1928 results about "Batch processing" patented technology

The invention provides an intelligent short message scheduling method and device based on multi-dimensional dynamic optimization, and the method comprises the steps: obtaining the performance data of a plurality of short message channels, and calculating a channel health score based on a weight dynamic adjustment model; determining a scheduling strategy according to the priority identifier of the to-be-sent message, and performing channel screening and optimal matching; executing message sending and monitoring a sending state; terminal state detection is carried out on the failure message through operator base station signaling, and a decision tree model is applied to determine a retry strategy; and performing Huffman coding compression processing on the P2-level marketing messages which fail in retry, and performing batch sending in an idle window. According to the method, a comprehensive performance evaluation index and reward function model is also constructed, and parameter optimization is performed by applying a reinforcement learning algorithm. According to the invention, multi-dimensional dynamic channel scoring, intelligent retry decision making based on terminal state perception, batch processing with balanced cost-time efficiency and a closed-loop self-optimization system are realized, the short message delivery rate is obviously improved, and the invalid retry rate and the sending cost are reduced.

The invention provides an intelligent analysis and execution method and system for database cascading operation, and relates to the technical field of database management.The intelligent analysis and execution method comprises the steps that a target table and an association table are extracted through a recursive query algorithm, field mapping analysis is carried out to generate a dependency weight matrix, cyclic dependency is recognized based on the matrix and decomposed into directed acyclic subgraphs, and the directed acyclic subgraphs are analyzed; node depth values and breadth values are calculated for topological sorting to generate an execution sequence; performing node classification on the execution sequence, organizing the execution sequence into a batch processing task group, calculating an optimal execution path through an adaptive path optimization algorithm, generating a distributed transaction control instruction, and allocating the task group to an execution thread pool for execution by using a consistent Hash algorithm; monitoring an execution process, dynamically adjusting thread pool resources according to a performance prediction value, executing cascade rollback when an exception occurs, and reconstructing a transaction execution path; according to the method, the execution efficiency and stability of the database cascade operation can be effectively improved, and the system resource consumption is reduced.

The present disclosure relates to efficiently receiving and processing input tasks in a way that is scalable and which reduces both the quantity of tokens processed by a foundation model (e.g., an LLM) as well as the number of API calls that are made in processing the input tasks. A system batches a set of inputs to provide as a single batch of input(s) into an LLM. The system generates one or more permutations of the batched input(s) to determine outputs based on variable orders in which the input data is provided within the respective permutations of the batched inputs. The system further may eliminate one or more of the data inputs within the respective batches to facilitate smaller batched inputs without sacrificing accuracy in a set of outputs generated by the LLM responsive to the batch permutations.

An adaptive data system (ADS) for cognitive data processing is disclosed. The ADS includes an adaptive semantic preprocessor, a trigger detector, a temporal batching engine, a symbolic encoder, and a dynamic cognitive transformer engine. The adaptive semantic preprocessor is configured to receive input data from one or more databases and identify cognitive data attributes comprising one or more contextual, semantic, and temporal attributes from the received input data. The trigger detector is configured to identify semantic divergence of the identified cognitive data attributes and provide a standardized data. The temporal batching engine is configured to provide a high-dimensional cognitive data from the standardized data. The symbolic encoder compresses the high-dimensional cognitive data. The dynamic cognitive transformer engine is configured to determine decision making rules, analyze the compressed high-dimensional cognitive data based on the decision making rules and provide recommendations based on an outcome of the analysis to a user.

The invention discloses a communication transmission control cabinet based on big data, and relates to the technical field of communication transmission, and the control cabinet comprises the steps: introducing a real-time network state perception and prediction module, collecting the data of a link through an embedded sensor, carrying out the prediction through combining with an LSTM time sequence model, carrying out the estimation of a future link state, introducing a multipath transmission mechanism, and carrying out the real-time network state perception and prediction. When tasks are distributed, bandwidth, delay and load conditions of paths are synthesized, batch uploading is performed through caching and compression strategies of edge computing nodes, occupation of links is effectively reduced, when link performance is reduced, a path switching mechanism can select alternative paths with optimal performance in real time, influences of link interruption on communication tasks are avoided, and meanwhile, the communication efficiency is improved. According to the high-real-time task priority strategy, an optimal path is adopted, delay of key tasks is reduced, non-real-time tasks are compressed and processed in batches at edge nodes, resources are not competed with real-time tasks, interference is avoided, and the requirements for ship navigation and real-time monitoring tasks are met.

