1411 results about "Data allocation" patented technology

The invention relates to the field of business data distribution, financial science and technology and medical health, and discloses a multi-agent cooperative task execution method, which comprises the following steps: receiving a task instruction input by a user, and carrying out task step configuration on the task instruction to obtain a sub-task sequence; judging whether the task information of each subtask meets a preset execution logic standard, and if yes, sending the subtask to an intelligent agent according to an identifier of the intelligent agent corresponding to the subtask; and recording task data generated when each agent executes the subtask, extracting a second keyword in the task data to construct a decision-making dependency relationship graph among the agents, extracting collaborative data of each agent collaborative completion task instruction from the decision-making dependency relationship graph, and optimizing subsequent task allocation by utilizing the collaborative data. According to the method, the cooperation process among the agents is optimized, and continuous learning and improvement are carried out, so that the overall efficiency and reliability of the multiple agents are improved.

The invention discloses a Transform large model training method based on cloud edge collaboration. The method comprises the following steps: S1, constructing a data set; s2, preprocessing the data set; s3, segmenting the preprocessed data set by using a data parallelism strategy, and performing distributed training by combining data parallelism and model parallelism technologies; s4, monitoring computing resources and network conditions of the edge equipment and the cloud server in real time, dynamically adjusting a data distribution strategy, and optimizing computing load distribution; s5, a multi-agent dominant actor-commentator algorithm is combined with a multi-arm tiger machine strategy, and the layered structure of the Transform model is adjusted in real time; s6, performing partial model reasoning tasks on the edge equipment in combination with the edge reasoning capability; s7, protecting data privacy by adopting a federal learning strategy and utilizing a differential privacy technology; and S8, performing hardware acceleration by utilizing heterogeneous computing resources. According to the method, a cloud edge cooperative computing and intelligent scheduling method is adopted, and large model training and reasoning with efficient privacy protection are realized.

The invention discloses a big data dynamic allocation and optimal scheduling method based on reinforcement learning. The method comprises the following steps: S1, constructing a real-time operation data set; s2, preprocessing the real-time operation data set, and constructing a reinforcement learning environment model; s3, initializing a hierarchical reinforcement learning model; s4, generating an optimal data distribution and scheduling strategy based on the hierarchical reinforcement learning model; s5, adjusting data distribution and task scheduling of each computing node in real time to balance the system load and maximize the resource utilization rate; s6, the hierarchical reinforcement learning model continuously monitors the system state and dynamically updates the strategy, and self-adaptive adjustment is carried out on resource allocation and scheduling in time when the system load or environment changes; and S7, through multi-round iterative optimization, gradually converging the hierarchical reinforcement learning model to an optimal strategy. Through application of reinforcement learning, automatic optimization of resource allocation and scheduling strategies is realized, and the resource utilization rate, the scheduling efficiency and the adaptability of the system are remarkably improved.

The invention discloses a video transmission method and system based on streaming processing, and relates to the technical field of video transmission, and the method comprises the steps: collecting a video stream, carrying out the preprocessing, extracting a video frame, packaging the video frame into a picture stream, carrying out the data fragmentation, distributing an initialization path for fragmented data, and calculating an initial traffic proportion; and optimizing path selection and adjusting path flow distribution according to network feedback to obtain a path optimization result, and transmitting the fragmented data according to the path optimization result. Through multi-level feature extraction and key frame selection of video frames, fragmented packaging of video data is realized, a dynamic path optimization technology is combined, path selection and flow distribution are dynamically adjusted based on a Q learning algorithm and a luminescence firefly algorithm, the transmission efficiency is improved, video image processing and a dynamic network optimization technology are fully combined, and the video image processing efficiency is improved. And a brand new solution is provided for efficient and stable transmission of high-definition video streams.

The invention belongs to the field of image data processing, and relates to an improved YOLOv10-based PCB surface defect detection system and method, the system is obtained by improving a YOLOv10 network model, a C2f module in a backbone network of the model is replaced by a multi-scale cross-stage fusion module, and the multi-scale cross-stage fusion module is used for extracting deep features of an image and capturing multi-scale information in input data; a dynamic perception feature information enhancement module is introduced into the neck network and applied to processing of P4 and P5 feature maps; a detection head of a YOLOv10 network model is replaced by a Lag module, the Lag module carries out channel adjustment through a grouping normalization convolution module and then passes through a shared convolution group, and data output by the shared convolution group is distributed to a positioning convolution module and a classification convolution module. The system can realize the detection of small defects under the interference of complex background noise, and has the advantages of high detection precision and efficiency and the like.

