2363 results about "Network layer" patented technology

The invention discloses a mechanical equipment state monitoring method and system based on multiple sensors, and the method comprises the five core steps: multi-modal data collection and preprocessing, dynamic feature fusion, adaptive threshold diagnosis, digital twin fault tracing and predictive maintenance decision. All-domain coverage of equipment is realized through a three-layer sensor network architecture, the problems of data synchronization and interference resistance are solved by utilizing a temperature and vibration integrated sensor, deep fusion and anomaly detection of multi-source data are realized in combination with an attention mechanism, a Gaussian mixture model, a three-dimensional convolutional neural network and the like, and finally a precise maintenance strategy is generated through digital twinning and reinforcement learning. The multi-sensor-based mechanical equipment state monitoring system comprises a sensor network layer, an edge computing layer, a cloud platform layer and a man-machine interaction layer, supports federated learning to protect data privacy, improves real-time diagnosis capability through edge-cloud collaboration, and enhances a reality interface to realize intelligent operation and maintenance interaction.

The invention relates to the technical field of part detection, and discloses a part defect automatic detection method based on machine vision. The method comprises the following steps: firstly, acquiring three-dimensional geometric parameters of a target part, and matching a historical defect sample set in a visual sample library according to the three-dimensional geometric parameters; performing defect type clustering division on the set to obtain a plurality of defect type subsets; processing the subsets one by one to execute multispectral feature extraction, and obtaining a reference detection area and a defect diffusion range parameter corresponding to each defect category; utilizing defect diffusion range parameters to configure the scanning step length of the multi-stage detection network layer, and generating a plurality of scale defect feature maps; and finally, performing cross-level association fusion on the feature maps to generate a fusion defect feature map, and outputting the fusion defect feature map as a final detection result. According to the method, three-dimensional geometric features and historical data are combined, and the comprehensiveness and accuracy of part defect detection are improved through multispectral extraction, adaptive scanning and feature fusion.

The invention discloses a land-sea-air-space holographic sensing and collaborative decision-making system based on multi-mode edge intelligence. The system comprises a sensing layer which is used for carrying out three-dimensional monitoring on a ship driving process, the sea, the sky, a shore base and a space formed by the ship driving process, the sea, the sky, the shore base and the sea, the sky and the shore base; the network layer is used for constructing a global communication basis, preprocessing monitoring data, judging whether the ship has an abnormal condition or not, and realizing data transmission of the ocean, the sky, a shore base and a space formed by the ocean, the sky and the shore base; and the application layer is used for judging whether an abnormal condition exists in the ship driving process or not based on the data of the ocean, the sky, the shore base and the space formed by the ocean, the sky and the shore base transmitted by the network layer, performing collision early warning decision based on the abnormal condition, and performing dynamic channel capacity prediction. And navigation guidance and route tracking in extreme weather are carried out based on environmental risk early warning, underwater obstacle collision is avoided, and early warning information and decision information are fed back to a sensing layer.

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.

A method is provided for processing data in a neural network system. The method includes receiving input data; processing the input data through a first set of neural network layers configured to perform data processing using MatMul-free techniques to produce intermediate data; further processing the intermediate data through a second set of neural network layers configured to simulate spiking neural network (SNN) functionalities using MatMul-free techniques; and outputting a result based on the processed data from the second set of neural network layers.

The invention discloses a multi-modal attack identification method fusing BMama and difference to guide trans-attention, which comprises the following steps: simulating a false data injection attack, a denial of service attack, an address resolution protocol spoofing attack and a domain name system spoofing attack, collecting physical layer sensor data and network layer flow data, and preprocessing multi-modal data; bMama is constructed to perform dynamic time modeling on multi-modal data, a graph neural network is combined to adversariate a variational auto-encoder, features of a power grid system topology and a communication topology structure are fused, and robustness of potential representation is enhanced through adversarial training; the method comprises the following steps of: guiding feature complementary fusion by using modal difference through a difference guide iteration cross-attention fusion mechanism, improving the capability of distinguishing complex attacks, finally carrying out attack detection and classification on fused modals, and executing end-to-end optimization according to a weighted combination of loss of each part. The method can effectively detect and classify the multi-modal attack in the smart power grid, and enhances the safety and reliability of a complex system.