The invention discloses a three-dimensional scene loading and rendering method for deep-sea three-dimensional environment deduction, and relates to the technical field of three-dimensional scene rendering, and the method comprises the following steps: obtaining and preprocessing various types of data of a deep-sea environment, and carrying out the grid processing of terrains and objects in the deep-sea environment; a deep sea three-dimensional scene is established based on the preprocessed deep sea environment data, scene uniform segmentation is carried out, a plurality of sub-scene blocks are obtained, and a block rendering sequence table is obtained; the rendering efficiency of the deep sea three-dimensional scene is remarkably improved by adopting the view cone removing technology and the batch processing rendering strategy, the rendering speed is increased, dependence on hardware resources is reduced, the rendering task can be efficiently completed under the condition that the resources are limited, and in addition, the rendering efficiency of the deep sea three-dimensional scene is improved. The strategy of dynamically adjusting the rendering detail level further balances details and performance, and ensures that the optimal rendering effect can be provided under different observation distances and hardware loads.

The invention discloses a label-based user portrait self-adaptive updating method, a medium and equipment, and solves the problems of poor data timeliness and lagging rule updating in a traditional offline batch processing mode through a collaborative mechanism of real-time stream processing and historical batch processing. A dynamic weight adjustment strategy is adopted, real-time user tags generated by real-time behavior flow data and batch user tags generated by historical behavior batch data analysis are subjected to aging weighted fusion, and dynamic changes of user behavior modes are effectively captured; through feedback behavior data of the user and a closed-loop iteration mechanism of the rule base, self-adaptive evolution of the label rule is realized, and the accuracy and the response speed of a recommendation system are remarkably improved.

The invention relates to the technical field of electric data processing, and discloses a system and a method for hybrid processing of mass offline data and mass real-time data, and the system comprises a queue management module which receives task requests, identifies and marks task types, distributes tasks to a stream processing queue or a batch processing queue, and sorts the tasks according to priorities; the task types comprise flow tasks and batch tasks; the thread pool management module establishes a thread pool, sequentially processes tasks according to priorities and collects real-time parameters; the calculation module is responsible for calculating task priorities and calculating task jitter factors based on real-time parameters; the scheduling decision module compares the task jitter factor with a reference value, determines a weight adjustment coefficient, corrects the priority and formulates a scheduling strategy; the alarm module judges whether to trigger an alarm. According to the invention, by introducing the dynamic priority scheduling and preemptive processing mechanism driven by the jitter factor, the real-time response capability and the resource utilization efficiency of the system are improved.

The invention discloses a big language model reasoning service optimization method, system and device and a medium. The method comprises the steps of obtaining a current reasoning request queue; performing dynamic sorting on each reasoning request in the current reasoning request queue; and performing dynamic batch processing on each reasoning request in the reasoning request queue by using an SLO-BS algorithm to obtain a current batch of reasoning requests, and inputting the current batch of reasoning requests into a large language model, the method, the system, the equipment and the medium can solve the problem of video memory fragmentation occurring during multi-task concurrent reasoning, and reduce the SLO violation rate at the same time.

The invention discloses a rural water supply pipe network pressure monitoring analysis method and device based on digital twinning. The method comprises the following steps: collecting historical basic data of a rural prediction area; flow and pressure sensors are arranged at nodes of a rural water supply network to obtain monitoring data; uploading the data to a server through a data stream processing framework, and preprocessing the data to obtain preprocessed data; constructing a relational database management system to perform batch processing on the preprocessed data to obtain historical basic data and monitoring data after batch processing; constructing a rural pipe network water pressure prediction model; constructing a pipe explosion detection and water pressure control model; according to the physical data, constructing a rural water supply pipe network geometric model based on ArcGIS; and constructing a rural water supply pipe network system data model and realizing visualization of the operation state of the water supply pipe network. Rural water supply characteristics and water consumption characteristics are fully considered, intelligent management and control of the rural water supply system are achieved, and reliability and safety of rural water supply are effectively guaranteed.