The invention relates to the field of resource scheduling, in particular to a cloud-side collaborative computing power dynamic distribution system, which comprises a task management module, a cloud-side collaborative computing power dynamic distribution module, a cloud-side collaborative computing power dynamic distribution module and a cloud-side collaborative computing power dynamic distribution module, the edge information management module is used for collecting information of edge equipment at an edge end and collecting calculation basic information and resource utilization rate of the edge equipment by issuing a calculation power test standard task; the computing power collaboration module is used for acquiring data of the edge information management module and distributing the tasks to the corresponding edge ends according to the computing power requirements of the tasks and the residual available computing power of the edge devices; the calculation feedback module is used for acquiring the isomerism and task calculation type of the edge equipment through the cloud edge communication module; the parameter dynamic optimization module sets a weight coefficient according to the heterogeneity of the edge end and the task calculation type, and the cloud edge collaborative computing power dynamic distribution system flexibly, efficiently and reliably carries out data distribution and optimizes a cloud edge collaborative scheduling distribution strategy.

The invention discloses a virtual power plant energy scheduling method and system under a local data abnormal condition, and the method comprises the steps: recognizing a data type and an incidence relation related to abnormal data through an incidence matrix after the abnormal data of a virtual power plant are collected and recognized; and calculating an abnormal data correction value based on the association relationship function and the real-time association data, and performing weighted average on the abnormal data correction value and the original abnormal data to obtain correction data. And then calculating an abnormal data time difference and a correlation deviation degree, and distributing a credibility weight for the corrected data. And finally, calculating the correlation degree between the scheduling parameter of the preset scheduling scheme and the weighted correction value, and selecting the scheme with the highest correlation degree as a virtual power plant resource scheduling scheme. By implementing the technical scheme provided by the invention, the scheduling accuracy in a data exception state is improved.

The invention provides an anomaly detection method and device based on adaptive multi-scale feature modeling, and relates to the technical field of data anomaly detection. The method combines time component decomposition and a gating network, and allocates suitable expert networks for data on different time scales. In an expert layer, a deep convolutional network and a cross-time-slice attention mechanism are utilized to mine mutual relations in different time periods and among the different time periods in a time sequence. Then, combining a graph structure, and modeling spatial interaction characteristics among variables; and finally, learning the potential representation of the data to generate reconstruction data, and calculating a reconstruction error and the KL divergence of a potential space to carry out model training, thereby carrying out efficient anomaly detection under an unsupervised condition. According to the method, the precision of anomaly detection in the industrial control system is improved, a more flexible and accurate anomaly detection tool is provided for practical application, and the method adapts to complex dynamic changes of time sequence data in the industrial control system under the condition that no label data exists.

The invention discloses an advertisement budget distribution method and system based on machine learning and user behaviors, and the method comprises the following steps: collecting the historical behavior data of a user, and extracting the feature data of the historical behavior data through feature engineering; constructing a user probability prediction model, and training the model by using the feature data; in an advertisement putting process, collecting real-time behavior data of a user, inputting the real-time behavior data into the trained model, and predicting an advertisement clicking probability of the user and an advertisement commodity purchasing probability of the user; a fusion model is constructed, the fusion model calculates the conversion rate of the user according to the advertisement clicking probability of the user and the advertisement commodity purchasing probability of the user, and calculates the channel conversion rate according to the putting channel; distributing a preliminary advertisement budget according to the historical data of the putting channel; and dynamically adjusting the preliminary advertisement budget of the putting channel based on the channel conversion rate. According to the invention, precise distribution of the advertisement budget can be realized, and the overall conversion effect of the advertisement is improved.

The invention relates to the technical field of information security, in particular to a computing method and system for information security. The method comprises the following steps of: partitioning and fragmenting input data, and distributing the data to a plurality of storage nodes through randomization, distributed storage and Hash mapping to ensure the safety of data storage and the distribution flexibility; establishing an index table for all the fragments; regularly triggering a data confusion mechanism, and adjusting the storage position of data fragments through a pseudo-random function; the integrity of the data is detected by generating a check code and an erasure code, it is ensured that the data is not tampered or damaged in the transmission or storage process, and the data is recovered through a redundant copy when the data is lost; the identity verification and the data integrity when the user accesses the data are ensured through authority authentication; and monitoring storage nodes and data access behaviors in real time, detecting potential threats and taking dynamic adjustment measures. According to the invention, through a multi-level security policy, the security and fault-tolerant capability of data processing are effectively improved.

