903 results about "Memory footprint" patented technology

The invention discloses a high-efficiency computer software system resource scheduling method, system and device and a medium, and the method comprises the steps: deploying a hardware counter in an operating system, and monitoring the CPU utilization rate, memory occupation, disk I / O, network bandwidth, the use condition of data aggregation system resources and the resource demand of each process or thread in real time; based on monitoring data, analyzing a current resource supply and demand state by adopting an advanced algorithm, and predicting a future resource demand trend; according to an analysis result, a resource allocation strategy is dynamically adjusted, it is ensured that a high-priority task obtains needed resources in time, and meanwhile fairness of a low-priority task is considered; data feedback after scheduling execution is collected, a scheduling algorithm is continuously optimized, and the scheduling efficiency is improved; the system, the equipment and the medium are used for realizing the high-efficiency computer software system resource scheduling method. The problems that an existing computer system is low in resource utilization rate, poor in key task stability and high in operation and maintenance cost are solved.

The invention relates to the technical field of resource scheduling, in particular to a cloud computing resource management system. In the cloud computing resource management process, the execution data of the computing tasks are analyzed, the task combinations with relevance are screened, and the computing path task set is established, so that the scheduling of the computing tasks is more intelligent, and the resource utilization rate is improved. And resource allocation is performed according to the matching degree of the calculation demand and the computing power pool, the adaptability of the calculation resources is dynamically adjusted, and accurate scheduling of the calculation task is realized. And in combination with the load state of the calculation node, the CPU utilization rate, the memory occupancy rate, the I / O load and other key indexes are monitored in real time, so that the resource allocation is more flexible, the calculation pressure of the high-load node is reduced, and the stability of the whole system is ensured. The load conditions of the computing power pools are evaluated, the task allocation strategy is adjusted, the computing tasks are reasonably distributed among the multiple computing power pools, the task migration and resource expansion strategy is optimized, and the balanced utilization rate of computing resources is improved.

The invention discloses a long time sequence information prediction method based on a multi-scale double-source fusion network model, time domain and frequency domain features are modeled at the same time, the ability to understand a complex time sequence is enhanced, an efficient multi-scale attention module of cross-space learning can capture short-term and long-term dependency relationships at the same time, and the prediction accuracy is improved. The modeling capability of different time scale information is improved, dynamic weighted fusion of time domain and frequency domain features is realized by a gating mechanism, and the flexibility and robustness of the model are improved. And through standardization and size projection, feature deviation and memory occupation are reduced, model convergence is accelerated, and the overall memory demand is reduced. The efficient multi-scale attention module accurately captures features, weakens noise and abnormal value influences, and reduces unnecessary calculation and memory consumption. The gating mechanism dynamically adjusts the feature weight, preferentially processes key information, and reduces the memory demand.

The invention discloses an edge computing node dynamic load balancing method based on a multi-agent system, and relates to the technical field of node load balancing. According to the edge computing node dynamic load balancing method based on the multi-agent system, the current computing power communication data and the operation environment data of each edge computing node are collected, the operation load index of each node is analyzed, and whether an overload node exists or not is judged; if an overload node exists, a plurality of nodes adjacent to the overload node are obtained, a task migration candidate set is screened out, finally, a target node is determined from the candidate set, and task migration operation is executed; the operation load index of the edge computing node is dynamically quantified by collecting and comprehensively analyzing multiple parameters such as the CPU utilization rate, the memory occupancy rate, the communication delay, the temperature rise rate, the I / O blocking rate, the power consumption fluctuation rate, the cache write-in waiting time and the vibration disturbance amplitude in real time. Compared with a traditional single index or fixed threshold mode, the method can identify the node overload state more accurately and timely.

The invention provides a target recognition model reasoning optimization method and device, and the method comprises the steps: firstly carrying out the structural analysis and sensitivity evaluation of a pre-training model, extracting the structural features of each network layer, activating the distribution features, carrying out the quantitative sensitivity scoring, and constructing a data set reflecting the hierarchical features and fault-tolerant capability; and querying a quantitative configuration knowledge base based on the data set to generate a heterogeneous quantitative strategy. Layered low-bit quantization is executed according to the strategy, and a layered weighted loss function is introduced to carry out quantization perception training, so that precision loss caused by bit width compression is effectively compensated. According to the method, through hierarchical heterogeneous quantification, the model recognition precision is preserved to the maximum extent while high compression ratio and reasoning acceleration are achieved, and particularly, the performance of a high-sensitivity layer is protected. The generated heterogeneous quantitative model remarkably reduces memory occupation and power consumption, is suitable for an edge hardware platform with limited resources, forms a set of complete automatic process from analysis and configuration to training compensation, and has good universality and engineering practical value.