The invention discloses a network security information analysis and statistics method based on a regulation and control cloud platform. Protocol identification, standardized mapping and blood relationship marking of multi-source security equipment data are realized through an edge layer protocol adaptation cluster and a metadata self-registration mechanism; constructing a real-time streaming and batch processing dual-channel framework based on regulation and control of cloud platform container resources, and fusing to generate a standardized security event object with a frequency weight and a hazard coefficient; designing a main ring-emergency ring double-path decision closed loop, respectively processing conventional events and high-risk threats, and realizing knowledge base iteration; extracting features by using a containerized architecture in combination with an XGBoost + isolated forest integrated model, detecting threats and generating rules; and a space-time-system-risk four-dimensional visualization engine is constructed, attack path drawing, event evolution display and high-risk area prediction are realized, and a management closed loop is formed. According to the network security information analysis and statistics method based on the regulation and control cloud platform, the intelligence and automation level of network security information analysis and statistics is improved.

The invention provides a cross-border e-commerce big data analysis system and method, and the method comprises the steps: obtaining multi-dimensional original business data of a cross-border e-commerce platform, carrying out the real-time collection through a distributed data collection system, and obtaining a structured business data set; data collected in real time is cleaned, converted and structured, a unified data model is constructed, and integration of heterogeneous data sources is achieved; storing the processed structured data in a time sequence database to provide data support for real-time analysis; performing real-time aggregation and statistical analysis on the newly added data to generate business index and key performance index data; a Lambda framework is adopted, batch processing and stream processing are combined, the historical data and the real-time data are subjected to full-amount analysis, and an analysis result is obtained; based on an analysis result, a data mining algorithm is adopted to identify a service mode and predict a future trend; a multi-dimensional data cube is constructed, multi-dimensional and multi-granularity data exploration and interactive analysis are supported, and management decision making is assisted.

The invention relates to the technical field of data security, in particular to a big data security storage method and system based on cloud computing, and the method comprises the following steps: initializing a cloud service node, selecting data blocks needing security storage, distributing an identifier for each data block, sorting and classifying the data blocks by adopting a batch processing mode, and storing the sorted data blocks into a database; and obtaining an initialized data block. According to the method, the security of the data in the cloud environment is greatly improved through key segmentation and storage of part of keys in a plurality of security cloud service nodes, the decryption rule is constructed by using the threshold cryptography model, the data can be decrypted only when a sufficient number of key parts are collected, unauthorized access and data leakage are effectively prevented, and the security of the data in the cloud environment is improved. The strategy of dynamically adjusting the secret key replacement period adapts to the access frequency and the change dynamic state of the storage data block, and the confidentiality, the integrity and the availability of the data are improved, especially in a sensitive service scene with a large data volume.

The invention relates to the field of heterogeneous computing resource management, in particular to a CPU (Central Processing Unit), GPU (Graphic Processing Unit) and NPU (Network Processing Unit) resource allocation method and system of a training and reckoning all-in-one machine. The invention discloses a CPU, GPU and NPU resource allocation system of a training and reckoning all-in-one machine. The system comprises a schedulable resource analysis module, a load analysis module and a resource allocation module. According to the method, the reference parameters and the real-time dynamic indexes of heterogeneous hardware are fused, so that deep perception and efficient quantification of computing power resources are realized; on the basis of an NPU temperature attenuation experiment, calibrating a computing power loss coefficient, and dynamically correcting available weight values of a CPU, a GPU and an NPU in combination with suitability analysis of a GPU stream processor utilization rate and a task batch processing demand and collaborative efficiency evaluation of a CPU dominant frequency and an IPC value; and the accuracy of resource availability prediction is improved, so that the system can still guarantee the stability of computing power output in complex environments such as high temperature and high concurrency.

The invention provides an intelligent laboratory full-process collaborative management system and method based on multi-dimensional data fusion, and the method comprises the steps: obtaining an original data stream from laboratory instrument equipment, carrying out the format recognition and conversion of heterogeneous instrument data through a standard protocol adapter, and generating a first data set in a unified format; aiming at the first data set, executing automatic analysis by adopting data middleware, and integrating into a structured second data set based on a metadata rule of field mapping and unit conversion; according to the second data set, a multi-source data fusion model is constructed, data are classified according to instrument types through batch processing and aggregated according to timestamps, and a fused third data set is generated; aiming at the initial process configuration, adjusting a node sequence and a parameter threshold value by using a visual design tool, and generating an optimized process configuration adaptive to the diversified scene; according to the optimized process configuration, process scheduling is executed through a dynamic process engine, execution time and resource occupation are monitored in real time, and a process execution log is generated.