The invention provides an open set cross-domain hyperspectral classification method and system based on multi-mode and optimal transmission, and relates to the technical field of hyperspectral image classification. The method specifically comprises the following steps: acquiring and utilizing an original hyperspectral image to construct a labeled source domain data set and an unlabeled target domain data set; utilizing a spatial-spectral feature extractor to respectively obtain spatial-spectral features of the source domain data and spatial-spectral features of the target domain data; and determining a source domain prototype, calculating a similarity matrix between the target domain data and the source domain prototype, solving an optimal transmission matching matrix, distributing a pseudo tag for each target domain data, and performing text correction on all the source domain data and all the target domain data by using a contrast learning loss function to obtain the target domain data. And the source domain prototype and the spatial spectrum feature extractor are optimized by constructing the total loss of minimizing hyperspectral image classification, so that classification prediction can be carried out on the hyperspectral image to be classified, and target domain data can be classified more accurately.

The invention relates to a self-adaptive partition circulation storage method and device suitable for a flash memory, and the method comprises the steps: obtaining an equipment parameter set and partition rule information of flash memory equipment, carrying out logic partition division on the equipment parameter set based on the partition rule information, and obtaining corresponding initial partition configuration information; obtaining a type identifier of the write-in data and cache mapping data, and carrying out association processing on the type identifier and the cache mapping data to obtain a corresponding target storage partition; performing storage planning analysis on the target storage partition and the target write-in block position according to a preset one-time programming perception data distribution algorithm to obtain a corresponding initial partition adjustment scheme; and performing comprehensive processing on the initial partition adjustment scheme and the dynamic partition information according to a preset Dynamic-FTL algorithm to obtain a corresponding global storage optimization strategy. According to the invention, the storage management strategy can be flexibly adjusted according to the characteristics and demand changes of different data.

The invention relates to a matrix storage operator optimization method and device, computer equipment and a readable storage medium. The method comprises the following steps: allocating memory resources for target data; determining a logic structure corresponding to the source data, establishing a first mapping relation between each logic index in the logic structure and a register address of the source data, and establishing a second mapping relation between each logic index in the logic structure and a memory address of the target data; and determining a corresponding relationship between a memory address of the target data and a register address of the source data based on the first mapping relationship and the second mapping relationship, and storing the source data stored in a register into a memory resource corresponding to the target data based on the corresponding relationship. By adopting the method, the generalization ability of the matrix storage operator can be improved.

The invention relates to the technical field of inventory management, in particular to an intelligent warehouse management system for main shaft parts based on digital twinning, which comprises a main shaft mapping module for acquiring a main shaft shipping space and an allocation path, comparing shipping space nodes with a moving timestamp difference to generate an identification result, the fluctuation identification module extracts channel nodes to analyze fluctuation threshold deviation and generate a report, the allocation control module generates a scheduling list based on queuing duration and shipping space data distribution weight, and the abnormity positioning module extracts unallocated parts to analyze interface difference and mark abnormal links. And the state early warning module integrates four indexes of abnormal data identification risk paths to generate a management scheme. According to the method, bin position nodes and main shaft movement timestamps are synchronously compared to identify difference nodes, a dynamic weight distribution mechanism is established in combination with channel node fluctuation analysis, an interruption link difference trend and interface delay data are integrated to construct a risk assessment model, and abnormal conduction path positioning and early warning are realized. And scheduling conflicts and resource waste caused by data deviation are reduced.

The invention relates to the technical field of block chains, and discloses a block chain node fault recovery method and a block chain system.The block chain node fault recovery method comprises the following steps that S1, the fault state of a block chain node is detected through a fault detection and notification module, whether a target node needs to be recovered or not is judged, and a recovery request is broadcasted; s2, through a recovery strategy generation module, generating initial probability distribution based on the recovery demand of the target node and the bandwidth and load state of the normal node, and determining a data distribution strategy of the normal node; and S3, according to the response state of the normal node, the probability distribution is adjusted through a dynamic adjustment and optimization module. According to the method, the problems of low node fault recovery efficiency, non-uniform task distribution, poor transmission reliability and long verification time consumption in the prior art are solved by dynamically adjusting probability distribution optimization, data blocking and multi-path parallel transmission, redundant coding combined consistency verification and a hierarchical priority strategy; and the efficiency and adaptability of data recovery are greatly improved.

