volume in the vehicle, the personnel tone and the sound data outside the vehicle; obtaining a control instruction according to the personnel voice characters and the discrimination factor; the vehicle is braked based on the control instruction; according to the invention, the self-adaptability and accuracy of the voice recognition emergency braking system of the intelligent driving vehicle can be improved.

The invention provides an image feature detection method based on flexible connection, relates to the technical field of image analysis and processing, and aims to solve the defects of an existing image feature detection method in the aspects of accuracy, processing speed, detection sensitivity, false detection rate and the like. The method comprises the following steps: firstly, acquiring an input image, converting the input image into a grayscale image, carrying out Gaussian filtering processing, then calculating a gradient magnitude and direction, and carrying out non-maximum suppression and dual-threshold processing to obtain a preliminary edge image and a final edge image; and then connecting the weak edge pixels, extracting image features through a connected region analysis algorithm, calculating parameters such as a geometric center, a perimeter and an area, judging whether the features meet requirements or not according to a preset rule, and finally outputting the image features meeting the requirements. According to the method, parameters can be flexibly adjusted, different images can be adapted, the method is excellent in the fields of object recognition, medical image analysis, industrial detection and the like, the detection accuracy and efficiency are improved, the false detection rate is reduced, and the method has wide application prospects and practical value.

The invention relates to the technical field of artificial intelligence, and provides a retrieval enhancement generation optimization method, system and device, a product and a medium, and the method comprises the steps: obtaining an original document, and carrying out the arrangement and index construction of the original document to obtain a retrieval document; constructing a hybrid retriever, and obtaining a first candidate document through the hybrid retriever; generating a hypothesis document through the first candidate document, and performing secondary hybrid retrieval on the retrieval document through the hybrid retriever to obtain a second candidate document; calculating the information association degree of the second candidate document; screening the second candidate document to obtain a coarse screening document; recombining and segmenting the roughly screened document to obtain segmented documents, and calculating key information density scores of words in the segmented documents to obtain vocabulary key information density scores of the words; and screening the segmented documents according to a fine screening threshold value and the vocabulary key information density score to obtain a target document. According to the method, the reliability of retrieval enhancement and the retrieval quality are effectively improved.

The invention discloses a quantum task execution method and device, equipment and a storage medium, and relates to the technical field of quantum. The method comprises the following steps: acquiring a logic quantum circuit of a quantum task to be executed, wherein the logic quantum circuit is an abstract logic circuit for executing the quantum task; according to topological information of the logic quantum circuit and the virtual quantum chip, a virtual quantum circuit of the quantum task is generated, the virtual quantum chip corresponds to a partial structure of the physical quantum chip, and the topological information of the virtual quantum chip is used for representing a topological relation among virtual quantum bits included in the virtual quantum chip; according to the virtual quantum circuit and the bit mapping relation between the virtual quantum chip and the physical quantum chip, a physical quantum circuit of the quantum task is generated, and the physical quantum circuit is a circuit which is constructed based on physical quantum bits and used for executing the quantum task; and executing the physical quantum circuit through the physical quantum chip to obtain an execution result of the quantum task. The method helps to improve the utilization efficiency of quantum computing resources.