The invention discloses an optimization method for a multi-head attention mechanism operator oriented to a domestic heterogeneous processor, which improves the efficiency of the multi-head attention mechanism operator from four aspects, and comprises the following steps of: firstly, combining the general computing power of a CPU (Central Processing Unit) and the advantages of a DSP (Digital Signal Processor) in the aspect of parallel computing; a high-performance multi-head attention mechanism operator operation method on a CPU + DSP heterogeneous processor is constructed; secondly, a previous softmax optimization algorithm is used for fusing the two batch processing matrix multiplication and a softmax operator, so that the memory access overhead of DSP equipment is reduced; then, a vector operation instruction of a DSP calculation core is used in the calculation process of a multi-head attention operator, and SIMD calculation characteristics of DSP equipment are fully utilized; and finally, during data transmission and calculation, a double-flow water mechanism is adopted, the data transmission time is covered, and the multi-head attention mechanism operator calculation efficiency is improved.

The invention discloses an Excel report automatic conversion and rendering method, system, device and medium, and relates to the field of data processing, visualization and document generation, the method comprises the following steps: adopting an intelligent Excel analysis engine to automatically analyze Excel file structure features, and selecting a most suitable analyzer to analyze an Excel file; based on an xlsx library and a data structured conversion mechanism, performing data processing on the analyzed Excel file, and constructing a structured data model; based on a dynamic component of React, constructing different types of visual generation components according to the structured data model, and determining a layout framework; and based on a dynamic component and a structured data model of React, dynamically loading and rendering the visual content in the layout framework by adopting a headless browser technology, configuring browser parameters suitable for generating a PDF format, and displaying a PDF document according to the browser parameters. The method has the advantages of high-flexibility Excel analysis capability, strong data processing capability, rich visual expressive force, high-quality PDF rendering and efficient batch processing capability.

The invention relates to the technical field of artificial intelligence and natural language processing, and discloses a task processing method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the dynamic batch processing of an input text task, and obtaining a conventional batch and an ultra-long batch; detecting a task belonging to an ultra-long batch in the to-be-processed text task as a priority text task, and realizing preemptive scheduling of the current text task by the priority text task through a hardware interrupt mechanism; calculating the priority text task by adopting a local-global mixed attention mechanism; calculating the text tasks belonging to the conventional batch by adopting a first sparse rate, and generating a first historical key value pair; calculating a priority text task by adopting a second sparse rate, and generating a second historical key value pair; and caching the first historical key value pair in a first cache pool, and caching the second historical key value pair in a second cache pool. The method can be applied to the field of financial science and technology businesses, and efficient differentiation processing and computing resource optimization of super-long and conventional text tasks are achieved.

The present disclosure relates to methods and systems based on a transformer model, in which an elastic transformer service system, referred to herein as an online lexical adaptation system (OTAS), is involved that accommodates diversified user requests with fluctuating query loads, while optimizing output accuracy and runtime delay. The OTAS uses lexical adaptation techniques that involve adding cue lexical elements to improve accuracy and removing redundant lexical elements to accelerate reasoning. To handle fluctuating query loads and diversified user requests, the OTAS also applies a perceptual selective batch processing algorithm for online lexical adaptive design. In a system service process, OTAS firstly processes incoming queries with similar requirements in batches to improve ingress throughput. Then, in order to balance between the overhead of lexical element growth and the potential of improving accuracy, OTAS adaptively adjusts lexical element execution settings by solving an optimization problem.

A substrate processing system includes a carry-in / out unit in which a cassette accommodating therein multiple substrates is carried in and out; a batch processing unit configured to process a lot including the multiple substrates at once; a single-wafer processing unit configured to process the substrates one by one; a first interface unit configured to distribute the substrates to the single-wafer processing unit or the batch processing unit; and a second interface unit configured to transfer the substrates between the batch processing unit and the single-wafer processing unit. The first interface unit includes a first placement unit configured to place therein the substrates before and after being processed by the single-wafer processing unit; a second placement unit configured to place therein the substrates before being processed by the batch processing unit; and a transfer device configured to transfer the substrates to the first placement unit and the second placement unit.

The invention belongs to the field of multi-modal RGB-T data fusion, and discloses a distributed streaming multi-modal fusion-oriented adaptive gradient compression optimization method and system, and the method comprises the steps: carrying out the personalized compression of data features of different modals through employing a modal-sensitive gradient compression strategy, and enabling the modals to comprise an RGB modal and an infrared modal; introducing physical constraint time sequence alignment loss, and performing time sequence alignment on the multi-modal data subjected to personalized compression by utilizing a physical model based on a thermal diffusion equation; the dynamic batch processing strategy is sensed through the video memory, the use condition of the video memory is monitored in real time, and the batch processing size is dynamically adjusted according to the residual capacity of the video memory. According to the method, a brand new solution is provided for efficient training of distributed streaming multi-modal data, and the precision of a multi-modal data fusion task and the resource utilization rate are improved.