The invention relates to the technical field of hierarchical storage, in particular to a photo-electromagnetic storage method and system based on hierarchical management, and the method comprises the following steps: collecting read-write speed, error rate, durability and cost data of optical storage and electromagnetic storage media, carrying out the sorting and grading processing of the data according to the read-write speed and the error rate, and carrying out the sorting and grading processing of the data; and performing score calculation on each storage medium to obtain a medium performance score. According to the method and the device, the data is effectively distributed to the most suitable storage medium by accurately scoring the performance of the storage medium and combining specific requirements of the to-be-stored data, so that the data access speed and efficiency are improved, the total storage cost is reduced, and particularly, when a large amount of data is processed, the data compression level and the encoding format are dynamically adjusted, and the data compression efficiency is improved. The storage efficiency of the data is further optimized, data redundancy is reduced, the overall performance of data storage and access is remarkably improved through optimization measures, and meanwhile long-term safety and integrity of the data are ensured.

The invention provides an annotation data quality evaluation method based on active learning, and relates to the technical field of data collection, and the method comprises the steps: obtaining historical annotation data and historical use scores, screening the historical annotation data according to the historical use scores, obtaining high-quality annotation data, and constructing an annotation quality evaluation model, analyzing the annotation data type that the annotation person is good at, distributing the unannotated task data to the annotation person to obtain a real-time annotation data set, inputting the real-time annotation data set into an annotation quality evaluation model to obtain a first quality score, performing interactive verification on the real-time annotation data set to obtain a second quality score, and obtaining a deviation value through comparison. When the deviation value is smaller than a preset threshold value, the annotation quality evaluation model is preliminarily adjusted, and after the use score of the real-time annotation data set is received, the annotation quality evaluation model is secondarily adjusted; the quality evaluation method can be improved.

The invention relates to the technical field of distributed storage, and particularly discloses a distributed storage data self-adaptive load balancing method and system, and the method comprises the steps: distributing data to each node in distributed storage based on a consistent Hash algorithm; key index values of all the nodes are collected in real time, whether the key index values of all the nodes exceed a first set threshold value or not is judged, or whether the response time efficiency of key data obtaining exceeds a second set threshold value or not is judged; if yes, evaluating and sorting the performance of each node in the distributed storage based on an entropy weight method and TOPSIS to obtain a sorting result; positioning nodes with better performance based on a sorting result; migrating the data or the key data under the nodes of which the key index values exceed a first set threshold value to the nodes with better performance; according to the method, intelligent migration of the data to the low-load node is realized, so that the problem of non-uniform data distribution is effectively improved, and the overall performance and reliability of the system are improved.

The invention relates to the technical field of data processing and communication, in particular to a multi-source heterogeneous data compression and transmission method and system for an intelligent fusion terminal, and the method comprises the steps: collecting multi-source heterogeneous data from different data sources through the intelligent fusion terminal, carrying out the data preprocessing of the collected multi-source heterogeneous data, and obtaining a data preprocessing result; comprising format unification and noise filtering; establishing a data feature analysis model, and performing feature extraction and classification on the preprocessed data; according to data feature extraction and classification results, dynamic weights are allocated to different types of data, and the data are divided into data blocks of different sizes according to the allocated dynamic weights and data features; for different types of data blocks, the priority of the data blocks is set, a proper compression algorithm is selected for compression, and the compressed data is transmitted through a network. The multi-source heterogeneous data is subjected to feature analysis and targeted compression processing, so that network bandwidth occupation and equipment energy consumption are reduced, and data transmission efficiency is improved.

The invention discloses an inference service deployment method, electronic equipment and a storage medium, and the method comprises the steps: responding to the creation of an inference service, reading a model information configuration table and an engine information configuration table, and carrying out the matching processing of the model information configuration table and the engine information table according to a pre-configured model name during the creation of the inference service, processing resources, inference engine mirror image identifiers and inference engine starting parameters which can be used for loading inference services on the container scheduling platform are obtained, and workload metadata used for bearing the inference services are created based on the processing resources, the inference engine mirror image identifiers and the inference engine starting parameters; the deployment of the inference service on the container scheduling platform is realized by distributing the workload metadata to the target cluster node. Through the method, the technical problem of relatively low deployment efficiency caused by manually configuring the parameters in the workload metadata depending on manpower in related technologies is solved, and the technical effects of simplifying the deployment process of the model reasoning service and improving the deployment efficiency are achieved.