The invention relates to a carbon emission checking system and method based on a block chain, and the system comprises a basic resource layer which collects enterprise energy consumption data in real time, employs cloud computing resources to provide data storage and computing capability, and employs a Hash algorithm to process the enterprise energy consumption data, and obtains a data abstract; the block chain network layer carries out distributed storage through an alliance chain architecture, carries out consensus evidence storage on the data abstract by adopting a PBFT consensus algorithm, and generates an encrypted data abstract; the intelligent contract layer receives the encrypted data abstract transmitted by the block chain network layer, and executes verification, calculation and supervision rules; and the application service layer calls the processing result of the intelligent contract layer, and respectively provides an enterprise carbon checking terminal service interface, an institution carbon checking terminal service interface and a competent department carbon supervision terminal service interface for the enterprise, a third-party checking institution and the competent department to check the carbon emission. According to the invention, high-efficiency check, high-credibility verification and whole-process traceable supervision of the carbon emission data are realized.

The invention provides an intelligent education resource sharing and authority management system based on a block chain, and belongs to the technical field of intelligent education, and the system comprises a block chain network layer, a resource right confirmation module, an intelligent contract module, a distributed storage network, a cross-chain interaction gateway and a dynamic optimization module, comprising a resource authentication chain, an authority management chain and a cross-chain interaction chain, and the chains realize data intercommunication through relay nodes; the resource right confirmation module adopts a three-level Hash nested structure to generate a non-tampering digital fingerprint, and binding and uplink the educational resource metadata and the creator DID; the intelligent contract module comprises a dynamic authority management contract and a resource transaction contract, and supports an access control strategy based on context awareness. According to the intelligent education resource sharing system, the core problems that the right of the education resources is difficult to confirm, the sharing efficiency is low, and the right management is inflexible are solved, and the safe, intelligent and extensible intelligent education resource sharing system is constructed.

A hybrid neural network architecture is disclosed that integrates matrix multiplication-free (MatMul-free) transformation layers with spiking neural network (SNN) layers for efficient, low-power computation. The system includes an interface module configured to convert intermediate continuous-valued data from MatMul-free layers into a spike-compatible format using encoding techniques such as rate coding, phase coding, or threshold-based conversion. The SNN layers process the spike-encoded data in an event-driven manner, enabling sparse, temporal inference. Training is supported by a hybrid optimization strategy combining backpropagation in MatMul-free components with surrogate gradient descent or spike-timing-dependent plasticity (STDP) in SNN layers. The architecture reduces computational complexity, supports real-time adaptability, and enables deployment in energy-constrained environments such as edge devices and neuromorphic platforms. The system may be implemented in hardware, software, or a co-designed pipeline optimized for dynamic sensor data, control signals, or continuous inference tasks.

The invention relates to the technical field of chemical enterprise production management, in particular to a chemical enterprise safety production informatization management system which comprises a sensing network layer architecture, a digital twin management platform, a risk management and control and decision center, a process closed-loop management center and an emergency cooperative processing platform. According to the chemical enterprise safety production informatization management system and method, through construction of a chemical knowledge graph, on the basis of a dynamic risk matrix and an AI prediction model library, equipment remaining service life prediction, process tiny anomaly capture and accident consequence simulation processing are realized; meanwhile, a root cause analysis module is used for associating low-level alarm and traversing a knowledge graph to automatically infer a fault root, physical equipment and a virtual model are bound through an entity-model mapping engine, the model state is dynamically updated in combination with a real-time rendering technology, and technological parameter optimization, accident deduction and scheme verification can be completed in an analogue simulation engine; and the management intuition and the decision-making scientificity are effectively improved.

The invention belongs to the technical field of intelligent engineering management, and discloses an automatic monitoring and control method of an engineering management system based on the Internet of Things. According to the method, a four-layer Internet of Things architecture comprising a sensing layer, a network layer, a platform layer and an application layer is constructed, and the four-layer Internet of Things architecture is uploaded to a cloud platform through a 5G / narrowband Internet of Things dual-mode transmission channel. A digital twinborn technology is innovatively adopted to construct a three-dimensional visual engineering model, intelligent identification and prediction of abnormal working conditions are realized through a machine learning algorithm, and a multi-stage linkage control mechanism is established. And when construction deviation or equipment failure is detected, the system automatically generates an optimization control strategy and issues the optimization control strategy to the execution terminal, so that accurate regulation and control of the construction machinery and intelligent pushing of early warning information are realized. According to the method, a manual inspection mode of traditional engineering management is broken through, full-process automatic supervision is realized through data fusion analysis and closed-loop control, the construction quality supervision precision is effectively improved by more than 30%, the safety accident rate is reduced by 50%, and the engineering management efficiency is remarkably improved.