The invention discloses an optimization method and device for improving a near-end strategy based on a language model and electronic equipment, and the method comprises the steps: determining a plurality of answers corresponding to question data, and determining a first probability value of a single vocabulary in each answer based on the plurality of answers; determining a second probability value of a single vocabulary in each answer based on a reference model in the language model, and determining a KL divergence based on the first probability value and the second probability value; determining an instant reward for each answer based on a reward model in the language model and the target reward signal; and determining a target loss function based on the question data, the answer, the first probability value, the immediate reward and the KL divergence to update a policy model of the language model based on the target loss function. According to the method provided by the invention, the memory occupation problem in the near-end strategy training process can be relieved, and the memory usage is reduced, so that the concurrency is improved, and the answer generation and training process is accelerated.

A method and system for optimizing compute runtime and memory footprint of a linear transformation process are provided. The method includes determining a set of optimal rotation parameters, wherein the optimal rotation parameters provide an optimal tradeoff between runtime compute resources and a memory footprint for a runtime execution of the linear transformation process; initializing the linear transformation process to run a boosting technique with the determined set of optimal rotation parameters, wherein the boosting technique, when executed at runtime as part of the linear transformation process, performs at least one iteration that yields rotated ciphertexts, and wherein the at least one iteration is based on the determined set optimal rotation parameters and at least one key switching key (KSK); and loading the initialized linear transformation process to an internal memory of a hardware accelerator.

The invention belongs to the field of machine learning, and discloses an FPGA (Field Programmable Gate Array) superposition processor acceleration system and method based on state space duality, which comprises a sparse predefined data acquirer, a reconfigurable systolic array, a partial sum cache, an element-by-element operation cache, a function calculation module, an on-chip memory management module and the like. Zero elements are eliminated through the sparse predefined data acquirer, redundant data are reduced, and redundant calculation is remarkably reduced; the reconfigurable systolic array flexibly supports multiple calculation modes, and the utilization rate of hardware resources is increased; the part and the cache realize cross-cycle accumulation and element-by-element operation cache integration results, the function calculation module completes nonlinear operation, and the on-chip memory management module optimizes result cache, so that on-chip operation of SSD calculation is ensured, off-chip memory access is remarkably reduced, and reasoning efficiency and energy efficiency are improved; by adopting the system, the memory occupation is effectively reduced, the element-by-element calculation efficiency is improved, and the sparse calculation redundancy is reduced, so that the reasoning process of the Mamba2 model is remarkably accelerated.

The invention discloses a retraining-free pruning and recombination method for a sparse expert hybrid large model, and belongs to the technical field of large model compression and optimization. The method aims at solving the problems that due to the fact that an existing sparse expert hybrid (SMoE) model needs to load all expert parameters, memory occupation is too high, and deployment is difficult. According to the method, firstly, redundant experts are identified and pruned based on routing activation statistics; then, decomposing the pruned experts into neuron-level functional fragments, and redistributing the fragments to the reserved experts according to structural similarity; and finally, original fragments and newly distributed fragments are merged in the reserved experts through a weighted clustering algorithm, so that compact experts with fewer parameters and stronger expression ability are reconstructed. According to the method, fine-grained operation is carried out at the neuron level, the inherent representation conflict and dislocation problems among experts are effectively solved, the performance of the compressed model is remarkably improved, and reliable technical support is provided for deploying a large-scale SMoE model.