The invention relates to the technical field of direct current motor servo drive control, and provides a Zynq AXI4 bus-based real-time transmission system and a control method thereof, and the system comprises a Zynq system on chip, a DDR3 common data area, an AXI4 bus interconnection architecture and a dynamic partition manager. By implementing the scheme, firstly, the multi-channel characteristic of the AXI4 bus is utilized, special transmission channels are distributed for different types of data, and parallel data interaction is realized; secondly, a dynamic partition manager is deployed at a PL end, a DDR3 public data area is dynamically divided into a plurality of partitions in real time according to needs, multi-task parallel is achieved, and the real-time performance of the system is improved; thirdly, the read-write operation on the DDR3 in each control period is split into a plurality of state machines through precise scheduling of the state machines, the state machines are combined into a state loop to be mounted to an AXI4 bus, it is ensured that key tasks are completed on time, and the certainty of the system is improved; fourthly, the size and the number of partitions in the DDR3 are dynamically adjusted through a dynamic partition manager, and the storage efficiency is improved.

The invention relates to the field of photovoltaic power generation, and discloses a link fusion method and system for a photovoltaic power station, and an intelligent system. The method comprises the steps of collecting original data of an intelligent system of a photovoltaic power station, and dividing the original data of the intelligent system into multiple classes; and assigning priorities to the multiple types of data, wherein each priority corresponds to a respective transmission data level. All communication link conditions at the current moment are evaluated, if the transmission data grade of the to-be-transmitted data is high, the communication link with the good transmission condition is selected, and the to-be-transmitted data is transmitted to an operation and maintenance management center of the photovoltaic power station; and automatically distributing the to-be-transmitted data of other transmission data levels to corresponding communication links for data transmission according to communication link conditions. Based on the method, the data processing efficiency and the operation and maintenance response speed of the photovoltaic power station can be remarkably improved, and meanwhile, the data transmission delay and the error rate caused by communication congestion are reduced.

The invention relates to a data processing method and system of an NAND FLASH storage array, computer equipment and a storage medium. The method comprises the following steps: receiving a data writing or reading instruction; and analyzing the instruction through the system-on-chip, and distributing the data to a target module in the plurality of NAND FLASH modules connected in parallel according to a preset strategy. And writing the data into the target module or reading the data from the target module through the control and communication line. And executing data management operation through the system-on-chip, specifically, writing data into different NAND FLASH modules in a dispersed manner by adopting a dynamic wear leveling algorithm so as to balance the erasing times of each module. And detecting and marking bad blocks in the NAND FLASH module in real time, and avoiding the bad blocks in calling operation after data storage. By the adoption of the method, the storage performance, reliability and expandability of satellite-borne storage can be comprehensively improved, and the method is suitable for task scenes with high reliability requirements.

The invention discloses a cross-chain meteorological and hydrological data consistency verification method oriented to multi-block-chain collaboration, which effectively solves the problem of data alignment caused by inconsistent time standards in a multi-chain environment by collecting multi-source data and generating a data tuple with a geographic identifier and distributing a unified reference timestamp for the data in combination with a physical clock synchronization mechanism. And furthermore, the time deviation is extracted through a layered verification structure and inter-chain cross check, and the timestamp weight is dynamically adjusted, so that the time synchronization precision of the cross-chain data is improved. Finally, a standardized time sequence is generated through segmented aggregation of the data, cross-chain storage is completed, regular backtracking verification is performed in combination with a supervision chain, time consistency and content credibility of the meteorological and hydrological data in the cross-chain circulation process are guaranteed, and efficient collaboration and traceability between heterogeneous block chain systems are achieved.

The invention provides a self-service printing regulation and control method and system for multiple printers, and the method comprises the steps: obtaining the configuration data of each printer when an edge computing device is successfully connected with the multiple printers; obtaining the printer state of the corresponding printer according to the configuration data of each printer; acquiring a printing order sent by a user, and extracting printing file data and printing requirements of the printing order; based on the printing requirement, the configuration data of each printer and the state of the printer, a target printer is allocated for the printing file data, and the printing file data and the printing requirement are sent to the target printer for printing through the edge computing device; and after the printing file data is printed, a printing success message is output, so that multiple printers are reasonably scheduled, the overall failure rate is reduced, and the success rate, the processing efficiency and the resource utilization rate of the printing task are improved.