The invention belongs to the technical field of base station equipment management, and discloses a base station equipment management method and system based on big data. The method comprises the following steps: firstly, collecting security situation data of a physical layer, a network layer and an application layer, extracting time sequence behavior characteristics, performing cross-layer correlation analysis, and constructing an equipment security credibility dynamic evaluation model; then, identifying vulnerability indexes of control nodes according to the trust attenuation curve, and constructing a cascade risk conduction model in combination with a topological connection relationship; dynamically dividing a security isolation domain based on the model and generating protection parameters and control rules; further, a differentiated security policy is configured, and a cross-domain collaborative response channel is established; and finally, dynamically adjusting the isolation domain boundary and the security policy by monitoring the security event frequency and the interception success rate in real time. According to the invention, the conversion from passive defense to active prediction is realized, and the safety protection capability and operation stability of the base station equipment are improved.

Apparatuses, systems, and techniques to perform a neural network. In at least one embodiment, a neural network is performed by at least combining nodes of a graph based, at least in part, on computing resources to perform operations corresponding to the nodes of the graph.

The invention discloses a block chain-based scheduling instruction trusted storage system, which relates to the technical field of block chains, and comprises a block chain network layer, an instruction acquisition module, an instruction verification module, a cross-chain storage module, a trusted tracing interface, an instruction life cycle management smart contract and a quantum security module, the block chain network layer comprises a plurality of block chain service units deployed at power dispatching nodes, the instruction acquisition module is used for acquiring a dispatching instruction data set and an associated digital signature generated by a dispatching terminal, and the instruction verification module is configured with a compliance verification rule base and multi-level verification logic. And the cross-chain storage module realizes a sub-chain storage architecture of scheduling instruction metadata and content data. According to the method, a double-chain architecture in which a metadata chain and a content chain are separated is adopted, and an improved Merkletree cross-chain verification technology is combined, so that on the premise of ensuring data privacy, cross-regional instruction synchronization delay is reduced, and meanwhile, fine-grained access control of sensitive instruction content is realized.

The invention discloses a dynamic sea condition ship-machine cooperative attitude control system and method for sea grass transplantation, and belongs to the crossing field of marine ecological restoration and intelligent ship control. The system comprises a mother ship attitude control layer, a communication management layer, an underwater operation end and a sensor network layer, the mother ship attitude control layer, the communication management layer, the underwater operation end and sensor network layer and the mother ship attitude control layer are sequentially connected through lines; the method integrates inertial navigation, visual measurement, event-triggered communication and adaptive filtering technologies, realizes high-precision attitude synchronization and stable operation of the ship and the underwater operation device in sea conditions of four levels and below, and can be widely applied to marine ecological engineering scenes such as seaweed bed restoration, coral transplantation and submerged vegetation reconstruction. And the operation efficiency and the environmental adaptability are effectively improved.

The invention belongs to the technical field of medical risk early warning, and discloses a medical risk dynamic early warning and intervention decision-making system based on a multi-mode Internet of Things and AI, which comprises a sensing layer, a network layer, a data processing layer, an AI analysis layer and an application layer, the sensing layer comprises a wearable device, an environment sensor, a medical device, a non-contact monitoring device and an implantation device; the network layer constructs a data transmission channel and is provided with an edge computing node; the data processing layer adopts a multi-modal data fusion engine, is responsible for data alignment, data cleaning and feature extraction, and constructs a knowledge graph; the AI analysis layer comprises a dynamic risk early warning model and an intervention decision engine; the application layer is provided with a three-level early warning board, an intelligent intervention terminal and a block chain evidence storage platform. According to the invention, the early warning window is advanced, and the recognition accuracy is improved; the system promotes a medical monitoring mode to be changed from post response to active defense, the medical accident rate is further reduced, and a technical foundation is provided for constructing a new generation of smart hospitals.