The invention relates to the technical field of three-dimensional models, in particular to a drawing method for making a three-dimensional model based on three-dimensional laser point clouds, which comprises the following steps of: sequentially reading point cloud data files of the three-dimensional laser point clouds, inserting coordinate values of each point into an octree structure, and when octree node buffer areas in a memory are full, drawing a three-dimensional laser point cloud into the octree structure; and writing the node data in the buffer area into a hard disk, and traversing the hard disk octree node set from bottom to top. According to the method, the three-dimensional laser point cloud data is inserted step by step, and the hierarchical aggregated octree structure is utilized, so that the point cloud data processing efficiency is effectively improved, and the memory occupation pressure is reduced; representative points in an octree structure are fused with an average normal to construct a continuous function field, a grid model is adaptively generated in a multi-detail-level mode, and the detail retaining capacity and drawing precision of the model are improved. Furthermore, accurate identification and positioning of topological features are realized by adopting calculation of a cell complex sequence and a topological feature noise rank.

The invention provides a computing power service dynamic resource allocation method and system applied to AI model training. The method comprises the following steps: firstly, collecting real-time computing power resource use data (including computing node load, memory occupation and data transmission delay) and model training state data (including training task stage identification, model parameter updating frequency and training data batch processing progress) in AI model training; generating a computing power resource demand association feature set, constructing a computing power resource dynamic allocation decision model including resource allocation priority judgment, adjustment amplitude calculation and scheduling opportunity selection units based on the set, and outputting a computing power resource allocation scheme (including computing node number, memory capacity and data transmission bandwidth adjustment instructions) through the model. Resources are scheduled according to the scheme, and new data are collected to update the feature set, so that dynamic and accurate allocation of computing power resources is realized, and the resource utilization rate and the training efficiency are improved.

The invention provides a main Monitor service pressure optimization method in a distributed storage cluster, and the method comprises the steps: S1, collecting the load state information of each Monitor node in real time through a monitoring module, and enabling the load state information to comprise the CPU utilization rate, the memory occupancy rate and the network bandwidth occupancy rate; s2, a load balancing module calculates the load weight of each Monitor node based on the load state information, and dynamically adjusts a message distribution strategy according to the load weight; s3, the multi-stage message distribution module distributes the state updating message to a plurality of Monitor nodes for parallel processing according to the message distribution strategy; and S4, the state synchronization module maintains the state consistency among the Monitor nodes through a consistency protocol, and regularly verifies the data version of each node. According to the main Monitor service pressure optimization method in the distributed storage cluster provided by the embodiment of the invention, the load pressure of the main Monitor node in the distributed storage upgrading process is effectively reduced, and the system message processing efficiency and stability are improved.

The embodiment of the invention discloses an agent arrangement method and device, a storage medium and terminal equipment, and relates to the field of agent editing. According to the method, the intelligent agent nodes with the same function are merged into the fused intelligent agent nodes, so that the complexity of the intelligent agent flow chart is remarkably simplified. The flow chart is clearer and easier to understand, unnecessary nodes and connecting lines are reduced, and the readability and maintainability of the flow are improved. Due to the fact that the agent nodes are combined, the user does not need to process too many details when editing and managing the agent process, the operation complexity can be reduced, and the user can complete design and adjustment of the process more quickly and more accurately. Occupancy of system resources can also be reduced by combining the agent nodes. And during operation, the fusion agent node can be processed as a whole, so that the calculation overhead and the memory occupation are reduced, and the overall performance of the system is improved.

The invention provides a computing resource scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps that a computing task request issued by a user is received, and the computing task request comprises a computing unit mask parameter; a scheduling instruction is generated according to the calculation task request, the scheduling instruction is sent to a command processing module, and the scheduling instruction comprises the calculation unit mask parameters; and analyzing the calculation unit mask parameter in the scheduling instruction by a command processing module, and distributing a calculation task to a target calculation unit set according to an analysis result. According to the method and the device, static binding of masks and task flows / queues in a traditional scheme is replaced by dynamic integration of the mask parameters and the scheduling instructions, the situation that independent task flows / queues are created for each mask combination is avoided, and memory occupation and system management overhead can be remarkably reduced.

The invention discloses a data verification method and device for a redundant disk array, equipment and a medium, and relates to the technical field of data verification, when a data verification value of target data is generated, the target data is firstly divided into a plurality of data blocks, and correspondingly reference data is also divided into one-to-one corresponding reference blocks; then, the unit verification value of each data block is determined by taking the data block as a unit, and the data verification value of the target data is obtained through block-by-block calculation, so that the data verification of the target data is realized according to the data verification value, the memory occupation in the data verification value generation process is reduced, the storage requirement of temporary data is reduced, and the data verification efficiency is improved. The high memory overhead of processing the whole target data at a time is avoided, and the calculation efficiency of the data verification value is improved. The size of the data block can be flexibly adjusted according to requirements, the application range is wide, the flexibility is high, the check and problem positioning of the stored data are facilitated, and the troubleshooting of abnormal conditions such as data damage of the stored data is facilitated.