The invention discloses a rapid marine ship target identification method based on YOLOv8, and is applied to the technical field of target identification. Comprising the following steps of collecting an image sample of a ship navigation water area in a digital vehicle, cleaning and marking the image sample, performing data enhancement on the image sample to obtain a data set which can be used for training and verification, constructing a target identification network model based on a YOLOv8 deep neural network, and obtaining a target identification result by setting hyper-parameters such as a learning rate and a batch processing size. And carrying out transfer learning by using the pre-training model, removing a repeated detection frame by using a non-maximum suppression algorithm and carrying out result filtering by using a confidence coefficient threshold to carry out post-processing on a reasoning result of the model so as to complete prediction of the ship target, and carrying out sparse pruning training on the trained model neural network so as to obtain the ship target. And carrying out calibration and quantification on the pruned model. According to the method, on the premise that the model detection precision is reserved to the maximum, memory consumption during equipment operation is reduced, and meanwhile the model detection speed is increased.

The invention relates to the technical field of personalized recommendation, in particular to a nonlinear enhanced decoupling type contrast hypergraph learning method for next POI recommendation. The method comprises the following steps: S1, constructing a multi-view decoupling hypergraph; s2, optimizing the multi-view decoupling hypergraph constructed in the step A to obtain a nonlinear hypergraph convolutional network; s3, based on self-adaptive fusion of user representation, learning and fusing the user preferences under the multiple views obtained in the step S2; and S4, realizing comparative learning and self-supervised learning based on an Encoder module and a GRACE module. According to the nonlinear enhanced decoupling type contrast hypergraph learning method for the next POI recommendation, by introducing ReLU and residual connection, the linear limitation of a traditional hypergraph layer is broken through, the model is endowed with higher expression ability, a KNN adjacency matrix sparse strategy is adopted, the calculation efficiency is remarkably improved on the premise that the precision is guaranteed, and the method is suitable for popularization and application. And meanwhile, batch processing InfoNCE and GRACE modules are creatively applied, so that robust cross-view collaborative learning on a large-scale data set is realized.

The invention provides a radar track classification method based on a double-layer LSTM model. The radar track classification method is used for classifying radar targets such as unmanned ships, unmanned aerial vehicles and birds in real time. According to the method, in combination with kinematics characteristics of the variable-length radar track, a self-adaptive data preprocessing strategy is adopted, forward filling and backward truncation are carried out on the track, and the effectiveness of characteristic data is ensured through a Masking technology and standardized normalization processing. A double-layer long-short-term memory (LSTM) model is used for time sequence modeling, a mixed attention mechanism is introduced to improve the extraction capability of the model on key track information, abnormal points and non-key track points in data are effectively processed, a batch processing strategy is adopted to improve the real-time performance of the system, and the method is suitable for monitoring unmanned ships and other low-altitude targets.

A personalized diagnostic system for healthcare, comprehensive: a deep learning framework trained on a diverse dataset of medical images to analyze and interpret medical images; a data fusion module that integrates imaging data with non-imaging patient data such as electronic health records (EHRs), genetic information, and biomarker profiles; a high-performance computing system that uses GPUs (Graphics Processing Units) and TPUs (Tensor Processing Units) for real-time and batch processing of medical data; an intuitive user interface that displays diagnostic results, visualizations of medical images, and interactive functions for adjusting diagnostic parameters; a continuous learning mechanism that updates the deep learning models based on new data and expert feedback; a cloud-based platform for managing the continuous learning process, including the storage of anonymized patient data and diagnostic results; an explanatory module that provides detailed explanations of the diagnostic process using techniques such as Grad-CAM (Gradient-weighted Class Activation Mapping) and SHAP (SHapley Additive exPlanations); and a role-based access control (RBAC) mechanism to secure patient data.