The invention belongs to the technical field of seismic equipment monitoring, and provides a seismic network communication fault positioning method based on multi-dimensional protocol diagnosis, which comprises physical layer IOT analysis, network layer protocol analysis, transport layer protocol analysis, application layer protocol analysis, a protection mechanism adaptive adjustment algorithm and a cross-layer collaborative analysis state mechanism. According to the method, multi-dimensional protocol fault analysis is realized, and the analysis accuracy is higher than that of a single-dimensional mode through analysis of application, transmission, network and physical four-layer protocols. Analysis is carried out through the sequence from the physical layer to the application layer, positioning can be completed after the problem is positioned on the upper layer, and high analysis efficiency is achieved. According to the method, the analysis process is completed mainly in a network detection mode, only physical layer analysis needs IOT hardware equipment to participate, the analysis can be achieved in a pure soft mode, and the method has the good cost advantage.

The provided is an anti-radiation low-latency chip for neural network inference acceleration. The following steps are included: deploying a neural network inference acceleration chip at a frontend of a detector, using a streaming architecture to correspond each pipeline stage to each major neural network layer, balancing a limited on-chip memory resource and support for a large-sized input, and constructing layer parallelism, channel parallelism, and convolution kernel parallelism. This application proposes to deploy an anti-radiation, low-latency, and efficient chip for convolutional neural network (CNN) inference acceleration is deployed at the frontend of the detector to improve an intelligence level of future detector hardware. To this end, a fine-grained streaming architecture, and fine-grained storage management, flexible compression and quantization, and anti-radiation digital chip design technologies are proposed to achieve a high throughput and a low on-chip memory consumption while achieving anti-radiation and low-latency inference.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a neural network automatic pruning method based on GRPO reinforcement learning, and the method comprises the steps: introducing a dynamic scaling factor into a batch normalization layer of a to-be-pruned neural network, and calculating the importance score of each convolution layer channel of the to-be-pruned neural network in combination with an attention mechanism; s2, constructing a multi-dimensional state vector containing layer structure features based on an importance calculation result in the step S1; s2, inputting the multi-dimensional state vector constructed in S2 into a strategy network of a GRPO reinforcement learning agent, generating a pruning action by the strategy network according to state information of a current network layer, and defining the action to represent a pruning rate of the layer; according to the method, a GRPO reinforcement learning algorithm is adopted, a traditional Critic model is abandoned, the strategy calculation process is simplified through a group sampling-relative advantage estimation mechanism, and memory occupation is remarkably reduced.

The invention relates to the technical field of printed circuit board defect detection, and provides a PCB defect detection method, device and equipment based on improved YoloV11n, and the method comprises the steps: constructing and enhancing a data set; an improved YOLOv11n model is constructed, wherein a C3k2IPConv module is used for replacing C3k2 modules of p2, p4, p6 and p8 layers of a YOLOv11n backbone network; an IPConv module is used for replacing the two 3 * 3 Conv modules of the detection head part; constructing a small target detection head at the detection head part; replacing a CIoU loss function with an Inner-MPDIOU loss function at a detection head part; the enhanced data set is input into the improved YOLOv11n model for training; and the trained Yolov11n model is used to detect the PCB defect, and the defect type is obtained. According to the method, the modeling capability of the model to the edge features of the defects in the complex form is enhanced, the adaptability of the model to defect targets in different sizes is enhanced, and the instability in the training process is reduced.

The invention provides a model training method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of neural network models and model training. The specific implementation scheme is as follows: a calculation unit executes quantization matrix multiplication based on Hadamard pre-transformation on an activation tensor and a weight tensor of a target model stored in a memory so as to generate an output tensor of a linear layer based on a low-precision tensor with smaller data bit width; using the output tensor and a subsequent network layer of the target model to complete forward propagation so as to obtain a loss value; and according to the loss value, updating model parameters of the target model stored in a memory through a back propagation algorithm. By means of the technical scheme, on the premise that the model training precision is guaranteed, memory resource occupation and the calculation amount in the calculation process can be remarkably reduced, and the training cost is reduced.