The invention discloses a large-scale video access and AI reasoning enhancement system and method, belongs to the technical field of video processing, and aims to solve the technical problem of how to realize large-scale video stream efficient access, resource elastic scheduling and abnormity self-healing in a complex environment. Comprising a resource dynamic scheduling module, a decoding and reasoning control module, a resolution dynamic processing module, a multi-stage shared memory transmission module, an exception self-healing and fault-tolerant module and a task parallel execution module, and resource allocation is optimized and calculated by dynamically binding a CPU core and GPU hardware unit isolation; the resolution is dynamically adjusted based on the scene algorithm precision requirement, and invalid calculation is reduced; a stream pushing and frame rate decoding strategy is controlled by using a Redis mark, and memory occupation is reduced by combining long and short queues; transmission coding and decoding are reduced by adopting a shared memory, and the cross-process interaction efficiency is improved; and task self-healing is realized through dual anomaly detection and process-level heartbeat monitoring.

The invention relates to the technical field of big data, and discloses a massive small file reading optimization method, system and device and a medium, and the method comprises the following steps: scanning small files in a distributed file system by using a Spark calculation engine to obtain metadata information of the small files; based on the metadata information, small files are classified, and the small files with the same type and data relevance are classified into one group; the resource states of cluster nodes are monitored in real time, the resource states comprise the processor utilization rate, the memory occupancy rate and the I / O load, the load score of each node is calculated, and small file task quotas are dynamically allocated; executing small file merging operation in parallel by utilizing a Spark memory calculation engine to generate a merged file containing a plurality of original small files; creating and maintaining index information in an external database, and recording the position and attribute of each original small file in the combined file; and providing a read-write interface through the special service layer, and positioning and accessing specific small file contents in the combined file.

The invention discloses a GPGPU (General Purpose Graphics Processing Unit)-based singular value decomposition acceleration method and equipment, belongs to the technical field of computer technologies, and is used for solving the problems that when an SVD (Singular Value Decomposition) technology is applied to hardware, a relatively large calculation amount and a large amount of memory occupation can be caused, and different index strategies influence the parallel operation efficiency of the hardware, so that the hardware performance is poor. And the overall performance of hardware is reduced. The method comprises the steps of obtaining an index sequence of a to-be-decomposed matrix; generating a plurality of groups of index sequence pairs based on the index sequence; sending a kernel function kernel to the GPGPU, and traversing each group of index sequence pairs through each block in the kernel function kernel; decomposing matrix data corresponding to the first group of index sequences in the to-be-decomposed matrix through the queue in each block to obtain a first decomposed matrix; and decomposing matrix data corresponding to the second group of index sequences in the first decomposition matrix to obtain a second decomposition matrix, and so on until the last group of decomposition matrix is obtained, thereby obtaining a singular value decomposition result.

The invention provides a display device and a sequence animation playing method, and the method can respond to a sequence animation playing instruction, obtain an updating period of a sequence animation, read a target bitmap object from a bitmap set associated with the sequence animation according to the updating period, and update an image frame displayed by an animation view according to the target bitmap object. Wherein the sequence animation comprises a plurality of continuous image frames, the bitmap set comprises a plurality of bitmap objects, the bitmap objects are used for representing the image frames of the sequence animation loaded into the running memory from the memory in advance, and the bitmap set is periodically reset according to the sequence animation stored in the memory; the target bitmap object is used for representing an image frame to be displayed by the animation view in the current updating period. According to the method, the bitmap set in the memory can be periodically loaded, the occupation optimization of the memory is realized, and the problem that the occupation of the memory is continuously increased when the sequence animation is played is solved.