The invention discloses a dynamic batch processing method and device for reasoning requests, electronic equipment and a storage medium, relates to the technical field of computers, and aims to learn and obtain an optimal batch processing strategy by utilizing a dynamic batch processing reward algorithm of reinforcement learning, dynamically adjust the batch processing amount of the reasoning requests and improve the efficiency of batch processing of the reasoning requests. The reasoning request processing efficiency and the resource utilization rate are remarkably improved, the training and reasoning progress is accelerated, the resource utilization rate and the reasoning response speed are improved, the real-time performance index is monitored and obtained to dynamically adjust the optimal batch processing strategy in the process that the reasoning node executes the reasoning request, data changes are adapted, and the reasoning efficiency and the reasoning response speed are improved. The method is suitable for reasoning scenes requiring high throughput, low delay and high resource utilization rate, so that the technical problem of low resource utilization rate or response delay increase caused by static batch processing in the face of request quantity fluctuation or data distribution change can be solved, and resource management and scheduling are more efficient and unified.

According to the model lightweight deployment method and device based on the hardware performance of the end system, parameters such as the maximum computing power and the batch processing amount are obtained through a static hardware performance evaluation query database, and the actual computing power and the memory are calculated in real time through dynamic operation state monitoring to serve as compression targets; when the hardware resource change exceeds a threshold value, light weight is triggered, and dynamic adjustment of a compression strategy is achieved; in the lightweight process, hardware parameters and model features are fused into a low-dimensional state vector, collaborative compression parameters of a reinforcement learning strategy network output pruning rate, quantization bit width and distillation temperature are input, and finally a lightweight model adaptive to the hardware dynamic environment is generated. The automatic compression process reduces the labor cost, ensures that the lightweight model is accurately matched with the end side hardware constraint, improves the reasoning speed and reduces the energy consumption.

The invention discloses an urban traffic intelligent management method based on multi-source data, and relates to the technical field of traffic data management, and the method comprises the steps: collecting multi-source traffic data, firstly carrying out the preprocessing, then carrying out the matching and integration, and building a unified traffic data warehouse; carrying out batch processing and stream processing on warehouse data by applying a distributed computing framework and a stream processing technology; on the basis of multi-source data, various traffic models are constructed and optimized, and a visual tool is developed to visually display an analysis result; by combining real-time traffic data, a model prediction result and historical data, traffic signals are dynamically adjusted, route planning and navigation services are provided for users, and routes and scheduling of public traffic are optimized; a traffic monitoring center is constructed, and real-time monitoring and timely early warning are carried out based on the traffic signal dynamic adjustment result and the real-time traffic data; establishing an emergency plan; and establishing a data sharing platform, and sharing the related traffic data. The system is used for monitoring, analyzing, managing and applying the traffic data.

The invention discloses a hierarchical dynamic scheduling method based on a strategy optimization DDQN algorithm, which is used for solving a dynamic scheduling problem of a reentrant hybrid flow shop with a batch processor, and comprises the following steps: firstly, determining an objective function and a constraint condition of the scheduling problem; secondly, by introducing a self-attention mechanism, providing a layered structure based on the self-attention mechanism DDQN, and constructing two agents, namely a batching agent and a scheduling agent, to respectively solve batching sub-problems and scheduling sub-problems in the problem; besides, in order to cope with the multi-stage batch processing and reentry scheduling characteristics in the problem, a Markov decision process considering the characteristics of the two agents is designed, and the Markov decision process comprises states, actions and rewards. Furthermore, an action selection strategy and a soft start target network updating strategy based on a mask combined with an epsilon-greedy strategy are provided, so that the efficiency and generalization ability are improved. The method has a remarkable effect on solving the dynamic scheduling problem of the reentrant hybrid flow shop with the batch processor.

The invention relates to the technical field of enterprise data management, in particular to a lightweight-based enterprise data dynamic integrated management system, which is characterized in that an acquisition module is used for deploying edge computing nodes, receiving multi-source heterogeneous information streams from manufacturing execution systems and equipment logs, dynamically analyzing and standardizing the information streams, and adding metadata tags; uploading is carried out in a batch processing mode; the map construction module is used for constructing a semiconductor blood relationship map by taking the standardized key information as a blood relationship clue; a graph database is used for efficient storage, and a RESTful API interface is configured to support batch import, so that data storage and relevance expression are more flexible and efficient; the prediction module performs reasoning on the atlas by adopting a graph neural network to generate predictive risk distribution, and a correlation analysis set generated by the prediction module is stored back to the atlas in a structured manner; by introducing a multi-thread concurrent write-in and lock mechanism, the atlas supports complex combination query based on a Cypher query language, and supports multi-level and traceability query.