The invention discloses an unmanned aerial vehicle communication data feature extraction method and an unknown type intrusion detection method. Physical layer information and network layer information of an unmanned aerial vehicle are acquired; wherein the physical layer information comprises the position, attitude, height and command type of the unmanned aerial vehicle, and the network layer information comprises an IP address, a port number, a protocol type and packet metadata; constructing an unmanned aerial vehicle state feature vector according to the physical layer information and the network layer information of the unmanned aerial vehicle; based on the trained CNN branch network, extracting communication data features used for intrusion detection in the unmanned aerial vehicle state feature vectors; a double-branch network structure of the convolutional neural network and the time sequence convolutional network is provided, a loss function is improved, an information entropy regularization item is introduced, efficient detection and distinguishing of unknown attack samples are achieved, the network structure has the advantages of being high in calculation efficiency and light in weight, and the method is suitable for large-scale popularization and application. The method is suitable for being deployed in resource-limited edge computing scenes such as unmanned aerial vehicles.

A programmable in-memory computing (IMC) accelerator for low-precision deep neural network inference, also referred to as PIMCA, is provided. Embodiments of the PIMCA integrate a large number of capacitive-coupling-based IMC static random-access memory (SRAM) macros and demonstrate large-scale integration of IMC SRAM macros. For example, a 28 nm prototype integrates 108 capacitive-coupling-based IMC SRAM macros of a total size of 3.4 megabytes (Mb), demonstrating one of the largest IMC hardware to date. In addition, a custom instruction set architecture (ISA) is developed featuring IMC and single-instruction-multiple-data (SIMD) functional units with hardware loop to support a range of deep neural network (DNN) layer types. The 28 nm prototype chip achieves a peak throughput of 4.9 tera operations per second (TOPS) and system-level peak energy-efficiency of 437 TOPS per watt (TOPS / W) at 40 megahertz (MHz) with a 1 volt (V) supply.

The invention discloses an indoor gas leakage monitoring and intelligent joint control system, and belongs to the technical field of intelligent safety monitoring systems. Comprising a sensing layer, a network layer, a control layer and a platform layer, the sensing layer comprises a multi-sensor array and an edge computing node, the multi-sensor array is combined with a catalytic combustion sensor, an infrared sensor, a semiconductor sensor and a temperature and humidity sensor, and sensor data are fused through a weighting algorithm so as to reduce the false alarm rate; a temperature and humidity sensor dynamically adjusts a detection threshold value to adapt to different climate conditions, and an edge computing node is deployed with a lightweight machine learning model. Through multi-sensor data fusion and a weighting algorithm, the false alarm rate is reduced to be smaller than 0.1% per year, environment self-adaptive calibration and AI auxiliary decision making are performed, interference of alcohol, perfume and the like is effectively eliminated, different climate conditions are adapted, leakage judgment is completed at an equipment end through edge calculation, cloud delay is avoided, a multi-stage emergency strategy is provided, and intelligent safe ecology driven by the Internet of Things is constructed.

The invention discloses a coal mine underground equipment personnel collaborative safety monitoring and risk early warning method, which comprises the following steps: deploying a sensing network, and collecting and processing personnel data and equipment data; evaluating the health state of the equipment based on the equipment data; cleaning the personnel data and then constructing a trajectory model; performing risk coupling analysis based on the three-dimensional risk identification model to obtain a comprehensive risk value; and performing grading response based on the comprehensive risk value and judging whether to perform model optimization or not. The invention further discloses a coal mine underground equipment personnel collaborative safety monitoring and risk early warning system which comprises a sensing layer, the sensing layer is connected with an analysis layer through a network layer, the analysis layer is connected with an execution layer, and the execution layer is connected with the sensing layer. The invention discloses a coal mine underground equipment personnel collaborative safety monitoring and risk early warning method and system, solves the technical bottlenecks of data splitting, response lag and poor environmental adaptability of a traditional monitoring system, and reduces the accident false alarm rate by more than 35% through spatial coupling analysis.

The invention discloses a communication network rapid adaptive control strategy generation method based on meta reinforcement learning, and relates to the field of communication network adaptive control, and the method comprises the steps: collecting and processing a physical layer signal and a network layer index, and obtaining a standardized multi-dimensional time sequence matrix; inputting the standardized multi-dimensional time sequence matrix into a hybrid encoder formed by CNN-LSTM, dynamically weighting through a self-attention mechanism, and outputting an environment feature vector; inputting the environment feature vector into a neural differential equation network, generating a strategy parameter increment and updating a strategy network parameter; and constructing a dynamic reward function based on physical layer features in the environment feature vector, and performing detection to obtain an adjusted dynamic reward value. According to the method, continuous time evolution of strategy parameters is realized through a neural differential equation network, and a dual-channel ResNet-ODE architecture is combined with a gating fusion mechanism, so that the problem of oscillation caused by discrete updating of a traditional reinforcement learning strategy is solved.