The invention provides a micro-service isolation operation method, medium and system for a productivity middle platform, belongs to the technical field of electric digital data processing, and provides the micro-service isolation operation method for the productivity middle platform, which realizes accurate scheduling of micro-service resources through multi-dimensional dynamic analysis. The method comprises the following steps: firstly, acquiring micro-service operation indexes including a processor occupancy rate, a memory occupancy rate, network throughput and the like, and generating a micro-service priority index; carrying out decomposition operation on the operation indexes, and constructing a reference and dynamic resource matrix; further calculating instantaneous and persistent competition indexes, and establishing a micro-service calling atlas; determining a resource allocation scheme by constructing a resource allocation equation set; determining a resource use threshold value by adopting an optimized dichotomy algorithm; and finally, the load of the resource unit is monitored in real time, when the load exceeds a threshold value, the migration cost is calculated, and the micro-service isolation operation is executed, so that the technical problem that a micro-service resource allocation and isolation mechanism cannot be accurately and dynamically adjusted in the prior art is solved.

The invention relates to the technical field of data processing, and provides a deep learning inference engine tensor optimization method and system for GPU acceleration. Performing asymmetric quantization on the first weight tensor of the original model to generate a second weight tensor, and updating the original model based on the second weight tensor to obtain an updated model; blocking the data tensor according to a preset dimension to generate input sub-blocks, and loading the input sub-blocks and a convolution kernel in the update model to a shared memory; calling the input sub-blocks from the shared memory, and processing the input sub-blocks of different batches in parallel based on a single kernel function formed by convolution kernels to generate a processing result; and based on the GPU utilization rate and the request queue length corresponding to the to-be-processed data, performing dynamic output adjustment to output a processing result. The performance and efficiency of a deep learning inference engine are improved, memory occupation and calculation delay are reduced, and powerful support is provided for deep learning application of GPU acceleration.

A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights. A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism. The application of structured sparsity lowers the span of search options and creates a relatively loose coupling between the data and control planes.

The invention provides a super-large-scale high-expandability grid generation method and device and a storage medium, and the method comprises the steps: obtaining a geometric model of a numerical simulation task, carrying out the surface grid division, obtaining a corresponding overall surface grid connected domain, carrying out the segmentation of the overall surface grid connected domain, obtaining a plurality of sub connected domains corresponding to the geometric model, and carrying out the segmentation of the sub connected domains; the method comprises the following steps: acquiring a plurality of sub-connected domains, distributing each sub-connected domain to each node, enabling each node to carry out volume mesh division on the sub-connected domains to obtain a mesh data file, searching other connecting surfaces corresponding to the connecting surfaces in the sub-connected domains, and finally updating mesh information in the mesh data file of each node according to a corresponding relationship among the connecting surfaces. And each node writes the updated grid information into the grid model file of the geometric model in parallel, so that the generation of the grid model for numerical simulation is realized, the memory occupation of each node during grid generation is reduced, the grid generation stability is ensured, and the file writing efficiency is greatly improved.

The embodiment of the invention provides an embedded AI power grid waveform dynamic bit width adaptive preprocessing method and system and a medium, and the method comprises the steps: obtaining the real-time sampling data of voltage and current, and analyzing the sampling precision of the real-time sampling data; setting a sampling precision threshold, and judging whether the sampling precision is greater than the sampling precision threshold; if the sampling precision is greater than the sampling precision threshold value, performing Q-format fixed-point number conversion on the real-time sampling data, and performing normalization processing on the real-time sampling data after the Q-format fixed-point number conversion; if the real-time sampling data is smaller than or equal to the real-time sampling data, converting the real-time sampling data into normalization by adopting an LUT table look-up method; normalized sampling data is input into a quantitative model, data bit width is output, a bit width adjustment strategy is generated based on a set bit width threshold value, the data bit width is dynamically adjusted, the data preprocessing efficiency is improved through Q format fixed-point and LUT lookup methods, memory occupation is reduced, and self-adaptive preprocessing can be conducted according to collected signals of different bit widths.

The invention relates to the technical field of intelligent terminals, in particular to an intelligent screen multi-terminal collaborative interaction system and method based on edge computing. The intelligent screen multi-terminal collaborative interaction system based on edge calculation comprises a terminal display unit, an edge calculation unit and an intelligent screen display unit, according to the method, feature information is extracted by integrating multiple factors, terminal display requirements and importance are accurately reflected, important information is judged according to priority permission levels, judgment is performed according to the feature information when the levels are the same or no level exists, the result is more reasonable, random or average distribution display is avoided, meanwhile, the memory occupancy rate of the smart screen is monitored in real time, and the user experience is improved. In addition, the historical information features are continuously updated, and the intelligence and adaptability of the whole system are improved.