The invention relates to a super-resolution fluorescence lifetime microscopic imaging method and system based on pixel relocation. The method comprises the following steps: S1, carrying out multi-focus parallel scanning on a sample by using an acousto-optic deflector; s2, synchronously collecting a fluorescence intensity image and fluorescence lifetime data through an area array detector and a point detector; and S3, carrying out super-resolution reconstruction on the fluorescence intensity image based on a pixel relocation algorithm, and mapping fluorescence lifetime data to a reconstructed image to generate a super-resolution fluorescence lifetime microscopic image. According to the invention, an AOD is adopted to replace a scanning galvanometer in a traditional TCSPC-FLIM imaging system as a light beam scanner; addressing scanning of AOD, image acquisition of EMCCD and life data acquisition of PMT and TCSPC cards are closely linked by combining well-designed multiple paths of synchronizing signals, and fluorescence life data are distributed to each dot matrix through a later data processing method, so that organic combination of super-resolution and FLIM can be realized without complicated equipment, and SR-FLIM images of samples are obtained.

The invention relates to an optimization method of a data type conversion operator, computer equipment, a readable storage medium and a computer program product. The method comprises the following steps: allocating memory resources for target data; establishing a read mapping relationship between each logic index in the logic structure of the source data and the memory address of the source data, and establishing a write mapping relationship between each logic index in the logic structure and the memory address of the target data; traversing the logic structure, aiming at any traversed logic index, determining a read address corresponding to the logic index based on the read mapping relationship, performing data reading from the memory resource corresponding to the source data based on the read address, converting the read data element from the first data type to the second data type, and storing the converted data element in the memory resource. And writing the data elements subjected to data type conversion into memory resources corresponding to the target data according to the write mapping relationship. By adopting the method, the calculation capability of the data type conversion operator can be improved.

The invention relates to the technical field of electronic digital data processing, in particular to an operation state monitoring method and system for injection molding equipment, and the method comprises the steps: collecting a multi-dimensional operation parameter time sequence of the injection molding equipment at different moments, collecting parameters of the same dimension into data sets, and constructing an isolated tree based on each data set; after sorting tree nodes of the isolated tree according to a data average value, distributing a tree node sequence number for each item of data; the combination of the dimension parameters at the same moment is regarded as a data point, the distribution relation of any two data points on the isolated tree is compared, the same-group degree of the data points is calculated, and the data points with the same-group degree higher than a set threshold value are classified into the same group; calculating the abnormal degree of the data points; and if the abnormal degree exceeds a set threshold value, determining that the data point is an abnormal data point and giving an alarm at the same time. The problem that the accuracy and reliability of state detection are not high is solved.

The invention relates to a micro-service fault root cause positioning method (Micro) based on a graph convolutional neural network, and the method analyzes the complex dependency relationship between micro-services through the graph convolutional neural network, helps to judge the fault type when a fault occurs, and comprises the steps: firstly, simulating various fault types through a monitoring system, and injecting the fault types into the system; the method comprises the following steps of: classifying and marking measurement data of a simulated fault, and then training based on historical measurement data through a graph convolutional neural network MericSage so as to realize instance-level fault root cause analysis. After a fault occurs, the system collects real-time fault data and service calling data, and constructs a micro-service heterogeneous topology subset through abnormal service calling data. Weights are allocated according to the real-time indicator data, a weighted heterogeneous topology is created, and a personalized random walk algorithm is performed on the weighted heterogeneous topology to generate a root cause candidate set. And finally, inputting the candidate set and the real-time data features into Metri Sage for feature weighted analysis, and determining the final fault root cause and type.

The invention discloses a data processing system and a data processing method of a hybrid cloud in a wireless communication system. The method comprises the steps that wireless communication equipment receives and sends data through a multi-mode communication interface, and a hybrid cloud platform receives the data and distributes the data to a public cloud or a private cloud for processing and storage according to a preset strategy. And then, the data processing module performs real-time cleaning, decoding and analysis to generate a processing result. Based on a deep reinforcement learning algorithm, the network optimization unit optimizes and adjusts communication parameters. And the processing result and the optimization instruction are fed back to the wireless communication equipment through the feedback channel, so that the performance and efficiency of the equipment in the network are improved. The invention further shows the characteristics of guaranteeing data security, a data cleaning mechanism, optimizing strategies, improving the resource utilization rate and the like, and the system efficiency and the data processing efficiency are enhanced.