The invention relates to a computing power resource dynamic scheduling method, device and equipment based on deep reinforcement learning and a medium thereof, and the method comprises the steps: constructing a joint state vector through real-time fusion of a network layer channel state and computing layer node load data, and driving a strategy network to generate transmission parameters and resource allocation actions of cooperative control; the code modulation parameters of the wireless transmission module and the computing resource proportion of the target node are synchronously configured in the execution layer, and dynamic task scheduling in the channel decay environment is achieved; a multi-target reward mechanism is designed to couple transmission bit error rate penalty, resource utilization efficiency and task timeliness evaluation indexes, and a reinforcement learning agent is guided to balance communication stability and computing power demand conflicts; according to the method, strategy network parameters are optimized through time difference errors, closed-loop feedback is formed in combination with channel state prediction and node load updating, the problems of network and calculation layer splitting decision, insufficient dynamic adaptability and multi-target optimization imbalance in the prior art are effectively solved, and the task scheduling success rate in the time-varying wireless environment is improved.

The invention relates to the technical field of node identification, in particular to a network key node identification method fusing improved measurement and propagation influence, which comprises the following steps: setting an edge weight and a cross-layer dependency relationship of an infrastructure network; constructing weighted cross-layer local contact centrality, attenuation cross-layer path centrality and random walk centrality indexes; taking the maximum value of the three adaptive scores as an improved measure of the node; defining metric value standardization; calculating a propagation influence value, standardizing the measurement value, and carrying out weighted fusion on the measurement value and the propagation influence value to obtain a fusion score; carrying out propagation influence value convergence judgment by utilizing an LT linear threshold model; and arranging the nodes based on the fusion score value, and outputting a key node identification result. The method solves the problems that a traditional key node identification method only regards a multi-layer network as a plurality of isolated single-layer networks, lacks measurement of node heterogeneity in the multi-layer network, ignores a coupling relation between network layers and is difficult to be accurately applied to an urban multi-layer infrastructure network.

The invention discloses systems and methods for privacy-preserving digital communications compliant with frameworks such as GDPR, DPDPA, HIPAA, and PSD2. A Virtual Identity (VI) is instantiated within a secure enclave and bound to one or more Compliance Jurisdiction Tokens (CJTs). Unlike conventional tokenisation limited to payment or aliasing, the invention enables multiple concurrent VIs (Multi-VI), each scoped to a declared purpose, jurisdiction, subnet, or session. Communication is permitted only if all bound CJTs validate inline, including Multi-CJT bindings where jurisdiction, purpose, and consent must all succeed, and Multi-Purpose CJTs (MCJTs) where multiple lawful purposes must be simultaneously satisfied. Each validation produces a Ledger-Anchored Validation Receipt (LAVR) containing pseudonymised metadata, anchored into tamper-evident ledgers for transparency. Regulators access receipts through a Regulator Query Interface (RQI), enabling filtered oversight without exposure of raw identifiers. The technical effect is to transform privacy and compliance into cryptographic enforcement across device, telecom, and network layers

The invention provides an LLM reasoning-oriented heterogeneous core particle architecture simulation and search method and system, and the method comprises the steps: constructing a heterogeneous core particle joint simulation platform which integrates behavior-level modeling aiming at various core particle types, simulates the calculation and data transmission behaviors of a heterogeneous core particle architecture and power consumption area characteristics, forms a simulation architecture, and carries out the simulation of the heterogeneous core particle architecture; carrying out performance evaluation on the simulation architecture; an improved simulated annealing search strategy is adopted to explore the design space of the simulation architecture, and the strategy comprises the following steps: configuring core particles of different types or scales for core particle groups executing tasks of different layers based on calculation and memory access characteristics of different network layers of LLM by adopting packet heterogeneous search, optimizing the search process by adopting a simulated annealing algorithm integrated with Pareto frontier optimization; a hybrid parallel strategy of TP, PP, DP and EP and grouping heterogeneous search are subjected to collaborative optimization, and optimal parallelism combination and task mapping based on core particle grouping are automatically explored.