The invention provides a multi-modal data active recommendation method based on cross-modal dynamic fusion and equipment resource perception. The method is applied to the technical field of data processing. The method comprises the following steps: acquiring multi-modal data through a smart home device end; performing modal feature extraction on the multi-modal data to generate a voice feature matrix, an environment probability matrix and an equipment state vector matrix; adopting a cross-modal dynamic fusion algorithm, combining time dimension and space dimension weights, and carrying out adaptive weighted fusion on the voice feature matrix, the environment probability matrix and the equipment state vector matrix; the CPU load and the memory occupancy rate of the central control equipment are detected in real time through the equipment resource monitoring module, and a data calculation strategy is dynamically adjusted; and based on the fused multi-modal feature matrix, generating an active recommendation instruction through user portrait modeling and knowledge graph association, and driving the smart home device to execute adaptive adjustment. In this way, the recommendation efficiency can be improved.

The invention relates to the technical field of page rendering, and discloses a page rendering method and device, terminal equipment and a readable storage medium. According to the page rendering method, page structure information of a to-be-rendered page is subjected to blocking processing, and an initial data block set is obtained; carrying out lazy loading processing on the initial data block set to obtain a target data block set; performing parameter analysis on the target data block set to generate structured rendering data; performing paging decision according to the structured rendering data to obtain page paging information; constructing a page rendering instruction set according to the page paging information; and performing drawing processing based on the page rendering instruction set to generate a visual page rendering result. According to the page rendering method, the page rendering efficiency and the cross-page typesetting accuracy are improved while the memory occupation is effectively reduced.

The invention provides a multi-player voice game performance optimization method and device based on dynamic resource management. The method comprises the following steps: acquiring a core source code of a game voice tool and pre-compiling the core source code to generate a byte code file; analyzing a target scene demand and pre-loading a related resource file; performing real-time acquisition and analysis on memory occupation and CPU load to obtain performance state data of the current system; based on the performance state data, when it is detected that memory occupation and / or CPU load exceed a preset threshold value, a pre-compiling mode and a resource loading strategy are automatically adjusted; when it is detected that the multi-person voice function is started, resources and byte codes needed by voice processing are placed in a high-priority queue, and cooperative scheduling is carried out on memory occupation and / or CPU loads. According to the method, the loading delay can be reduced, the frame rate can be improved, the communication delay can be reduced, and real-time voice processing and high-load requirements of games can be dynamically considered.

The embodiment of the invention discloses a translation model training method, an information translation method, an information translation system and a related product. The training method comprises the following steps: performing low-rank decomposition on an original matrix to obtain an initial low-rank matrix; performing iterative training on the initial low-rank matrix by using each source language text and each target language text to obtain a new low-rank matrix different from the initial low-rank matrix; and updating partial model parameters of the large language model by using the new low-rank matrix to generate a translation model for translating the to-be-translated text. The initial low-rank matrix is introduced to approximately simulate all parameters of the large language model, the number of parameters needing to be trained can be reduced, the calculation complexity and memory occupation in the training process can be reduced, the cost is reduced, meanwhile, the large language model can be efficiently and finely adjusted, and therefore the translation model which can be specially suitable for translation tasks is generated; and the manual workload and translation time are reduced.

The invention relates to the technical field of Web-end 3D model rendering, in particular to a web-end large-scale model performance optimization method, which remarkably improves the rendering efficiency and user experience of a Web-end 3D model through multiple technical means of WebWorker multi-process rendering optimization, dynamic data source optimization and cross-level geometric merging optimization, and improves the rendering efficiency and user experience of the Web-end 3D model through WebWorker multi-process rendering optimization. A resource request and a data analysis task are migrated to a background thread, a branch port parallel request technology is utilized to avoid blockage of a main thread and ensure fluency and responsiveness of a user interface, cross-level geometric combination optimization combines model components based on spatial proximity to generate a single Buffer Geometry, the number of drawing calling times is reduced, memory occupation is reduced, and the drawing efficiency is improved. And meanwhile, necessary model definition is kept.